diff --git a/CHANGELOG.md b/CHANGELOG.md
index b23b959e..b286c6d3 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -20,6 +20,30 @@ You can now watch Claude work in a real Chrome window and direct it from a sideb
 
 - **Agent timeout raised to 5 minutes.** Multi-page tasks (navigating directories, filling forms across pages) need more than the previous 2-minute limit.
 
+## [0.11.21.0] - 2026-03-26
+
+### Fixed
+
+- **`/autoplan` reviews now count toward the ship readiness gate.** When `/autoplan` ran full CEO + Design + Eng reviews, `/ship` still showed "0 runs" for Eng Review because autoplan-logged entries weren't being read correctly. Now the dashboard shows source attribution (e.g., "CLEAR (PLAN via /autoplan)") so you can see exactly which tool satisfied each review.
+- **`/ship` no longer tells you to "run /review first."** Ship runs its own pre-landing review in Step 3.5 — asking you to run the same review separately was redundant. The gate is removed; ship just does it.
+- **`/land-and-deploy` now checks all 8 review types.** Previously missed `review`, `adversarial-review`, and `codex-plan-review` — if you only ran `/review` (not `/plan-eng-review`), land-and-deploy wouldn't see it.
+- **Dashboard Outside Voice row now works.** Was showing "0 runs" even after outside voices ran in `/plan-ceo-review` or `/plan-eng-review`. Now correctly maps to `codex-plan-review` entries.
+- **`/codex review` now tracks staleness.** Added the `commit` field to codex review log entries so the dashboard can detect when a codex review is outdated.
+- **`/autoplan` no longer hardcodes "clean" status.** Review log entries from autoplan used to always record `status:"clean"` even when issues were found. Now uses proper placeholder tokens that Claude substitutes with real values.
+
+## [0.11.20.0] - 2026-03-26
+
+### Added
+
+- **GitLab support for `/retro` and `/ship`.** You can now run `/ship` on GitLab repos — it creates merge requests via `glab mr create` instead of `gh pr create`. `/retro` detects default branches on both platforms. All 11 skills using `BASE_BRANCH_DETECT` automatically get GitHub, GitLab, and git-native fallback detection.
+- **GitHub Enterprise and self-hosted GitLab detection.** If the remote URL doesn't match `github.com` or `gitlab`, gstack checks `gh auth status` / `glab auth status` to detect authenticated platforms — no manual config needed.
+- **`/document-release` works on GitLab.** After `/ship` creates a merge request, the auto-invoked `/document-release` reads and updates the MR body via `glab` instead of failing silently.
+- **GitLab safety gate for `/land-and-deploy`.** Instead of silently failing on GitLab repos, `/land-and-deploy` now stops early with a clear message that GitLab merge support is not yet implemented.
+
+### Fixed
+
+- **Deduplicated gen-skill-docs resolvers.** The template generator had duplicate inline resolver functions that shadowed the modular versions, causing generated SKILL.md files to miss recent resolver updates.
+
 ## [0.11.19.0] - 2026-03-24
 
 ### Fixed
diff --git a/SKILL.md b/SKILL.md
index 6c7d67ae..26f01927 100644
--- a/SKILL.md
+++ b/SKILL.md
@@ -27,9 +27,11 @@ _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr
 find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
 _CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
+_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
 echo "BRANCH: $_BRANCH"
 echo "PROACTIVE: $_PROACTIVE"
+echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
 source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
 REPO_MODE=${REPO_MODE:-unknown}
 echo "REPO_MODE: $REPO_MODE"
@@ -47,8 +49,11 @@ echo '{"skill":"gstack","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basen
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do [ -f "$_PF" ] && ~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true; break; done
 ```
 
-If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills — only invoke
-them when the user explicitly asks. The user opted out of proactive suggestions.
+If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
+auto-invoke skills based on conversation context. Only run skills the user explicitly
+types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say:
+"I think /skillname might help here — want me to run it?" and wait for confirmation.
+The user opted out of proactive behavior.
 
 If output shows `UPGRADE_AVAILABLE <old> <new>`: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED <from> <to>`: tell user "Running gstack v{to} (just updated!)" and continue.
 
@@ -97,42 +102,44 @@ touch ~/.gstack/.telemetry-prompted
 
 This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 
+If `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: After telemetry is handled,
+ask the user about proactive behavior. Use AskUserQuestion:
+
+> gstack can proactively figure out when you might need a skill while you work —
+> like suggesting /qa when you say "does this work?" or /investigate when you hit
+> a bug. We recommend keeping this on — it speeds up every part of your workflow.
+
+Options:
+- A) Keep it on (recommended)
+- B) Turn it off — I'll type /commands myself
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set proactive true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set proactive false`
+
+Always run:
+```bash
+touch ~/.gstack/.proactive-prompted
+```
+
+This only happens once. If `PROACTIVE_PROMPTED` is `yes`, skip this entirely.
+
 ## Contributor Mode
 
-If `_CONTRIB` is `true`: you are in **contributor mode**. You're a gstack user who also helps make it better.
+If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
 
-**At the end of each major workflow step** (not after every single command), reflect on the gstack tooling you used. Rate your experience 0 to 10. If it wasn't a 10, think about why. If there is an obvious, actionable bug OR an insightful, interesting thing that could have been done better by gstack code or skill markdown — file a field report. Maybe our contributor will help make us better!
-
-**Calibration — this is the bar:** For example, `$B js "await fetch(...)"` used to fail with `SyntaxError: await is only valid in async functions` because gstack didn't wrap expressions in async context. Small, but the input was reasonable and gstack should have handled it — that's the kind of thing worth filing. Things less consequential than this, ignore.
-
-**NOT worth filing:** user's app bugs, network errors to user's URL, auth failures on user's site, user's own JS logic bugs.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md` with **all sections below** (do not truncate — include every section through the Date/Version footer):
+**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
 
+**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
 ```
 # {Title}
-
-Hey gstack team — ran into this while using /{skill-name}:
-
-**What I was trying to do:** {what the user/agent was attempting}
-**What happened instead:** {what actually happened}
-**My Rating:** {0-10} — {one sentence on why it wasn't a 10}
-
-## Steps to reproduce
+**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
+## Repro
 1. {step}
-
-## Raw output
-```
-{paste the actual error or unexpected output here}
-```
-
 ## What would make this a 10
-{one sentence: what gstack should have done differently}
-
-**Date:** {YYYY-MM-DD} | **Version:** {gstack version} | **Skill:** /{skill}
+{one sentence}
+**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
 ```
-
-Slug: lowercase, hyphens, max 60 chars (e.g. `browse-js-no-await`). Skip if file already exists. Max 3 reports per session. File inline and continue — don't stop the workflow. Tell user: "Filed gstack field report: {title}"
+Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
 
 ## Completion Status Protocol
 
diff --git a/TODOS.md b/TODOS.md
index c7617c8a..b1ade477 100644
--- a/TODOS.md
+++ b/TODOS.md
@@ -213,6 +213,18 @@ Linux cookie import shipped in v0.11.11.0 (Wave 3). Supports Chrome, Chromium, B
 
 ## Ship
 
+### GitLab support for /land-and-deploy
+
+**What:** Add GitLab MR merge + CI polling support to `/land-and-deploy` skill. Currently uses `gh pr view`, `gh pr checks`, `gh pr merge`, and `gh run list/view` in 15+ places — each needs a GitLab conditional path using `glab ci status`, `glab mr merge`, etc.
+
+**Why:** Without this, GitLab users can `/ship` (create MR) but can't `/land-and-deploy` (merge + verify). Completes the GitLab story end-to-end.
+
+**Context:** `/retro`, `/ship`, and `/document-release` now support GitLab via the multi-platform `BASE_BRANCH_DETECT` resolver. `/land-and-deploy` has deeper GitHub-specific semantics (merge queues, required checks via `gh pr checks`, deploy workflow polling) that have different shapes on GitLab. The `glab` CLI (v1.90.0) supports `glab mr merge`, `glab ci status`, `glab ci view` but with different output formats and no merge queue concept.
+
+**Effort:** L
+**Priority:** P2
+**Depends on:** None (BASE_BRANCH_DETECT multi-platform resolver is already done)
+
 ### Ship log — persistent record of /ship runs
 
 **What:** Append structured JSON entry to `.gstack/ship-log.json` at end of every /ship run (version, date, branch, PR URL, review findings, Greptile stats, todos completed, test results).
diff --git a/autoplan/SKILL.md b/autoplan/SKILL.md
index bfb2a176..aee5d372 100644
--- a/autoplan/SKILL.md
+++ b/autoplan/SKILL.md
@@ -36,9 +36,11 @@ _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr
 find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
 _CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
+_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
 echo "BRANCH: $_BRANCH"
 echo "PROACTIVE: $_PROACTIVE"
+echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
 source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
 REPO_MODE=${REPO_MODE:-unknown}
 echo "REPO_MODE: $REPO_MODE"
@@ -56,8 +58,11 @@ echo '{"skill":"autoplan","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(bas
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do [ -f "$_PF" ] && ~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true; break; done
 ```
 
-If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills — only invoke
-them when the user explicitly asks. The user opted out of proactive suggestions.
+If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
+auto-invoke skills based on conversation context. Only run skills the user explicitly
+types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say:
+"I think /skillname might help here — want me to run it?" and wait for confirmation.
+The user opted out of proactive behavior.
 
 If output shows `UPGRADE_AVAILABLE <old> <new>`: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED <from> <to>`: tell user "Running gstack v{to} (just updated!)" and continue.
 
@@ -106,6 +111,27 @@ touch ~/.gstack/.telemetry-prompted
 
 This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 
+If `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: After telemetry is handled,
+ask the user about proactive behavior. Use AskUserQuestion:
+
+> gstack can proactively figure out when you might need a skill while you work —
+> like suggesting /qa when you say "does this work?" or /investigate when you hit
+> a bug. We recommend keeping this on — it speeds up every part of your workflow.
+
+Options:
+- A) Keep it on (recommended)
+- B) Turn it off — I'll type /commands myself
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set proactive true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set proactive false`
+
+Always run:
+```bash
+touch ~/.gstack/.proactive-prompted
+```
+
+This only happens once. If `PROACTIVE_PROMPTED` is `yes`, skip this entirely.
+
 ## AskUserQuestion Format
 
 **ALWAYS follow this structure for every AskUserQuestion call:**
@@ -113,7 +139,6 @@ This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
 3. **Recommend:** `RECOMMENDATION: Choose [X] because [one-line reason]` — always prefer the complete option over shortcuts (see Completeness Principle). Include `Completeness: X/10` for each option. Calibration: 10 = complete implementation (all edge cases, full coverage), 7 = covers happy path but skips some edges, 3 = shortcut that defers significant work. If both options are 8+, pick the higher; if one is ≤5, flag it.
 4. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
-5. **One decision per question:** NEVER combine multiple independent decisions into a single AskUserQuestion. Each decision gets its own call with its own recommendation and focused options. Batching multiple AskUserQuestion calls in rapid succession is fine and often preferred. Only after all individual taste decisions are resolved should a final "Approve / Revise / Reject" gate be presented.
 
 Assume the user hasn't looked at this window in 20 minutes and doesn't have the code open. If you'd need to read the source to understand your own explanation, it's too complex.
 
@@ -121,97 +146,54 @@ Per-skill instructions may add additional formatting rules on top of this baseli
 
 ## Completeness Principle — Boil the Lake
 
-AI-assisted coding makes the marginal cost of completeness near-zero. When you present options:
+AI makes completeness near-free. Always recommend the complete option over shortcuts — the delta is minutes with CC+gstack. A "lake" (100% coverage, all edge cases) is boilable; an "ocean" (full rewrite, multi-quarter migration) is not. Boil lakes, flag oceans.
 
-- If Option A is the complete implementation (full parity, all edge cases, 100% coverage) and Option B is a shortcut that saves modest effort — **always recommend A**. The delta between 80 lines and 150 lines is meaningless with CC+gstack. "Good enough" is the wrong instinct when "complete" costs minutes more.
-- **Lake vs. ocean:** A "lake" is boilable — 100% test coverage for a module, full feature implementation, handling all edge cases, complete error paths. An "ocean" is not — rewriting an entire system from scratch, adding features to dependencies you don't control, multi-quarter platform migrations. Recommend boiling lakes. Flag oceans as out of scope.
-- **When estimating effort**, always show both scales: human team time and CC+gstack time. The compression ratio varies by task type — use this reference:
+**Effort reference** — always show both scales:
 
 | Task type | Human team | CC+gstack | Compression |
 |-----------|-----------|-----------|-------------|
-| Boilerplate / scaffolding | 2 days | 15 min | ~100x |
-| Test writing | 1 day | 15 min | ~50x |
-| Feature implementation | 1 week | 30 min | ~30x |
-| Bug fix + regression test | 4 hours | 15 min | ~20x |
-| Architecture / design | 2 days | 4 hours | ~5x |
-| Research / exploration | 1 day | 3 hours | ~3x |
+| Boilerplate | 2 days | 15 min | ~100x |
+| Tests | 1 day | 15 min | ~50x |
+| Feature | 1 week | 30 min | ~30x |
+| Bug fix | 4 hours | 15 min | ~20x |
 
-- This principle applies to test coverage, error handling, documentation, edge cases, and feature completeness. Don't skip the last 10% to "save time" — with AI, that 10% costs seconds.
+Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-**Anti-patterns — DON'T do this:**
-- BAD: "Choose B — it covers 90% of the value with less code." (If A is only 70 lines more, choose A.)
-- BAD: "We can skip edge case handling to save time." (Edge case handling costs minutes with CC.)
-- BAD: "Let's defer test coverage to a follow-up PR." (Tests are the cheapest lake to boil.)
-- BAD: Quoting only human-team effort: "This would take 2 weeks." (Say: "2 weeks human / ~1 hour CC.")
+## Repo Ownership — See Something, Say Something
 
-## Repo Ownership Mode — See Something, Say Something
+`REPO_MODE` controls how to handle issues outside your branch:
+- **`solo`** — You own everything. Investigate and offer to fix proactively.
+- **`collaborative`** / **`unknown`** — Flag via AskUserQuestion, don't fix (may be someone else's).
 
-`REPO_MODE` from the preamble tells you who owns issues in this repo:
-
-- **`solo`** — One person does 80%+ of the work. They own everything. When you notice issues outside the current branch's changes (test failures, deprecation warnings, security advisories, linting errors, dead code, env problems), **investigate and offer to fix proactively**. The solo dev is the only person who will fix it. Default to action.
-- **`collaborative`** — Multiple active contributors. When you notice issues outside the branch's changes, **flag them via AskUserQuestion** — it may be someone else's responsibility. Default to asking, not fixing.
-- **`unknown`** — Treat as collaborative (safer default — ask before fixing).
-
-**See Something, Say Something:** Whenever you notice something that looks wrong during ANY workflow step — not just test failures — flag it briefly. One sentence: what you noticed and its impact. In solo mode, follow up with "Want me to fix it?" In collaborative mode, just flag it and move on.
-
-Never let a noticed issue silently pass. The whole point is proactive communication.
+Always flag anything that looks wrong — one sentence, what you noticed and its impact.
 
 ## Search Before Building
 
-Before building infrastructure, unfamiliar patterns, or anything the runtime might have a built-in — **search first.** Read `~/.claude/skills/gstack/ETHOS.md` for the full philosophy.
+Before building anything unfamiliar, **search first.** See `~/.claude/skills/gstack/ETHOS.md`.
+- **Layer 1** (tried and true) — don't reinvent. **Layer 2** (new and popular) — scrutinize. **Layer 3** (first principles) — prize above all.
 
-**Three layers of knowledge:**
-- **Layer 1** (tried and true — in distribution). Don't reinvent the wheel. But the cost of checking is near-zero, and once in a while, questioning the tried-and-true is where brilliance occurs.
-- **Layer 2** (new and popular — search for these). But scrutinize: humans are subject to mania. Search results are inputs to your thinking, not answers.
-- **Layer 3** (first principles — prize these above all). Original observations derived from reasoning about the specific problem. The most valuable of all.
-
-**Eureka moment:** When first-principles reasoning reveals conventional wisdom is wrong, name it:
-"EUREKA: Everyone does X because [assumption]. But [evidence] shows this is wrong. Y is better because [reasoning]."
-
-Log eureka moments:
+**Eureka:** When first-principles reasoning contradicts conventional wisdom, name it and log:
 ```bash
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
-Replace SKILL_NAME and ONE_LINE_SUMMARY. Runs inline — don't stop the workflow.
-
-**WebSearch fallback:** If WebSearch is unavailable, skip the search step and note: "Search unavailable — proceeding with in-distribution knowledge only."
 
 ## Contributor Mode
 
-If `_CONTRIB` is `true`: you are in **contributor mode**. You're a gstack user who also helps make it better.
+If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
 
-**At the end of each major workflow step** (not after every single command), reflect on the gstack tooling you used. Rate your experience 0 to 10. If it wasn't a 10, think about why. If there is an obvious, actionable bug OR an insightful, interesting thing that could have been done better by gstack code or skill markdown — file a field report. Maybe our contributor will help make us better!
-
-**Calibration — this is the bar:** For example, `$B js "await fetch(...)"` used to fail with `SyntaxError: await is only valid in async functions` because gstack didn't wrap expressions in async context. Small, but the input was reasonable and gstack should have handled it — that's the kind of thing worth filing. Things less consequential than this, ignore.
-
-**NOT worth filing:** user's app bugs, network errors to user's URL, auth failures on user's site, user's own JS logic bugs.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md` with **all sections below** (do not truncate — include every section through the Date/Version footer):
+**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
 
+**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
 ```
 # {Title}
-
-Hey gstack team — ran into this while using /{skill-name}:
-
-**What I was trying to do:** {what the user/agent was attempting}
-**What happened instead:** {what actually happened}
-**My Rating:** {0-10} — {one sentence on why it wasn't a 10}
-
-## Steps to reproduce
+**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
+## Repro
 1. {step}
-
-## Raw output
-```
-{paste the actual error or unexpected output here}
-```
-
 ## What would make this a 10
-{one sentence: what gstack should have done differently}
-
-**Date:** {YYYY-MM-DD} | **Version:** {gstack version} | **Skill:** /{skill}
+{one sentence}
+**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
 ```
-
-Slug: lowercase, hyphens, max 60 chars (e.g. `browse-js-no-await`). Skip if file already exists. Max 3 reports per session. File inline and continue — don't stop the workflow. Tell user: "Filed gstack field report: {title}"
+Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
 
 ## Completion Status Protocol
 
@@ -302,22 +284,42 @@ Then write a `## GSTACK REVIEW REPORT` section to the end of the plan file:
 file you are allowed to edit in plan mode. The plan file review report is part of the
 plan's living status.
 
-## Step 0: Detect base branch
+## Step 0: Detect platform and base branch
 
-Determine which branch this PR targets. Use the result as "the base branch" in all subsequent steps.
+First, detect the git hosting platform from the remote URL:
 
-1. Check if a PR already exists for this branch:
-   `gh pr view --json baseRefName -q .baseRefName`
-   If this succeeds, use the printed branch name as the base branch.
+```bash
+git remote get-url origin 2>/dev/null
+```
 
-2. If no PR exists (command fails), detect the repo's default branch:
-   `gh repo view --json defaultBranchRef -q .defaultBranchRef.name`
+- If the URL contains "github.com" → platform is **GitHub**
+- If the URL contains "gitlab" → platform is **GitLab**
+- Otherwise, check CLI availability:
+  - `gh auth status 2>/dev/null` succeeds → platform is **GitHub** (covers GitHub Enterprise)
+  - `glab auth status 2>/dev/null` succeeds → platform is **GitLab** (covers self-hosted)
+  - Neither → **unknown** (use git-native commands only)
 
-3. If both commands fail, fall back to `main`.
+Determine which branch this PR/MR targets, or the repo's default branch if no
+PR/MR exists. Use the result as "the base branch" in all subsequent steps.
+
+**If GitHub:**
+1. `gh pr view --json baseRefName -q .baseRefName` — if succeeds, use it
+2. `gh repo view --json defaultBranchRef -q .defaultBranchRef.name` — if succeeds, use it
+
+**If GitLab:**
+1. `glab mr view -F json 2>/dev/null` and extract the `target_branch` field — if succeeds, use it
+2. `glab repo view -F json 2>/dev/null` and extract the `default_branch` field — if succeeds, use it
+
+**Git-native fallback (if unknown platform, or CLI commands fail):**
+1. `git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's|refs/remotes/origin/||'`
+2. If that fails: `git rev-parse --verify origin/main 2>/dev/null` → use `main`
+3. If that fails: `git rev-parse --verify origin/master 2>/dev/null` → use `master`
+
+If all fail, fall back to `main`.
 
 Print the detected base branch name. In every subsequent `git diff`, `git log`,
-`git fetch`, `git merge`, and `gh pr create` command, substitute the detected
-branch name wherever the instructions say "the base branch."
+`git fetch`, `git merge`, and PR/MR creation command, substitute the detected
+branch name wherever the instructions say "the base branch" or `<default>`.
 
 ---
 
@@ -927,24 +929,24 @@ AskUserQuestion options:
 
 ## Completion: Write Review Logs
 
-On approval, write 3 separate review log entries so /ship's dashboard recognizes them:
+On approval, write 3 separate review log entries so /ship's dashboard recognizes them.
+Replace TIMESTAMP, STATUS, and N with actual values from each review phase.
+STATUS is "clean" if no unresolved issues, "issues_open" otherwise.
 
 ```bash
 COMMIT=$(git rev-parse --short HEAD 2>/dev/null)
 TIMESTAMP=$(date -u +%Y-%m-%dT%H:%M:%SZ)
 
-~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"plan-ceo-review","timestamp":"'"$TIMESTAMP"'","status":"clean","unresolved":0,"critical_gaps":0,"mode":"SELECTIVE_EXPANSION","via":"autoplan","commit":"'"$COMMIT"'"}'
+~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"plan-ceo-review","timestamp":"'"$TIMESTAMP"'","status":"STATUS","unresolved":N,"critical_gaps":N,"mode":"SELECTIVE_EXPANSION","via":"autoplan","commit":"'"$COMMIT"'"}'
 
-~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"plan-eng-review","timestamp":"'"$TIMESTAMP"'","status":"clean","unresolved":0,"critical_gaps":0,"issues_found":0,"mode":"FULL_REVIEW","via":"autoplan","commit":"'"$COMMIT"'"}'
+~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"plan-eng-review","timestamp":"'"$TIMESTAMP"'","status":"STATUS","unresolved":N,"critical_gaps":N,"issues_found":N,"mode":"FULL_REVIEW","via":"autoplan","commit":"'"$COMMIT"'"}'
 ```
 
 If Phase 2 ran (UI scope):
 ```bash
-~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"plan-design-review","timestamp":"'"$TIMESTAMP"'","status":"clean","unresolved":0,"via":"autoplan","commit":"'"$COMMIT"'"}'
+~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"plan-design-review","timestamp":"'"$TIMESTAMP"'","status":"STATUS","unresolved":N,"via":"autoplan","commit":"'"$COMMIT"'"}'
 ```
 
-Replace field values with actual counts from the review.
-
 Dual voice logs (one per phase that ran):
 ```bash
 ~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"autoplan-voices","timestamp":"'"$TIMESTAMP"'","status":"STATUS","source":"SOURCE","phase":"ceo","via":"autoplan","consensus_confirmed":N,"consensus_disagree":N,"commit":"'"$COMMIT"'"}'
diff --git a/autoplan/SKILL.md.tmpl b/autoplan/SKILL.md.tmpl
index 661e8fb0..7cf78ced 100644
--- a/autoplan/SKILL.md.tmpl
+++ b/autoplan/SKILL.md.tmpl
@@ -584,24 +584,24 @@ AskUserQuestion options:
 
 ## Completion: Write Review Logs
 
-On approval, write 3 separate review log entries so /ship's dashboard recognizes them:
+On approval, write 3 separate review log entries so /ship's dashboard recognizes them.
+Replace TIMESTAMP, STATUS, and N with actual values from each review phase.
+STATUS is "clean" if no unresolved issues, "issues_open" otherwise.
 
 ```bash
 COMMIT=$(git rev-parse --short HEAD 2>/dev/null)
 TIMESTAMP=$(date -u +%Y-%m-%dT%H:%M:%SZ)
 
-~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"plan-ceo-review","timestamp":"'"$TIMESTAMP"'","status":"clean","unresolved":0,"critical_gaps":0,"mode":"SELECTIVE_EXPANSION","via":"autoplan","commit":"'"$COMMIT"'"}'
+~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"plan-ceo-review","timestamp":"'"$TIMESTAMP"'","status":"STATUS","unresolved":N,"critical_gaps":N,"mode":"SELECTIVE_EXPANSION","via":"autoplan","commit":"'"$COMMIT"'"}'
 
-~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"plan-eng-review","timestamp":"'"$TIMESTAMP"'","status":"clean","unresolved":0,"critical_gaps":0,"issues_found":0,"mode":"FULL_REVIEW","via":"autoplan","commit":"'"$COMMIT"'"}'
+~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"plan-eng-review","timestamp":"'"$TIMESTAMP"'","status":"STATUS","unresolved":N,"critical_gaps":N,"issues_found":N,"mode":"FULL_REVIEW","via":"autoplan","commit":"'"$COMMIT"'"}'
 ```
 
 If Phase 2 ran (UI scope):
 ```bash
-~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"plan-design-review","timestamp":"'"$TIMESTAMP"'","status":"clean","unresolved":0,"via":"autoplan","commit":"'"$COMMIT"'"}'
+~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"plan-design-review","timestamp":"'"$TIMESTAMP"'","status":"STATUS","unresolved":N,"via":"autoplan","commit":"'"$COMMIT"'"}'
 ```
 
-Replace field values with actual counts from the review.
-
 Dual voice logs (one per phase that ran):
 ```bash
 ~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"autoplan-voices","timestamp":"'"$TIMESTAMP"'","status":"STATUS","source":"SOURCE","phase":"ceo","via":"autoplan","consensus_confirmed":N,"consensus_disagree":N,"commit":"'"$COMMIT"'"}'
diff --git a/benchmark/SKILL.md b/benchmark/SKILL.md
index 1b00ac31..d6d65ae2 100644
--- a/benchmark/SKILL.md
+++ b/benchmark/SKILL.md
@@ -29,9 +29,11 @@ _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr
 find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
 _CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
+_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
 echo "BRANCH: $_BRANCH"
 echo "PROACTIVE: $_PROACTIVE"
+echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
 source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
 REPO_MODE=${REPO_MODE:-unknown}
 echo "REPO_MODE: $REPO_MODE"
@@ -49,8 +51,11 @@ echo '{"skill":"benchmark","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(ba
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do [ -f "$_PF" ] && ~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true; break; done
 ```
 
-If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills — only invoke
-them when the user explicitly asks. The user opted out of proactive suggestions.
+If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
+auto-invoke skills based on conversation context. Only run skills the user explicitly
+types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say:
+"I think /skillname might help here — want me to run it?" and wait for confirmation.
+The user opted out of proactive behavior.
 
 If output shows `UPGRADE_AVAILABLE <old> <new>`: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED <from> <to>`: tell user "Running gstack v{to} (just updated!)" and continue.
 
@@ -99,42 +104,44 @@ touch ~/.gstack/.telemetry-prompted
 
 This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 
+If `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: After telemetry is handled,
+ask the user about proactive behavior. Use AskUserQuestion:
+
+> gstack can proactively figure out when you might need a skill while you work —
+> like suggesting /qa when you say "does this work?" or /investigate when you hit
+> a bug. We recommend keeping this on — it speeds up every part of your workflow.
+
+Options:
+- A) Keep it on (recommended)
+- B) Turn it off — I'll type /commands myself
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set proactive true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set proactive false`
+
+Always run:
+```bash
+touch ~/.gstack/.proactive-prompted
+```
+
+This only happens once. If `PROACTIVE_PROMPTED` is `yes`, skip this entirely.
+
 ## Contributor Mode
 
-If `_CONTRIB` is `true`: you are in **contributor mode**. You're a gstack user who also helps make it better.
+If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
 
-**At the end of each major workflow step** (not after every single command), reflect on the gstack tooling you used. Rate your experience 0 to 10. If it wasn't a 10, think about why. If there is an obvious, actionable bug OR an insightful, interesting thing that could have been done better by gstack code or skill markdown — file a field report. Maybe our contributor will help make us better!
-
-**Calibration — this is the bar:** For example, `$B js "await fetch(...)"` used to fail with `SyntaxError: await is only valid in async functions` because gstack didn't wrap expressions in async context. Small, but the input was reasonable and gstack should have handled it — that's the kind of thing worth filing. Things less consequential than this, ignore.
-
-**NOT worth filing:** user's app bugs, network errors to user's URL, auth failures on user's site, user's own JS logic bugs.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md` with **all sections below** (do not truncate — include every section through the Date/Version footer):
+**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
 
+**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
 ```
 # {Title}
-
-Hey gstack team — ran into this while using /{skill-name}:
-
-**What I was trying to do:** {what the user/agent was attempting}
-**What happened instead:** {what actually happened}
-**My Rating:** {0-10} — {one sentence on why it wasn't a 10}
-
-## Steps to reproduce
+**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
+## Repro
 1. {step}
-
-## Raw output
-```
-{paste the actual error or unexpected output here}
-```
-
 ## What would make this a 10
-{one sentence: what gstack should have done differently}
-
-**Date:** {YYYY-MM-DD} | **Version:** {gstack version} | **Skill:** /{skill}
+{one sentence}
+**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
 ```
-
-Slug: lowercase, hyphens, max 60 chars (e.g. `browse-js-no-await`). Skip if file already exists. Max 3 reports per session. File inline and continue — don't stop the workflow. Tell user: "Filed gstack field report: {title}"
+Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
 
 ## Completion Status Protocol
 
diff --git a/browse/SKILL.md b/browse/SKILL.md
index bcec129e..928f474f 100644
--- a/browse/SKILL.md
+++ b/browse/SKILL.md
@@ -29,9 +29,11 @@ _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr
 find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
 _CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
+_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
 echo "BRANCH: $_BRANCH"
 echo "PROACTIVE: $_PROACTIVE"
+echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
 source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
 REPO_MODE=${REPO_MODE:-unknown}
 echo "REPO_MODE: $REPO_MODE"
@@ -49,8 +51,11 @@ echo '{"skill":"browse","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basen
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do [ -f "$_PF" ] && ~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true; break; done
 ```
 
-If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills — only invoke
-them when the user explicitly asks. The user opted out of proactive suggestions.
+If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
+auto-invoke skills based on conversation context. Only run skills the user explicitly
+types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say:
+"I think /skillname might help here — want me to run it?" and wait for confirmation.
+The user opted out of proactive behavior.
 
 If output shows `UPGRADE_AVAILABLE <old> <new>`: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED <from> <to>`: tell user "Running gstack v{to} (just updated!)" and continue.
 
@@ -99,42 +104,44 @@ touch ~/.gstack/.telemetry-prompted
 
 This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 
+If `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: After telemetry is handled,
+ask the user about proactive behavior. Use AskUserQuestion:
+
+> gstack can proactively figure out when you might need a skill while you work —
+> like suggesting /qa when you say "does this work?" or /investigate when you hit
+> a bug. We recommend keeping this on — it speeds up every part of your workflow.
+
+Options:
+- A) Keep it on (recommended)
+- B) Turn it off — I'll type /commands myself
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set proactive true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set proactive false`
+
+Always run:
+```bash
+touch ~/.gstack/.proactive-prompted
+```
+
+This only happens once. If `PROACTIVE_PROMPTED` is `yes`, skip this entirely.
+
 ## Contributor Mode
 
-If `_CONTRIB` is `true`: you are in **contributor mode**. You're a gstack user who also helps make it better.
+If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
 
-**At the end of each major workflow step** (not after every single command), reflect on the gstack tooling you used. Rate your experience 0 to 10. If it wasn't a 10, think about why. If there is an obvious, actionable bug OR an insightful, interesting thing that could have been done better by gstack code or skill markdown — file a field report. Maybe our contributor will help make us better!
-
-**Calibration — this is the bar:** For example, `$B js "await fetch(...)"` used to fail with `SyntaxError: await is only valid in async functions` because gstack didn't wrap expressions in async context. Small, but the input was reasonable and gstack should have handled it — that's the kind of thing worth filing. Things less consequential than this, ignore.
-
-**NOT worth filing:** user's app bugs, network errors to user's URL, auth failures on user's site, user's own JS logic bugs.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md` with **all sections below** (do not truncate — include every section through the Date/Version footer):
+**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
 
+**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
 ```
 # {Title}
-
-Hey gstack team — ran into this while using /{skill-name}:
-
-**What I was trying to do:** {what the user/agent was attempting}
-**What happened instead:** {what actually happened}
-**My Rating:** {0-10} — {one sentence on why it wasn't a 10}
-
-## Steps to reproduce
+**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
+## Repro
 1. {step}
-
-## Raw output
-```
-{paste the actual error or unexpected output here}
-```
-
 ## What would make this a 10
-{one sentence: what gstack should have done differently}
-
-**Date:** {YYYY-MM-DD} | **Version:** {gstack version} | **Skill:** /{skill}
+{one sentence}
+**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
 ```
-
-Slug: lowercase, hyphens, max 60 chars (e.g. `browse-js-no-await`). Skip if file already exists. Max 3 reports per session. File inline and continue — don't stop the workflow. Tell user: "Filed gstack field report: {title}"
+Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
 
 ## Completion Status Protocol
 
diff --git a/canary/SKILL.md b/canary/SKILL.md
index fc04b672..08903c71 100644
--- a/canary/SKILL.md
+++ b/canary/SKILL.md
@@ -29,9 +29,11 @@ _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr
 find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
 _CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
+_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
 echo "BRANCH: $_BRANCH"
 echo "PROACTIVE: $_PROACTIVE"
+echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
 source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
 REPO_MODE=${REPO_MODE:-unknown}
 echo "REPO_MODE: $REPO_MODE"
@@ -49,8 +51,11 @@ echo '{"skill":"canary","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basen
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do [ -f "$_PF" ] && ~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true; break; done
 ```
 
-If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills — only invoke
-them when the user explicitly asks. The user opted out of proactive suggestions.
+If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
+auto-invoke skills based on conversation context. Only run skills the user explicitly
+types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say:
+"I think /skillname might help here — want me to run it?" and wait for confirmation.
+The user opted out of proactive behavior.
 
 If output shows `UPGRADE_AVAILABLE <old> <new>`: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED <from> <to>`: tell user "Running gstack v{to} (just updated!)" and continue.
 
@@ -99,6 +104,27 @@ touch ~/.gstack/.telemetry-prompted
 
 This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 
+If `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: After telemetry is handled,
+ask the user about proactive behavior. Use AskUserQuestion:
+
+> gstack can proactively figure out when you might need a skill while you work —
+> like suggesting /qa when you say "does this work?" or /investigate when you hit
+> a bug. We recommend keeping this on — it speeds up every part of your workflow.
+
+Options:
+- A) Keep it on (recommended)
+- B) Turn it off — I'll type /commands myself
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set proactive true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set proactive false`
+
+Always run:
+```bash
+touch ~/.gstack/.proactive-prompted
+```
+
+This only happens once. If `PROACTIVE_PROMPTED` is `yes`, skip this entirely.
+
 ## AskUserQuestion Format
 
 **ALWAYS follow this structure for every AskUserQuestion call:**
@@ -106,7 +132,6 @@ This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
 3. **Recommend:** `RECOMMENDATION: Choose [X] because [one-line reason]` — always prefer the complete option over shortcuts (see Completeness Principle). Include `Completeness: X/10` for each option. Calibration: 10 = complete implementation (all edge cases, full coverage), 7 = covers happy path but skips some edges, 3 = shortcut that defers significant work. If both options are 8+, pick the higher; if one is ≤5, flag it.
 4. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
-5. **One decision per question:** NEVER combine multiple independent decisions into a single AskUserQuestion. Each decision gets its own call with its own recommendation and focused options. Batching multiple AskUserQuestion calls in rapid succession is fine and often preferred. Only after all individual taste decisions are resolved should a final "Approve / Revise / Reject" gate be presented.
 
 Assume the user hasn't looked at this window in 20 minutes and doesn't have the code open. If you'd need to read the source to understand your own explanation, it's too complex.
 
@@ -114,65 +139,36 @@ Per-skill instructions may add additional formatting rules on top of this baseli
 
 ## Completeness Principle — Boil the Lake
 
-AI-assisted coding makes the marginal cost of completeness near-zero. When you present options:
+AI makes completeness near-free. Always recommend the complete option over shortcuts — the delta is minutes with CC+gstack. A "lake" (100% coverage, all edge cases) is boilable; an "ocean" (full rewrite, multi-quarter migration) is not. Boil lakes, flag oceans.
 
-- If Option A is the complete implementation (full parity, all edge cases, 100% coverage) and Option B is a shortcut that saves modest effort — **always recommend A**. The delta between 80 lines and 150 lines is meaningless with CC+gstack. "Good enough" is the wrong instinct when "complete" costs minutes more.
-- **Lake vs. ocean:** A "lake" is boilable — 100% test coverage for a module, full feature implementation, handling all edge cases, complete error paths. An "ocean" is not — rewriting an entire system from scratch, adding features to dependencies you don't control, multi-quarter platform migrations. Recommend boiling lakes. Flag oceans as out of scope.
-- **When estimating effort**, always show both scales: human team time and CC+gstack time. The compression ratio varies by task type — use this reference:
+**Effort reference** — always show both scales:
 
 | Task type | Human team | CC+gstack | Compression |
 |-----------|-----------|-----------|-------------|
-| Boilerplate / scaffolding | 2 days | 15 min | ~100x |
-| Test writing | 1 day | 15 min | ~50x |
-| Feature implementation | 1 week | 30 min | ~30x |
-| Bug fix + regression test | 4 hours | 15 min | ~20x |
-| Architecture / design | 2 days | 4 hours | ~5x |
-| Research / exploration | 1 day | 3 hours | ~3x |
+| Boilerplate | 2 days | 15 min | ~100x |
+| Tests | 1 day | 15 min | ~50x |
+| Feature | 1 week | 30 min | ~30x |
+| Bug fix | 4 hours | 15 min | ~20x |
 
-- This principle applies to test coverage, error handling, documentation, edge cases, and feature completeness. Don't skip the last 10% to "save time" — with AI, that 10% costs seconds.
-
-**Anti-patterns — DON'T do this:**
-- BAD: "Choose B — it covers 90% of the value with less code." (If A is only 70 lines more, choose A.)
-- BAD: "We can skip edge case handling to save time." (Edge case handling costs minutes with CC.)
-- BAD: "Let's defer test coverage to a follow-up PR." (Tests are the cheapest lake to boil.)
-- BAD: Quoting only human-team effort: "This would take 2 weeks." (Say: "2 weeks human / ~1 hour CC.")
+Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
 ## Contributor Mode
 
-If `_CONTRIB` is `true`: you are in **contributor mode**. You're a gstack user who also helps make it better.
+If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
 
-**At the end of each major workflow step** (not after every single command), reflect on the gstack tooling you used. Rate your experience 0 to 10. If it wasn't a 10, think about why. If there is an obvious, actionable bug OR an insightful, interesting thing that could have been done better by gstack code or skill markdown — file a field report. Maybe our contributor will help make us better!
-
-**Calibration — this is the bar:** For example, `$B js "await fetch(...)"` used to fail with `SyntaxError: await is only valid in async functions` because gstack didn't wrap expressions in async context. Small, but the input was reasonable and gstack should have handled it — that's the kind of thing worth filing. Things less consequential than this, ignore.
-
-**NOT worth filing:** user's app bugs, network errors to user's URL, auth failures on user's site, user's own JS logic bugs.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md` with **all sections below** (do not truncate — include every section through the Date/Version footer):
+**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
 
+**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
 ```
 # {Title}
-
-Hey gstack team — ran into this while using /{skill-name}:
-
-**What I was trying to do:** {what the user/agent was attempting}
-**What happened instead:** {what actually happened}
-**My Rating:** {0-10} — {one sentence on why it wasn't a 10}
-
-## Steps to reproduce
+**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
+## Repro
 1. {step}
-
-## Raw output
-```
-{paste the actual error or unexpected output here}
-```
-
 ## What would make this a 10
-{one sentence: what gstack should have done differently}
-
-**Date:** {YYYY-MM-DD} | **Version:** {gstack version} | **Skill:** /{skill}
+{one sentence}
+**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
 ```
-
-Slug: lowercase, hyphens, max 60 chars (e.g. `browse-js-no-await`). Skip if file already exists. Max 3 reports per session. File inline and continue — don't stop the workflow. Tell user: "Filed gstack field report: {title}"
+Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
 
 ## Completion Status Protocol
 
@@ -282,22 +278,42 @@ If `NEEDS_SETUP`:
 2. Run: `cd <SKILL_DIR> && ./setup`
 3. If `bun` is not installed: `curl -fsSL https://bun.sh/install | bash`
 
-## Step 0: Detect base branch
+## Step 0: Detect platform and base branch
 
-Determine which branch this PR targets. Use the result as "the base branch" in all subsequent steps.
+First, detect the git hosting platform from the remote URL:
 
-1. Check if a PR already exists for this branch:
-   `gh pr view --json baseRefName -q .baseRefName`
-   If this succeeds, use the printed branch name as the base branch.
+```bash
+git remote get-url origin 2>/dev/null
+```
 
-2. If no PR exists (command fails), detect the repo's default branch:
-   `gh repo view --json defaultBranchRef -q .defaultBranchRef.name`
+- If the URL contains "github.com" → platform is **GitHub**
+- If the URL contains "gitlab" → platform is **GitLab**
+- Otherwise, check CLI availability:
+  - `gh auth status 2>/dev/null` succeeds → platform is **GitHub** (covers GitHub Enterprise)
+  - `glab auth status 2>/dev/null` succeeds → platform is **GitLab** (covers self-hosted)
+  - Neither → **unknown** (use git-native commands only)
 
-3. If both commands fail, fall back to `main`.
+Determine which branch this PR/MR targets, or the repo's default branch if no
+PR/MR exists. Use the result as "the base branch" in all subsequent steps.
+
+**If GitHub:**
+1. `gh pr view --json baseRefName -q .baseRefName` — if succeeds, use it
+2. `gh repo view --json defaultBranchRef -q .defaultBranchRef.name` — if succeeds, use it
+
+**If GitLab:**
+1. `glab mr view -F json 2>/dev/null` and extract the `target_branch` field — if succeeds, use it
+2. `glab repo view -F json 2>/dev/null` and extract the `default_branch` field — if succeeds, use it
+
+**Git-native fallback (if unknown platform, or CLI commands fail):**
+1. `git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's|refs/remotes/origin/||'`
+2. If that fails: `git rev-parse --verify origin/main 2>/dev/null` → use `main`
+3. If that fails: `git rev-parse --verify origin/master 2>/dev/null` → use `master`
+
+If all fail, fall back to `main`.
 
 Print the detected base branch name. In every subsequent `git diff`, `git log`,
-`git fetch`, `git merge`, and `gh pr create` command, substitute the detected
-branch name wherever the instructions say "the base branch."
+`git fetch`, `git merge`, and PR/MR creation command, substitute the detected
+branch name wherever the instructions say "the base branch" or `<default>`.
 
 ---
 
diff --git a/codex/SKILL.md b/codex/SKILL.md
index 9709fba1..ec9eea7c 100644
--- a/codex/SKILL.md
+++ b/codex/SKILL.md
@@ -30,9 +30,11 @@ _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr
 find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
 _CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
+_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
 echo "BRANCH: $_BRANCH"
 echo "PROACTIVE: $_PROACTIVE"
+echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
 source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
 REPO_MODE=${REPO_MODE:-unknown}
 echo "REPO_MODE: $REPO_MODE"
@@ -50,8 +52,11 @@ echo '{"skill":"codex","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basena
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do [ -f "$_PF" ] && ~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true; break; done
 ```
 
-If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills — only invoke
-them when the user explicitly asks. The user opted out of proactive suggestions.
+If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
+auto-invoke skills based on conversation context. Only run skills the user explicitly
+types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say:
+"I think /skillname might help here — want me to run it?" and wait for confirmation.
+The user opted out of proactive behavior.
 
 If output shows `UPGRADE_AVAILABLE <old> <new>`: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED <from> <to>`: tell user "Running gstack v{to} (just updated!)" and continue.
 
@@ -100,6 +105,27 @@ touch ~/.gstack/.telemetry-prompted
 
 This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 
+If `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: After telemetry is handled,
+ask the user about proactive behavior. Use AskUserQuestion:
+
+> gstack can proactively figure out when you might need a skill while you work —
+> like suggesting /qa when you say "does this work?" or /investigate when you hit
+> a bug. We recommend keeping this on — it speeds up every part of your workflow.
+
+Options:
+- A) Keep it on (recommended)
+- B) Turn it off — I'll type /commands myself
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set proactive true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set proactive false`
+
+Always run:
+```bash
+touch ~/.gstack/.proactive-prompted
+```
+
+This only happens once. If `PROACTIVE_PROMPTED` is `yes`, skip this entirely.
+
 ## AskUserQuestion Format
 
 **ALWAYS follow this structure for every AskUserQuestion call:**
@@ -107,7 +133,6 @@ This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
 3. **Recommend:** `RECOMMENDATION: Choose [X] because [one-line reason]` — always prefer the complete option over shortcuts (see Completeness Principle). Include `Completeness: X/10` for each option. Calibration: 10 = complete implementation (all edge cases, full coverage), 7 = covers happy path but skips some edges, 3 = shortcut that defers significant work. If both options are 8+, pick the higher; if one is ≤5, flag it.
 4. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
-5. **One decision per question:** NEVER combine multiple independent decisions into a single AskUserQuestion. Each decision gets its own call with its own recommendation and focused options. Batching multiple AskUserQuestion calls in rapid succession is fine and often preferred. Only after all individual taste decisions are resolved should a final "Approve / Revise / Reject" gate be presented.
 
 Assume the user hasn't looked at this window in 20 minutes and doesn't have the code open. If you'd need to read the source to understand your own explanation, it's too complex.
 
@@ -115,97 +140,54 @@ Per-skill instructions may add additional formatting rules on top of this baseli
 
 ## Completeness Principle — Boil the Lake
 
-AI-assisted coding makes the marginal cost of completeness near-zero. When you present options:
+AI makes completeness near-free. Always recommend the complete option over shortcuts — the delta is minutes with CC+gstack. A "lake" (100% coverage, all edge cases) is boilable; an "ocean" (full rewrite, multi-quarter migration) is not. Boil lakes, flag oceans.
 
-- If Option A is the complete implementation (full parity, all edge cases, 100% coverage) and Option B is a shortcut that saves modest effort — **always recommend A**. The delta between 80 lines and 150 lines is meaningless with CC+gstack. "Good enough" is the wrong instinct when "complete" costs minutes more.
-- **Lake vs. ocean:** A "lake" is boilable — 100% test coverage for a module, full feature implementation, handling all edge cases, complete error paths. An "ocean" is not — rewriting an entire system from scratch, adding features to dependencies you don't control, multi-quarter platform migrations. Recommend boiling lakes. Flag oceans as out of scope.
-- **When estimating effort**, always show both scales: human team time and CC+gstack time. The compression ratio varies by task type — use this reference:
+**Effort reference** — always show both scales:
 
 | Task type | Human team | CC+gstack | Compression |
 |-----------|-----------|-----------|-------------|
-| Boilerplate / scaffolding | 2 days | 15 min | ~100x |
-| Test writing | 1 day | 15 min | ~50x |
-| Feature implementation | 1 week | 30 min | ~30x |
-| Bug fix + regression test | 4 hours | 15 min | ~20x |
-| Architecture / design | 2 days | 4 hours | ~5x |
-| Research / exploration | 1 day | 3 hours | ~3x |
+| Boilerplate | 2 days | 15 min | ~100x |
+| Tests | 1 day | 15 min | ~50x |
+| Feature | 1 week | 30 min | ~30x |
+| Bug fix | 4 hours | 15 min | ~20x |
 
-- This principle applies to test coverage, error handling, documentation, edge cases, and feature completeness. Don't skip the last 10% to "save time" — with AI, that 10% costs seconds.
+Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-**Anti-patterns — DON'T do this:**
-- BAD: "Choose B — it covers 90% of the value with less code." (If A is only 70 lines more, choose A.)
-- BAD: "We can skip edge case handling to save time." (Edge case handling costs minutes with CC.)
-- BAD: "Let's defer test coverage to a follow-up PR." (Tests are the cheapest lake to boil.)
-- BAD: Quoting only human-team effort: "This would take 2 weeks." (Say: "2 weeks human / ~1 hour CC.")
+## Repo Ownership — See Something, Say Something
 
-## Repo Ownership Mode — See Something, Say Something
+`REPO_MODE` controls how to handle issues outside your branch:
+- **`solo`** — You own everything. Investigate and offer to fix proactively.
+- **`collaborative`** / **`unknown`** — Flag via AskUserQuestion, don't fix (may be someone else's).
 
-`REPO_MODE` from the preamble tells you who owns issues in this repo:
-
-- **`solo`** — One person does 80%+ of the work. They own everything. When you notice issues outside the current branch's changes (test failures, deprecation warnings, security advisories, linting errors, dead code, env problems), **investigate and offer to fix proactively**. The solo dev is the only person who will fix it. Default to action.
-- **`collaborative`** — Multiple active contributors. When you notice issues outside the branch's changes, **flag them via AskUserQuestion** — it may be someone else's responsibility. Default to asking, not fixing.
-- **`unknown`** — Treat as collaborative (safer default — ask before fixing).
-
-**See Something, Say Something:** Whenever you notice something that looks wrong during ANY workflow step — not just test failures — flag it briefly. One sentence: what you noticed and its impact. In solo mode, follow up with "Want me to fix it?" In collaborative mode, just flag it and move on.
-
-Never let a noticed issue silently pass. The whole point is proactive communication.
+Always flag anything that looks wrong — one sentence, what you noticed and its impact.
 
 ## Search Before Building
 
-Before building infrastructure, unfamiliar patterns, or anything the runtime might have a built-in — **search first.** Read `~/.claude/skills/gstack/ETHOS.md` for the full philosophy.
+Before building anything unfamiliar, **search first.** See `~/.claude/skills/gstack/ETHOS.md`.
+- **Layer 1** (tried and true) — don't reinvent. **Layer 2** (new and popular) — scrutinize. **Layer 3** (first principles) — prize above all.
 
-**Three layers of knowledge:**
-- **Layer 1** (tried and true — in distribution). Don't reinvent the wheel. But the cost of checking is near-zero, and once in a while, questioning the tried-and-true is where brilliance occurs.
-- **Layer 2** (new and popular — search for these). But scrutinize: humans are subject to mania. Search results are inputs to your thinking, not answers.
-- **Layer 3** (first principles — prize these above all). Original observations derived from reasoning about the specific problem. The most valuable of all.
-
-**Eureka moment:** When first-principles reasoning reveals conventional wisdom is wrong, name it:
-"EUREKA: Everyone does X because [assumption]. But [evidence] shows this is wrong. Y is better because [reasoning]."
-
-Log eureka moments:
+**Eureka:** When first-principles reasoning contradicts conventional wisdom, name it and log:
 ```bash
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
-Replace SKILL_NAME and ONE_LINE_SUMMARY. Runs inline — don't stop the workflow.
-
-**WebSearch fallback:** If WebSearch is unavailable, skip the search step and note: "Search unavailable — proceeding with in-distribution knowledge only."
 
 ## Contributor Mode
 
-If `_CONTRIB` is `true`: you are in **contributor mode**. You're a gstack user who also helps make it better.
+If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
 
-**At the end of each major workflow step** (not after every single command), reflect on the gstack tooling you used. Rate your experience 0 to 10. If it wasn't a 10, think about why. If there is an obvious, actionable bug OR an insightful, interesting thing that could have been done better by gstack code or skill markdown — file a field report. Maybe our contributor will help make us better!
-
-**Calibration — this is the bar:** For example, `$B js "await fetch(...)"` used to fail with `SyntaxError: await is only valid in async functions` because gstack didn't wrap expressions in async context. Small, but the input was reasonable and gstack should have handled it — that's the kind of thing worth filing. Things less consequential than this, ignore.
-
-**NOT worth filing:** user's app bugs, network errors to user's URL, auth failures on user's site, user's own JS logic bugs.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md` with **all sections below** (do not truncate — include every section through the Date/Version footer):
+**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
 
+**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
 ```
 # {Title}
-
-Hey gstack team — ran into this while using /{skill-name}:
-
-**What I was trying to do:** {what the user/agent was attempting}
-**What happened instead:** {what actually happened}
-**My Rating:** {0-10} — {one sentence on why it wasn't a 10}
-
-## Steps to reproduce
+**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
+## Repro
 1. {step}
-
-## Raw output
-```
-{paste the actual error or unexpected output here}
-```
-
 ## What would make this a 10
-{one sentence: what gstack should have done differently}
-
-**Date:** {YYYY-MM-DD} | **Version:** {gstack version} | **Skill:** /{skill}
+{one sentence}
+**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
 ```
-
-Slug: lowercase, hyphens, max 60 chars (e.g. `browse-js-no-await`). Skip if file already exists. Max 3 reports per session. File inline and continue — don't stop the workflow. Tell user: "Filed gstack field report: {title}"
+Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
 
 ## Completion Status Protocol
 
@@ -296,22 +278,42 @@ Then write a `## GSTACK REVIEW REPORT` section to the end of the plan file:
 file you are allowed to edit in plan mode. The plan file review report is part of the
 plan's living status.
 
-## Step 0: Detect base branch
+## Step 0: Detect platform and base branch
 
-Determine which branch this PR targets. Use the result as "the base branch" in all subsequent steps.
+First, detect the git hosting platform from the remote URL:
 
-1. Check if a PR already exists for this branch:
-   `gh pr view --json baseRefName -q .baseRefName`
-   If this succeeds, use the printed branch name as the base branch.
+```bash
+git remote get-url origin 2>/dev/null
+```
 
-2. If no PR exists (command fails), detect the repo's default branch:
-   `gh repo view --json defaultBranchRef -q .defaultBranchRef.name`
+- If the URL contains "github.com" → platform is **GitHub**
+- If the URL contains "gitlab" → platform is **GitLab**
+- Otherwise, check CLI availability:
+  - `gh auth status 2>/dev/null` succeeds → platform is **GitHub** (covers GitHub Enterprise)
+  - `glab auth status 2>/dev/null` succeeds → platform is **GitLab** (covers self-hosted)
+  - Neither → **unknown** (use git-native commands only)
 
-3. If both commands fail, fall back to `main`.
+Determine which branch this PR/MR targets, or the repo's default branch if no
+PR/MR exists. Use the result as "the base branch" in all subsequent steps.
+
+**If GitHub:**
+1. `gh pr view --json baseRefName -q .baseRefName` — if succeeds, use it
+2. `gh repo view --json defaultBranchRef -q .defaultBranchRef.name` — if succeeds, use it
+
+**If GitLab:**
+1. `glab mr view -F json 2>/dev/null` and extract the `target_branch` field — if succeeds, use it
+2. `glab repo view -F json 2>/dev/null` and extract the `default_branch` field — if succeeds, use it
+
+**Git-native fallback (if unknown platform, or CLI commands fail):**
+1. `git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's|refs/remotes/origin/||'`
+2. If that fails: `git rev-parse --verify origin/main 2>/dev/null` → use `main`
+3. If that fails: `git rev-parse --verify origin/master 2>/dev/null` → use `master`
+
+If all fail, fall back to `main`.
 
 Print the detected base branch name. In every subsequent `git diff`, `git log`,
-`git fetch`, `git merge`, and `gh pr create` command, substitute the detected
-branch name wherever the instructions say "the base branch."
+`git fetch`, `git merge`, and PR/MR creation command, substitute the detected
+branch name wherever the instructions say "the base branch" or `<default>`.
 
 ---
 
@@ -421,7 +423,7 @@ CROSS-MODEL ANALYSIS:
 
 7. Persist the review result:
 ```bash
-~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"codex-review","timestamp":"TIMESTAMP","status":"STATUS","gate":"GATE","findings":N,"findings_fixed":N}'
+~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"codex-review","timestamp":"TIMESTAMP","status":"STATUS","gate":"GATE","findings":N,"findings_fixed":N,"commit":"'"$(git rev-parse --short HEAD)"'"}'
 ```
 
 Substitute: TIMESTAMP (ISO 8601), STATUS ("clean" if PASS, "issues_found" if FAIL),
diff --git a/codex/SKILL.md.tmpl b/codex/SKILL.md.tmpl
index 338df93b..77021c82 100644
--- a/codex/SKILL.md.tmpl
+++ b/codex/SKILL.md.tmpl
@@ -127,7 +127,7 @@ CROSS-MODEL ANALYSIS:
 
 7. Persist the review result:
 ```bash
-~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"codex-review","timestamp":"TIMESTAMP","status":"STATUS","gate":"GATE","findings":N,"findings_fixed":N}'
+~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"codex-review","timestamp":"TIMESTAMP","status":"STATUS","gate":"GATE","findings":N,"findings_fixed":N,"commit":"'"$(git rev-parse --short HEAD)"'"}'
 ```
 
 Substitute: TIMESTAMP (ISO 8601), STATUS ("clean" if PASS, "issues_found" if FAIL),
diff --git a/connect-chrome/SKILL.md b/connect-chrome/SKILL.md
index 5d153a60..c1879b61 100644
--- a/connect-chrome/SKILL.md
+++ b/connect-chrome/SKILL.md
@@ -27,9 +27,11 @@ _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr
 find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
 _CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
+_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
 echo "BRANCH: $_BRANCH"
 echo "PROACTIVE: $_PROACTIVE"
+echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
 source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
 REPO_MODE=${REPO_MODE:-unknown}
 echo "REPO_MODE: $REPO_MODE"
@@ -47,8 +49,11 @@ echo '{"skill":"connect-chrome","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do [ -f "$_PF" ] && ~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true; break; done
 ```
 
-If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills — only invoke
-them when the user explicitly asks. The user opted out of proactive suggestions.
+If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
+auto-invoke skills based on conversation context. Only run skills the user explicitly
+types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say:
+"I think /skillname might help here — want me to run it?" and wait for confirmation.
+The user opted out of proactive behavior.
 
 If output shows `UPGRADE_AVAILABLE <old> <new>`: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED <from> <to>`: tell user "Running gstack v{to} (just updated!)" and continue.
 
@@ -97,6 +102,27 @@ touch ~/.gstack/.telemetry-prompted
 
 This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 
+If `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: After telemetry is handled,
+ask the user about proactive behavior. Use AskUserQuestion:
+
+> gstack can proactively figure out when you might need a skill while you work —
+> like suggesting /qa when you say "does this work?" or /investigate when you hit
+> a bug. We recommend keeping this on — it speeds up every part of your workflow.
+
+Options:
+- A) Keep it on (recommended)
+- B) Turn it off — I'll type /commands myself
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set proactive true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set proactive false`
+
+Always run:
+```bash
+touch ~/.gstack/.proactive-prompted
+```
+
+This only happens once. If `PROACTIVE_PROMPTED` is `yes`, skip this entirely.
+
 ## AskUserQuestion Format
 
 **ALWAYS follow this structure for every AskUserQuestion call:**
@@ -104,7 +130,6 @@ This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
 3. **Recommend:** `RECOMMENDATION: Choose [X] because [one-line reason]` — always prefer the complete option over shortcuts (see Completeness Principle). Include `Completeness: X/10` for each option. Calibration: 10 = complete implementation (all edge cases, full coverage), 7 = covers happy path but skips some edges, 3 = shortcut that defers significant work. If both options are 8+, pick the higher; if one is ≤5, flag it.
 4. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
-5. **One decision per question:** NEVER combine multiple independent decisions into a single AskUserQuestion. Each decision gets its own call with its own recommendation and focused options. Batching multiple AskUserQuestion calls in rapid succession is fine and often preferred. Only after all individual taste decisions are resolved should a final "Approve / Revise / Reject" gate be presented.
 
 Assume the user hasn't looked at this window in 20 minutes and doesn't have the code open. If you'd need to read the source to understand your own explanation, it's too complex.
 
@@ -112,97 +137,54 @@ Per-skill instructions may add additional formatting rules on top of this baseli
 
 ## Completeness Principle — Boil the Lake
 
-AI-assisted coding makes the marginal cost of completeness near-zero. When you present options:
+AI makes completeness near-free. Always recommend the complete option over shortcuts — the delta is minutes with CC+gstack. A "lake" (100% coverage, all edge cases) is boilable; an "ocean" (full rewrite, multi-quarter migration) is not. Boil lakes, flag oceans.
 
-- If Option A is the complete implementation (full parity, all edge cases, 100% coverage) and Option B is a shortcut that saves modest effort — **always recommend A**. The delta between 80 lines and 150 lines is meaningless with CC+gstack. "Good enough" is the wrong instinct when "complete" costs minutes more.
-- **Lake vs. ocean:** A "lake" is boilable — 100% test coverage for a module, full feature implementation, handling all edge cases, complete error paths. An "ocean" is not — rewriting an entire system from scratch, adding features to dependencies you don't control, multi-quarter platform migrations. Recommend boiling lakes. Flag oceans as out of scope.
-- **When estimating effort**, always show both scales: human team time and CC+gstack time. The compression ratio varies by task type — use this reference:
+**Effort reference** — always show both scales:
 
 | Task type | Human team | CC+gstack | Compression |
 |-----------|-----------|-----------|-------------|
-| Boilerplate / scaffolding | 2 days | 15 min | ~100x |
-| Test writing | 1 day | 15 min | ~50x |
-| Feature implementation | 1 week | 30 min | ~30x |
-| Bug fix + regression test | 4 hours | 15 min | ~20x |
-| Architecture / design | 2 days | 4 hours | ~5x |
-| Research / exploration | 1 day | 3 hours | ~3x |
+| Boilerplate | 2 days | 15 min | ~100x |
+| Tests | 1 day | 15 min | ~50x |
+| Feature | 1 week | 30 min | ~30x |
+| Bug fix | 4 hours | 15 min | ~20x |
 
-- This principle applies to test coverage, error handling, documentation, edge cases, and feature completeness. Don't skip the last 10% to "save time" — with AI, that 10% costs seconds.
+Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-**Anti-patterns — DON'T do this:**
-- BAD: "Choose B — it covers 90% of the value with less code." (If A is only 70 lines more, choose A.)
-- BAD: "We can skip edge case handling to save time." (Edge case handling costs minutes with CC.)
-- BAD: "Let's defer test coverage to a follow-up PR." (Tests are the cheapest lake to boil.)
-- BAD: Quoting only human-team effort: "This would take 2 weeks." (Say: "2 weeks human / ~1 hour CC.")
+## Repo Ownership — See Something, Say Something
 
-## Repo Ownership Mode — See Something, Say Something
+`REPO_MODE` controls how to handle issues outside your branch:
+- **`solo`** — You own everything. Investigate and offer to fix proactively.
+- **`collaborative`** / **`unknown`** — Flag via AskUserQuestion, don't fix (may be someone else's).
 
-`REPO_MODE` from the preamble tells you who owns issues in this repo:
-
-- **`solo`** — One person does 80%+ of the work. They own everything. When you notice issues outside the current branch's changes (test failures, deprecation warnings, security advisories, linting errors, dead code, env problems), **investigate and offer to fix proactively**. The solo dev is the only person who will fix it. Default to action.
-- **`collaborative`** — Multiple active contributors. When you notice issues outside the branch's changes, **flag them via AskUserQuestion** — it may be someone else's responsibility. Default to asking, not fixing.
-- **`unknown`** — Treat as collaborative (safer default — ask before fixing).
-
-**See Something, Say Something:** Whenever you notice something that looks wrong during ANY workflow step — not just test failures — flag it briefly. One sentence: what you noticed and its impact. In solo mode, follow up with "Want me to fix it?" In collaborative mode, just flag it and move on.
-
-Never let a noticed issue silently pass. The whole point is proactive communication.
+Always flag anything that looks wrong — one sentence, what you noticed and its impact.
 
 ## Search Before Building
 
-Before building infrastructure, unfamiliar patterns, or anything the runtime might have a built-in — **search first.** Read `~/.claude/skills/gstack/ETHOS.md` for the full philosophy.
+Before building anything unfamiliar, **search first.** See `~/.claude/skills/gstack/ETHOS.md`.
+- **Layer 1** (tried and true) — don't reinvent. **Layer 2** (new and popular) — scrutinize. **Layer 3** (first principles) — prize above all.
 
-**Three layers of knowledge:**
-- **Layer 1** (tried and true — in distribution). Don't reinvent the wheel. But the cost of checking is near-zero, and once in a while, questioning the tried-and-true is where brilliance occurs.
-- **Layer 2** (new and popular — search for these). But scrutinize: humans are subject to mania. Search results are inputs to your thinking, not answers.
-- **Layer 3** (first principles — prize these above all). Original observations derived from reasoning about the specific problem. The most valuable of all.
-
-**Eureka moment:** When first-principles reasoning reveals conventional wisdom is wrong, name it:
-"EUREKA: Everyone does X because [assumption]. But [evidence] shows this is wrong. Y is better because [reasoning]."
-
-Log eureka moments:
+**Eureka:** When first-principles reasoning contradicts conventional wisdom, name it and log:
 ```bash
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
-Replace SKILL_NAME and ONE_LINE_SUMMARY. Runs inline — don't stop the workflow.
-
-**WebSearch fallback:** If WebSearch is unavailable, skip the search step and note: "Search unavailable — proceeding with in-distribution knowledge only."
 
 ## Contributor Mode
 
-If `_CONTRIB` is `true`: you are in **contributor mode**. You're a gstack user who also helps make it better.
+If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
 
-**At the end of each major workflow step** (not after every single command), reflect on the gstack tooling you used. Rate your experience 0 to 10. If it wasn't a 10, think about why. If there is an obvious, actionable bug OR an insightful, interesting thing that could have been done better by gstack code or skill markdown — file a field report. Maybe our contributor will help make us better!
-
-**Calibration — this is the bar:** For example, `$B js "await fetch(...)"` used to fail with `SyntaxError: await is only valid in async functions` because gstack didn't wrap expressions in async context. Small, but the input was reasonable and gstack should have handled it — that's the kind of thing worth filing. Things less consequential than this, ignore.
-
-**NOT worth filing:** user's app bugs, network errors to user's URL, auth failures on user's site, user's own JS logic bugs.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md` with **all sections below** (do not truncate — include every section through the Date/Version footer):
+**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
 
+**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
 ```
 # {Title}
-
-Hey gstack team — ran into this while using /{skill-name}:
-
-**What I was trying to do:** {what the user/agent was attempting}
-**What happened instead:** {what actually happened}
-**My Rating:** {0-10} — {one sentence on why it wasn't a 10}
-
-## Steps to reproduce
+**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
+## Repro
 1. {step}
-
-## Raw output
-```
-{paste the actual error or unexpected output here}
-```
-
 ## What would make this a 10
-{one sentence: what gstack should have done differently}
-
-**Date:** {YYYY-MM-DD} | **Version:** {gstack version} | **Skill:** /{skill}
+{one sentence}
+**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
 ```
-
-Slug: lowercase, hyphens, max 60 chars (e.g. `browse-js-no-await`). Skip if file already exists. Max 3 reports per session. File inline and continue — don't stop the workflow. Tell user: "Filed gstack field report: {title}"
+Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
 
 ## Completion Status Protocol
 
diff --git a/cso/SKILL.md b/cso/SKILL.md
index 8e73b73a..3f092fd6 100644
--- a/cso/SKILL.md
+++ b/cso/SKILL.md
@@ -33,9 +33,11 @@ _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr
 find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
 _CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
+_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
 echo "BRANCH: $_BRANCH"
 echo "PROACTIVE: $_PROACTIVE"
+echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
 source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
 REPO_MODE=${REPO_MODE:-unknown}
 echo "REPO_MODE: $REPO_MODE"
@@ -53,8 +55,11 @@ echo '{"skill":"cso","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do [ -f "$_PF" ] && ~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true; break; done
 ```
 
-If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills — only invoke
-them when the user explicitly asks. The user opted out of proactive suggestions.
+If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
+auto-invoke skills based on conversation context. Only run skills the user explicitly
+types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say:
+"I think /skillname might help here — want me to run it?" and wait for confirmation.
+The user opted out of proactive behavior.
 
 If output shows `UPGRADE_AVAILABLE <old> <new>`: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED <from> <to>`: tell user "Running gstack v{to} (just updated!)" and continue.
 
@@ -103,6 +108,27 @@ touch ~/.gstack/.telemetry-prompted
 
 This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 
+If `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: After telemetry is handled,
+ask the user about proactive behavior. Use AskUserQuestion:
+
+> gstack can proactively figure out when you might need a skill while you work —
+> like suggesting /qa when you say "does this work?" or /investigate when you hit
+> a bug. We recommend keeping this on — it speeds up every part of your workflow.
+
+Options:
+- A) Keep it on (recommended)
+- B) Turn it off — I'll type /commands myself
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set proactive true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set proactive false`
+
+Always run:
+```bash
+touch ~/.gstack/.proactive-prompted
+```
+
+This only happens once. If `PROACTIVE_PROMPTED` is `yes`, skip this entirely.
+
 ## AskUserQuestion Format
 
 **ALWAYS follow this structure for every AskUserQuestion call:**
@@ -110,7 +136,6 @@ This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
 3. **Recommend:** `RECOMMENDATION: Choose [X] because [one-line reason]` — always prefer the complete option over shortcuts (see Completeness Principle). Include `Completeness: X/10` for each option. Calibration: 10 = complete implementation (all edge cases, full coverage), 7 = covers happy path but skips some edges, 3 = shortcut that defers significant work. If both options are 8+, pick the higher; if one is ≤5, flag it.
 4. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
-5. **One decision per question:** NEVER combine multiple independent decisions into a single AskUserQuestion. Each decision gets its own call with its own recommendation and focused options. Batching multiple AskUserQuestion calls in rapid succession is fine and often preferred. Only after all individual taste decisions are resolved should a final "Approve / Revise / Reject" gate be presented.
 
 Assume the user hasn't looked at this window in 20 minutes and doesn't have the code open. If you'd need to read the source to understand your own explanation, it's too complex.
 
@@ -118,65 +143,36 @@ Per-skill instructions may add additional formatting rules on top of this baseli
 
 ## Completeness Principle — Boil the Lake
 
-AI-assisted coding makes the marginal cost of completeness near-zero. When you present options:
+AI makes completeness near-free. Always recommend the complete option over shortcuts — the delta is minutes with CC+gstack. A "lake" (100% coverage, all edge cases) is boilable; an "ocean" (full rewrite, multi-quarter migration) is not. Boil lakes, flag oceans.
 
-- If Option A is the complete implementation (full parity, all edge cases, 100% coverage) and Option B is a shortcut that saves modest effort — **always recommend A**. The delta between 80 lines and 150 lines is meaningless with CC+gstack. "Good enough" is the wrong instinct when "complete" costs minutes more.
-- **Lake vs. ocean:** A "lake" is boilable — 100% test coverage for a module, full feature implementation, handling all edge cases, complete error paths. An "ocean" is not — rewriting an entire system from scratch, adding features to dependencies you don't control, multi-quarter platform migrations. Recommend boiling lakes. Flag oceans as out of scope.
-- **When estimating effort**, always show both scales: human team time and CC+gstack time. The compression ratio varies by task type — use this reference:
+**Effort reference** — always show both scales:
 
 | Task type | Human team | CC+gstack | Compression |
 |-----------|-----------|-----------|-------------|
-| Boilerplate / scaffolding | 2 days | 15 min | ~100x |
-| Test writing | 1 day | 15 min | ~50x |
-| Feature implementation | 1 week | 30 min | ~30x |
-| Bug fix + regression test | 4 hours | 15 min | ~20x |
-| Architecture / design | 2 days | 4 hours | ~5x |
-| Research / exploration | 1 day | 3 hours | ~3x |
+| Boilerplate | 2 days | 15 min | ~100x |
+| Tests | 1 day | 15 min | ~50x |
+| Feature | 1 week | 30 min | ~30x |
+| Bug fix | 4 hours | 15 min | ~20x |
 
-- This principle applies to test coverage, error handling, documentation, edge cases, and feature completeness. Don't skip the last 10% to "save time" — with AI, that 10% costs seconds.
-
-**Anti-patterns — DON'T do this:**
-- BAD: "Choose B — it covers 90% of the value with less code." (If A is only 70 lines more, choose A.)
-- BAD: "We can skip edge case handling to save time." (Edge case handling costs minutes with CC.)
-- BAD: "Let's defer test coverage to a follow-up PR." (Tests are the cheapest lake to boil.)
-- BAD: Quoting only human-team effort: "This would take 2 weeks." (Say: "2 weeks human / ~1 hour CC.")
+Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
 ## Contributor Mode
 
-If `_CONTRIB` is `true`: you are in **contributor mode**. You're a gstack user who also helps make it better.
+If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
 
-**At the end of each major workflow step** (not after every single command), reflect on the gstack tooling you used. Rate your experience 0 to 10. If it wasn't a 10, think about why. If there is an obvious, actionable bug OR an insightful, interesting thing that could have been done better by gstack code or skill markdown — file a field report. Maybe our contributor will help make us better!
-
-**Calibration — this is the bar:** For example, `$B js "await fetch(...)"` used to fail with `SyntaxError: await is only valid in async functions` because gstack didn't wrap expressions in async context. Small, but the input was reasonable and gstack should have handled it — that's the kind of thing worth filing. Things less consequential than this, ignore.
-
-**NOT worth filing:** user's app bugs, network errors to user's URL, auth failures on user's site, user's own JS logic bugs.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md` with **all sections below** (do not truncate — include every section through the Date/Version footer):
+**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
 
+**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
 ```
 # {Title}
-
-Hey gstack team — ran into this while using /{skill-name}:
-
-**What I was trying to do:** {what the user/agent was attempting}
-**What happened instead:** {what actually happened}
-**My Rating:** {0-10} — {one sentence on why it wasn't a 10}
-
-## Steps to reproduce
+**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
+## Repro
 1. {step}
-
-## Raw output
-```
-{paste the actual error or unexpected output here}
-```
-
 ## What would make this a 10
-{one sentence: what gstack should have done differently}
-
-**Date:** {YYYY-MM-DD} | **Version:** {gstack version} | **Skill:** /{skill}
+{one sentence}
+**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
 ```
-
-Slug: lowercase, hyphens, max 60 chars (e.g. `browse-js-no-await`). Skip if file already exists. Max 3 reports per session. File inline and continue — don't stop the workflow. Tell user: "Filed gstack field report: {title}"
+Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
 
 ## Completion Status Protocol
 
diff --git a/design-consultation/SKILL.md b/design-consultation/SKILL.md
index c2b5f532..68cdd346 100644
--- a/design-consultation/SKILL.md
+++ b/design-consultation/SKILL.md
@@ -34,9 +34,11 @@ _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr
 find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
 _CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
+_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
 echo "BRANCH: $_BRANCH"
 echo "PROACTIVE: $_PROACTIVE"
+echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
 source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
 REPO_MODE=${REPO_MODE:-unknown}
 echo "REPO_MODE: $REPO_MODE"
@@ -54,8 +56,11 @@ echo '{"skill":"design-consultation","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","re
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do [ -f "$_PF" ] && ~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true; break; done
 ```
 
-If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills — only invoke
-them when the user explicitly asks. The user opted out of proactive suggestions.
+If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
+auto-invoke skills based on conversation context. Only run skills the user explicitly
+types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say:
+"I think /skillname might help here — want me to run it?" and wait for confirmation.
+The user opted out of proactive behavior.
 
 If output shows `UPGRADE_AVAILABLE <old> <new>`: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED <from> <to>`: tell user "Running gstack v{to} (just updated!)" and continue.
 
@@ -104,6 +109,27 @@ touch ~/.gstack/.telemetry-prompted
 
 This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 
+If `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: After telemetry is handled,
+ask the user about proactive behavior. Use AskUserQuestion:
+
+> gstack can proactively figure out when you might need a skill while you work —
+> like suggesting /qa when you say "does this work?" or /investigate when you hit
+> a bug. We recommend keeping this on — it speeds up every part of your workflow.
+
+Options:
+- A) Keep it on (recommended)
+- B) Turn it off — I'll type /commands myself
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set proactive true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set proactive false`
+
+Always run:
+```bash
+touch ~/.gstack/.proactive-prompted
+```
+
+This only happens once. If `PROACTIVE_PROMPTED` is `yes`, skip this entirely.
+
 ## AskUserQuestion Format
 
 **ALWAYS follow this structure for every AskUserQuestion call:**
@@ -111,7 +137,6 @@ This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
 3. **Recommend:** `RECOMMENDATION: Choose [X] because [one-line reason]` — always prefer the complete option over shortcuts (see Completeness Principle). Include `Completeness: X/10` for each option. Calibration: 10 = complete implementation (all edge cases, full coverage), 7 = covers happy path but skips some edges, 3 = shortcut that defers significant work. If both options are 8+, pick the higher; if one is ≤5, flag it.
 4. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
-5. **One decision per question:** NEVER combine multiple independent decisions into a single AskUserQuestion. Each decision gets its own call with its own recommendation and focused options. Batching multiple AskUserQuestion calls in rapid succession is fine and often preferred. Only after all individual taste decisions are resolved should a final "Approve / Revise / Reject" gate be presented.
 
 Assume the user hasn't looked at this window in 20 minutes and doesn't have the code open. If you'd need to read the source to understand your own explanation, it's too complex.
 
@@ -119,97 +144,54 @@ Per-skill instructions may add additional formatting rules on top of this baseli
 
 ## Completeness Principle — Boil the Lake
 
-AI-assisted coding makes the marginal cost of completeness near-zero. When you present options:
+AI makes completeness near-free. Always recommend the complete option over shortcuts — the delta is minutes with CC+gstack. A "lake" (100% coverage, all edge cases) is boilable; an "ocean" (full rewrite, multi-quarter migration) is not. Boil lakes, flag oceans.
 
-- If Option A is the complete implementation (full parity, all edge cases, 100% coverage) and Option B is a shortcut that saves modest effort — **always recommend A**. The delta between 80 lines and 150 lines is meaningless with CC+gstack. "Good enough" is the wrong instinct when "complete" costs minutes more.
-- **Lake vs. ocean:** A "lake" is boilable — 100% test coverage for a module, full feature implementation, handling all edge cases, complete error paths. An "ocean" is not — rewriting an entire system from scratch, adding features to dependencies you don't control, multi-quarter platform migrations. Recommend boiling lakes. Flag oceans as out of scope.
-- **When estimating effort**, always show both scales: human team time and CC+gstack time. The compression ratio varies by task type — use this reference:
+**Effort reference** — always show both scales:
 
 | Task type | Human team | CC+gstack | Compression |
 |-----------|-----------|-----------|-------------|
-| Boilerplate / scaffolding | 2 days | 15 min | ~100x |
-| Test writing | 1 day | 15 min | ~50x |
-| Feature implementation | 1 week | 30 min | ~30x |
-| Bug fix + regression test | 4 hours | 15 min | ~20x |
-| Architecture / design | 2 days | 4 hours | ~5x |
-| Research / exploration | 1 day | 3 hours | ~3x |
+| Boilerplate | 2 days | 15 min | ~100x |
+| Tests | 1 day | 15 min | ~50x |
+| Feature | 1 week | 30 min | ~30x |
+| Bug fix | 4 hours | 15 min | ~20x |
 
-- This principle applies to test coverage, error handling, documentation, edge cases, and feature completeness. Don't skip the last 10% to "save time" — with AI, that 10% costs seconds.
+Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-**Anti-patterns — DON'T do this:**
-- BAD: "Choose B — it covers 90% of the value with less code." (If A is only 70 lines more, choose A.)
-- BAD: "We can skip edge case handling to save time." (Edge case handling costs minutes with CC.)
-- BAD: "Let's defer test coverage to a follow-up PR." (Tests are the cheapest lake to boil.)
-- BAD: Quoting only human-team effort: "This would take 2 weeks." (Say: "2 weeks human / ~1 hour CC.")
+## Repo Ownership — See Something, Say Something
 
-## Repo Ownership Mode — See Something, Say Something
+`REPO_MODE` controls how to handle issues outside your branch:
+- **`solo`** — You own everything. Investigate and offer to fix proactively.
+- **`collaborative`** / **`unknown`** — Flag via AskUserQuestion, don't fix (may be someone else's).
 
-`REPO_MODE` from the preamble tells you who owns issues in this repo:
-
-- **`solo`** — One person does 80%+ of the work. They own everything. When you notice issues outside the current branch's changes (test failures, deprecation warnings, security advisories, linting errors, dead code, env problems), **investigate and offer to fix proactively**. The solo dev is the only person who will fix it. Default to action.
-- **`collaborative`** — Multiple active contributors. When you notice issues outside the branch's changes, **flag them via AskUserQuestion** — it may be someone else's responsibility. Default to asking, not fixing.
-- **`unknown`** — Treat as collaborative (safer default — ask before fixing).
-
-**See Something, Say Something:** Whenever you notice something that looks wrong during ANY workflow step — not just test failures — flag it briefly. One sentence: what you noticed and its impact. In solo mode, follow up with "Want me to fix it?" In collaborative mode, just flag it and move on.
-
-Never let a noticed issue silently pass. The whole point is proactive communication.
+Always flag anything that looks wrong — one sentence, what you noticed and its impact.
 
 ## Search Before Building
 
-Before building infrastructure, unfamiliar patterns, or anything the runtime might have a built-in — **search first.** Read `~/.claude/skills/gstack/ETHOS.md` for the full philosophy.
+Before building anything unfamiliar, **search first.** See `~/.claude/skills/gstack/ETHOS.md`.
+- **Layer 1** (tried and true) — don't reinvent. **Layer 2** (new and popular) — scrutinize. **Layer 3** (first principles) — prize above all.
 
-**Three layers of knowledge:**
-- **Layer 1** (tried and true — in distribution). Don't reinvent the wheel. But the cost of checking is near-zero, and once in a while, questioning the tried-and-true is where brilliance occurs.
-- **Layer 2** (new and popular — search for these). But scrutinize: humans are subject to mania. Search results are inputs to your thinking, not answers.
-- **Layer 3** (first principles — prize these above all). Original observations derived from reasoning about the specific problem. The most valuable of all.
-
-**Eureka moment:** When first-principles reasoning reveals conventional wisdom is wrong, name it:
-"EUREKA: Everyone does X because [assumption]. But [evidence] shows this is wrong. Y is better because [reasoning]."
-
-Log eureka moments:
+**Eureka:** When first-principles reasoning contradicts conventional wisdom, name it and log:
 ```bash
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
-Replace SKILL_NAME and ONE_LINE_SUMMARY. Runs inline — don't stop the workflow.
-
-**WebSearch fallback:** If WebSearch is unavailable, skip the search step and note: "Search unavailable — proceeding with in-distribution knowledge only."
 
 ## Contributor Mode
 
-If `_CONTRIB` is `true`: you are in **contributor mode**. You're a gstack user who also helps make it better.
+If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
 
-**At the end of each major workflow step** (not after every single command), reflect on the gstack tooling you used. Rate your experience 0 to 10. If it wasn't a 10, think about why. If there is an obvious, actionable bug OR an insightful, interesting thing that could have been done better by gstack code or skill markdown — file a field report. Maybe our contributor will help make us better!
-
-**Calibration — this is the bar:** For example, `$B js "await fetch(...)"` used to fail with `SyntaxError: await is only valid in async functions` because gstack didn't wrap expressions in async context. Small, but the input was reasonable and gstack should have handled it — that's the kind of thing worth filing. Things less consequential than this, ignore.
-
-**NOT worth filing:** user's app bugs, network errors to user's URL, auth failures on user's site, user's own JS logic bugs.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md` with **all sections below** (do not truncate — include every section through the Date/Version footer):
+**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
 
+**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
 ```
 # {Title}
-
-Hey gstack team — ran into this while using /{skill-name}:
-
-**What I was trying to do:** {what the user/agent was attempting}
-**What happened instead:** {what actually happened}
-**My Rating:** {0-10} — {one sentence on why it wasn't a 10}
-
-## Steps to reproduce
+**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
+## Repro
 1. {step}
-
-## Raw output
-```
-{paste the actual error or unexpected output here}
-```
-
 ## What would make this a 10
-{one sentence: what gstack should have done differently}
-
-**Date:** {YYYY-MM-DD} | **Version:** {gstack version} | **Skill:** /{skill}
+{one sentence}
+**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
 ```
-
-Slug: lowercase, hyphens, max 60 chars (e.g. `browse-js-no-await`). Skip if file already exists. Max 3 reports per session. File inline and continue — don't stop the workflow. Tell user: "Filed gstack field report: {title}"
+Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
 
 ## Completion Status Protocol
 
diff --git a/design-review/SKILL.md b/design-review/SKILL.md
index ad71db57..e539b337 100644
--- a/design-review/SKILL.md
+++ b/design-review/SKILL.md
@@ -34,9 +34,11 @@ _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr
 find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
 _CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
+_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
 echo "BRANCH: $_BRANCH"
 echo "PROACTIVE: $_PROACTIVE"
+echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
 source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
 REPO_MODE=${REPO_MODE:-unknown}
 echo "REPO_MODE: $REPO_MODE"
@@ -54,8 +56,11 @@ echo '{"skill":"design-review","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do [ -f "$_PF" ] && ~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true; break; done
 ```
 
-If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills — only invoke
-them when the user explicitly asks. The user opted out of proactive suggestions.
+If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
+auto-invoke skills based on conversation context. Only run skills the user explicitly
+types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say:
+"I think /skillname might help here — want me to run it?" and wait for confirmation.
+The user opted out of proactive behavior.
 
 If output shows `UPGRADE_AVAILABLE <old> <new>`: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED <from> <to>`: tell user "Running gstack v{to} (just updated!)" and continue.
 
@@ -104,6 +109,27 @@ touch ~/.gstack/.telemetry-prompted
 
 This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 
+If `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: After telemetry is handled,
+ask the user about proactive behavior. Use AskUserQuestion:
+
+> gstack can proactively figure out when you might need a skill while you work —
+> like suggesting /qa when you say "does this work?" or /investigate when you hit
+> a bug. We recommend keeping this on — it speeds up every part of your workflow.
+
+Options:
+- A) Keep it on (recommended)
+- B) Turn it off — I'll type /commands myself
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set proactive true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set proactive false`
+
+Always run:
+```bash
+touch ~/.gstack/.proactive-prompted
+```
+
+This only happens once. If `PROACTIVE_PROMPTED` is `yes`, skip this entirely.
+
 ## AskUserQuestion Format
 
 **ALWAYS follow this structure for every AskUserQuestion call:**
@@ -111,7 +137,6 @@ This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
 3. **Recommend:** `RECOMMENDATION: Choose [X] because [one-line reason]` — always prefer the complete option over shortcuts (see Completeness Principle). Include `Completeness: X/10` for each option. Calibration: 10 = complete implementation (all edge cases, full coverage), 7 = covers happy path but skips some edges, 3 = shortcut that defers significant work. If both options are 8+, pick the higher; if one is ≤5, flag it.
 4. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
-5. **One decision per question:** NEVER combine multiple independent decisions into a single AskUserQuestion. Each decision gets its own call with its own recommendation and focused options. Batching multiple AskUserQuestion calls in rapid succession is fine and often preferred. Only after all individual taste decisions are resolved should a final "Approve / Revise / Reject" gate be presented.
 
 Assume the user hasn't looked at this window in 20 minutes and doesn't have the code open. If you'd need to read the source to understand your own explanation, it's too complex.
 
@@ -119,97 +144,54 @@ Per-skill instructions may add additional formatting rules on top of this baseli
 
 ## Completeness Principle — Boil the Lake
 
-AI-assisted coding makes the marginal cost of completeness near-zero. When you present options:
+AI makes completeness near-free. Always recommend the complete option over shortcuts — the delta is minutes with CC+gstack. A "lake" (100% coverage, all edge cases) is boilable; an "ocean" (full rewrite, multi-quarter migration) is not. Boil lakes, flag oceans.
 
-- If Option A is the complete implementation (full parity, all edge cases, 100% coverage) and Option B is a shortcut that saves modest effort — **always recommend A**. The delta between 80 lines and 150 lines is meaningless with CC+gstack. "Good enough" is the wrong instinct when "complete" costs minutes more.
-- **Lake vs. ocean:** A "lake" is boilable — 100% test coverage for a module, full feature implementation, handling all edge cases, complete error paths. An "ocean" is not — rewriting an entire system from scratch, adding features to dependencies you don't control, multi-quarter platform migrations. Recommend boiling lakes. Flag oceans as out of scope.
-- **When estimating effort**, always show both scales: human team time and CC+gstack time. The compression ratio varies by task type — use this reference:
+**Effort reference** — always show both scales:
 
 | Task type | Human team | CC+gstack | Compression |
 |-----------|-----------|-----------|-------------|
-| Boilerplate / scaffolding | 2 days | 15 min | ~100x |
-| Test writing | 1 day | 15 min | ~50x |
-| Feature implementation | 1 week | 30 min | ~30x |
-| Bug fix + regression test | 4 hours | 15 min | ~20x |
-| Architecture / design | 2 days | 4 hours | ~5x |
-| Research / exploration | 1 day | 3 hours | ~3x |
+| Boilerplate | 2 days | 15 min | ~100x |
+| Tests | 1 day | 15 min | ~50x |
+| Feature | 1 week | 30 min | ~30x |
+| Bug fix | 4 hours | 15 min | ~20x |
 
-- This principle applies to test coverage, error handling, documentation, edge cases, and feature completeness. Don't skip the last 10% to "save time" — with AI, that 10% costs seconds.
+Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-**Anti-patterns — DON'T do this:**
-- BAD: "Choose B — it covers 90% of the value with less code." (If A is only 70 lines more, choose A.)
-- BAD: "We can skip edge case handling to save time." (Edge case handling costs minutes with CC.)
-- BAD: "Let's defer test coverage to a follow-up PR." (Tests are the cheapest lake to boil.)
-- BAD: Quoting only human-team effort: "This would take 2 weeks." (Say: "2 weeks human / ~1 hour CC.")
+## Repo Ownership — See Something, Say Something
 
-## Repo Ownership Mode — See Something, Say Something
+`REPO_MODE` controls how to handle issues outside your branch:
+- **`solo`** — You own everything. Investigate and offer to fix proactively.
+- **`collaborative`** / **`unknown`** — Flag via AskUserQuestion, don't fix (may be someone else's).
 
-`REPO_MODE` from the preamble tells you who owns issues in this repo:
-
-- **`solo`** — One person does 80%+ of the work. They own everything. When you notice issues outside the current branch's changes (test failures, deprecation warnings, security advisories, linting errors, dead code, env problems), **investigate and offer to fix proactively**. The solo dev is the only person who will fix it. Default to action.
-- **`collaborative`** — Multiple active contributors. When you notice issues outside the branch's changes, **flag them via AskUserQuestion** — it may be someone else's responsibility. Default to asking, not fixing.
-- **`unknown`** — Treat as collaborative (safer default — ask before fixing).
-
-**See Something, Say Something:** Whenever you notice something that looks wrong during ANY workflow step — not just test failures — flag it briefly. One sentence: what you noticed and its impact. In solo mode, follow up with "Want me to fix it?" In collaborative mode, just flag it and move on.
-
-Never let a noticed issue silently pass. The whole point is proactive communication.
+Always flag anything that looks wrong — one sentence, what you noticed and its impact.
 
 ## Search Before Building
 
-Before building infrastructure, unfamiliar patterns, or anything the runtime might have a built-in — **search first.** Read `~/.claude/skills/gstack/ETHOS.md` for the full philosophy.
+Before building anything unfamiliar, **search first.** See `~/.claude/skills/gstack/ETHOS.md`.
+- **Layer 1** (tried and true) — don't reinvent. **Layer 2** (new and popular) — scrutinize. **Layer 3** (first principles) — prize above all.
 
-**Three layers of knowledge:**
-- **Layer 1** (tried and true — in distribution). Don't reinvent the wheel. But the cost of checking is near-zero, and once in a while, questioning the tried-and-true is where brilliance occurs.
-- **Layer 2** (new and popular — search for these). But scrutinize: humans are subject to mania. Search results are inputs to your thinking, not answers.
-- **Layer 3** (first principles — prize these above all). Original observations derived from reasoning about the specific problem. The most valuable of all.
-
-**Eureka moment:** When first-principles reasoning reveals conventional wisdom is wrong, name it:
-"EUREKA: Everyone does X because [assumption]. But [evidence] shows this is wrong. Y is better because [reasoning]."
-
-Log eureka moments:
+**Eureka:** When first-principles reasoning contradicts conventional wisdom, name it and log:
 ```bash
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
-Replace SKILL_NAME and ONE_LINE_SUMMARY. Runs inline — don't stop the workflow.
-
-**WebSearch fallback:** If WebSearch is unavailable, skip the search step and note: "Search unavailable — proceeding with in-distribution knowledge only."
 
 ## Contributor Mode
 
-If `_CONTRIB` is `true`: you are in **contributor mode**. You're a gstack user who also helps make it better.
+If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
 
-**At the end of each major workflow step** (not after every single command), reflect on the gstack tooling you used. Rate your experience 0 to 10. If it wasn't a 10, think about why. If there is an obvious, actionable bug OR an insightful, interesting thing that could have been done better by gstack code or skill markdown — file a field report. Maybe our contributor will help make us better!
-
-**Calibration — this is the bar:** For example, `$B js "await fetch(...)"` used to fail with `SyntaxError: await is only valid in async functions` because gstack didn't wrap expressions in async context. Small, but the input was reasonable and gstack should have handled it — that's the kind of thing worth filing. Things less consequential than this, ignore.
-
-**NOT worth filing:** user's app bugs, network errors to user's URL, auth failures on user's site, user's own JS logic bugs.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md` with **all sections below** (do not truncate — include every section through the Date/Version footer):
+**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
 
+**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
 ```
 # {Title}
-
-Hey gstack team — ran into this while using /{skill-name}:
-
-**What I was trying to do:** {what the user/agent was attempting}
-**What happened instead:** {what actually happened}
-**My Rating:** {0-10} — {one sentence on why it wasn't a 10}
-
-## Steps to reproduce
+**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
+## Repro
 1. {step}
-
-## Raw output
-```
-{paste the actual error or unexpected output here}
-```
-
 ## What would make this a 10
-{one sentence: what gstack should have done differently}
-
-**Date:** {YYYY-MM-DD} | **Version:** {gstack version} | **Skill:** /{skill}
+{one sentence}
+**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
 ```
-
-Slug: lowercase, hyphens, max 60 chars (e.g. `browse-js-no-await`). Skip if file already exists. Max 3 reports per session. File inline and continue — don't stop the workflow. Tell user: "Filed gstack field report: {title}"
+Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
 
 ## Completion Status Protocol
 
diff --git a/document-release/SKILL.md b/document-release/SKILL.md
index a77eb15a..ee08867a 100644
--- a/document-release/SKILL.md
+++ b/document-release/SKILL.md
@@ -31,9 +31,11 @@ _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr
 find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
 _CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
+_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
 echo "BRANCH: $_BRANCH"
 echo "PROACTIVE: $_PROACTIVE"
+echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
 source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
 REPO_MODE=${REPO_MODE:-unknown}
 echo "REPO_MODE: $REPO_MODE"
@@ -51,8 +53,11 @@ echo '{"skill":"document-release","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo"
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do [ -f "$_PF" ] && ~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true; break; done
 ```
 
-If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills — only invoke
-them when the user explicitly asks. The user opted out of proactive suggestions.
+If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
+auto-invoke skills based on conversation context. Only run skills the user explicitly
+types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say:
+"I think /skillname might help here — want me to run it?" and wait for confirmation.
+The user opted out of proactive behavior.
 
 If output shows `UPGRADE_AVAILABLE <old> <new>`: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED <from> <to>`: tell user "Running gstack v{to} (just updated!)" and continue.
 
@@ -101,6 +106,27 @@ touch ~/.gstack/.telemetry-prompted
 
 This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 
+If `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: After telemetry is handled,
+ask the user about proactive behavior. Use AskUserQuestion:
+
+> gstack can proactively figure out when you might need a skill while you work —
+> like suggesting /qa when you say "does this work?" or /investigate when you hit
+> a bug. We recommend keeping this on — it speeds up every part of your workflow.
+
+Options:
+- A) Keep it on (recommended)
+- B) Turn it off — I'll type /commands myself
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set proactive true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set proactive false`
+
+Always run:
+```bash
+touch ~/.gstack/.proactive-prompted
+```
+
+This only happens once. If `PROACTIVE_PROMPTED` is `yes`, skip this entirely.
+
 ## AskUserQuestion Format
 
 **ALWAYS follow this structure for every AskUserQuestion call:**
@@ -108,7 +134,6 @@ This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
 3. **Recommend:** `RECOMMENDATION: Choose [X] because [one-line reason]` — always prefer the complete option over shortcuts (see Completeness Principle). Include `Completeness: X/10` for each option. Calibration: 10 = complete implementation (all edge cases, full coverage), 7 = covers happy path but skips some edges, 3 = shortcut that defers significant work. If both options are 8+, pick the higher; if one is ≤5, flag it.
 4. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
-5. **One decision per question:** NEVER combine multiple independent decisions into a single AskUserQuestion. Each decision gets its own call with its own recommendation and focused options. Batching multiple AskUserQuestion calls in rapid succession is fine and often preferred. Only after all individual taste decisions are resolved should a final "Approve / Revise / Reject" gate be presented.
 
 Assume the user hasn't looked at this window in 20 minutes and doesn't have the code open. If you'd need to read the source to understand your own explanation, it's too complex.
 
@@ -116,65 +141,36 @@ Per-skill instructions may add additional formatting rules on top of this baseli
 
 ## Completeness Principle — Boil the Lake
 
-AI-assisted coding makes the marginal cost of completeness near-zero. When you present options:
+AI makes completeness near-free. Always recommend the complete option over shortcuts — the delta is minutes with CC+gstack. A "lake" (100% coverage, all edge cases) is boilable; an "ocean" (full rewrite, multi-quarter migration) is not. Boil lakes, flag oceans.
 
-- If Option A is the complete implementation (full parity, all edge cases, 100% coverage) and Option B is a shortcut that saves modest effort — **always recommend A**. The delta between 80 lines and 150 lines is meaningless with CC+gstack. "Good enough" is the wrong instinct when "complete" costs minutes more.
-- **Lake vs. ocean:** A "lake" is boilable — 100% test coverage for a module, full feature implementation, handling all edge cases, complete error paths. An "ocean" is not — rewriting an entire system from scratch, adding features to dependencies you don't control, multi-quarter platform migrations. Recommend boiling lakes. Flag oceans as out of scope.
-- **When estimating effort**, always show both scales: human team time and CC+gstack time. The compression ratio varies by task type — use this reference:
+**Effort reference** — always show both scales:
 
 | Task type | Human team | CC+gstack | Compression |
 |-----------|-----------|-----------|-------------|
-| Boilerplate / scaffolding | 2 days | 15 min | ~100x |
-| Test writing | 1 day | 15 min | ~50x |
-| Feature implementation | 1 week | 30 min | ~30x |
-| Bug fix + regression test | 4 hours | 15 min | ~20x |
-| Architecture / design | 2 days | 4 hours | ~5x |
-| Research / exploration | 1 day | 3 hours | ~3x |
+| Boilerplate | 2 days | 15 min | ~100x |
+| Tests | 1 day | 15 min | ~50x |
+| Feature | 1 week | 30 min | ~30x |
+| Bug fix | 4 hours | 15 min | ~20x |
 
-- This principle applies to test coverage, error handling, documentation, edge cases, and feature completeness. Don't skip the last 10% to "save time" — with AI, that 10% costs seconds.
-
-**Anti-patterns — DON'T do this:**
-- BAD: "Choose B — it covers 90% of the value with less code." (If A is only 70 lines more, choose A.)
-- BAD: "We can skip edge case handling to save time." (Edge case handling costs minutes with CC.)
-- BAD: "Let's defer test coverage to a follow-up PR." (Tests are the cheapest lake to boil.)
-- BAD: Quoting only human-team effort: "This would take 2 weeks." (Say: "2 weeks human / ~1 hour CC.")
+Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
 ## Contributor Mode
 
-If `_CONTRIB` is `true`: you are in **contributor mode**. You're a gstack user who also helps make it better.
+If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
 
-**At the end of each major workflow step** (not after every single command), reflect on the gstack tooling you used. Rate your experience 0 to 10. If it wasn't a 10, think about why. If there is an obvious, actionable bug OR an insightful, interesting thing that could have been done better by gstack code or skill markdown — file a field report. Maybe our contributor will help make us better!
-
-**Calibration — this is the bar:** For example, `$B js "await fetch(...)"` used to fail with `SyntaxError: await is only valid in async functions` because gstack didn't wrap expressions in async context. Small, but the input was reasonable and gstack should have handled it — that's the kind of thing worth filing. Things less consequential than this, ignore.
-
-**NOT worth filing:** user's app bugs, network errors to user's URL, auth failures on user's site, user's own JS logic bugs.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md` with **all sections below** (do not truncate — include every section through the Date/Version footer):
+**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
 
+**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
 ```
 # {Title}
-
-Hey gstack team — ran into this while using /{skill-name}:
-
-**What I was trying to do:** {what the user/agent was attempting}
-**What happened instead:** {what actually happened}
-**My Rating:** {0-10} — {one sentence on why it wasn't a 10}
-
-## Steps to reproduce
+**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
+## Repro
 1. {step}
-
-## Raw output
-```
-{paste the actual error or unexpected output here}
-```
-
 ## What would make this a 10
-{one sentence: what gstack should have done differently}
-
-**Date:** {YYYY-MM-DD} | **Version:** {gstack version} | **Skill:** /{skill}
+{one sentence}
+**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
 ```
-
-Slug: lowercase, hyphens, max 60 chars (e.g. `browse-js-no-await`). Skip if file already exists. Max 3 reports per session. File inline and continue — don't stop the workflow. Tell user: "Filed gstack field report: {title}"
+Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
 
 ## Completion Status Protocol
 
@@ -265,22 +261,42 @@ Then write a `## GSTACK REVIEW REPORT` section to the end of the plan file:
 file you are allowed to edit in plan mode. The plan file review report is part of the
 plan's living status.
 
-## Step 0: Detect base branch
+## Step 0: Detect platform and base branch
 
-Determine which branch this PR targets. Use the result as "the base branch" in all subsequent steps.
+First, detect the git hosting platform from the remote URL:
 
-1. Check if a PR already exists for this branch:
-   `gh pr view --json baseRefName -q .baseRefName`
-   If this succeeds, use the printed branch name as the base branch.
+```bash
+git remote get-url origin 2>/dev/null
+```
 
-2. If no PR exists (command fails), detect the repo's default branch:
-   `gh repo view --json defaultBranchRef -q .defaultBranchRef.name`
+- If the URL contains "github.com" → platform is **GitHub**
+- If the URL contains "gitlab" → platform is **GitLab**
+- Otherwise, check CLI availability:
+  - `gh auth status 2>/dev/null` succeeds → platform is **GitHub** (covers GitHub Enterprise)
+  - `glab auth status 2>/dev/null` succeeds → platform is **GitLab** (covers self-hosted)
+  - Neither → **unknown** (use git-native commands only)
 
-3. If both commands fail, fall back to `main`.
+Determine which branch this PR/MR targets, or the repo's default branch if no
+PR/MR exists. Use the result as "the base branch" in all subsequent steps.
+
+**If GitHub:**
+1. `gh pr view --json baseRefName -q .baseRefName` — if succeeds, use it
+2. `gh repo view --json defaultBranchRef -q .defaultBranchRef.name` — if succeeds, use it
+
+**If GitLab:**
+1. `glab mr view -F json 2>/dev/null` and extract the `target_branch` field — if succeeds, use it
+2. `glab repo view -F json 2>/dev/null` and extract the `default_branch` field — if succeeds, use it
+
+**Git-native fallback (if unknown platform, or CLI commands fail):**
+1. `git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's|refs/remotes/origin/||'`
+2. If that fails: `git rev-parse --verify origin/main 2>/dev/null` → use `main`
+3. If that fails: `git rev-parse --verify origin/master 2>/dev/null` → use `master`
+
+If all fail, fall back to `main`.
 
 Print the detected base branch name. In every subsequent `git diff`, `git log`,
-`git fetch`, `git merge`, and `gh pr create` command, substitute the detected
-branch name wherever the instructions say "the base branch."
+`git fetch`, `git merge`, and PR/MR creation command, substitute the detected
+branch name wherever the instructions say "the base branch" or `<default>`.
 
 ---
 
@@ -553,14 +569,20 @@ EOF
 git push
 ```
 
-**PR body update (idempotent, race-safe):**
+**PR/MR body update (idempotent, race-safe):**
 
-1. Read the existing PR body into a PID-unique tempfile:
+1. Read the existing PR/MR body into a PID-unique tempfile (use the platform detected in Step 0):
 
+**If GitHub:**
 ```bash
 gh pr view --json body -q .body > /tmp/gstack-pr-body-$$.md
 ```
 
+**If GitLab:**
+```bash
+glab mr view -F json 2>/dev/null | python3 -c "import sys,json; print(json.load(sys.stdin).get('description',''))" > /tmp/gstack-pr-body-$$.md
+```
+
 2. If the tempfile already contains a `## Documentation` section, replace that section with the
    updated content. If it does not contain one, append a `## Documentation` section at the end.
 
@@ -570,18 +592,28 @@ gh pr view --json body -q .body > /tmp/gstack-pr-body-$$.md
 
 4. Write the updated body back:
 
+**If GitHub:**
 ```bash
 gh pr edit --body-file /tmp/gstack-pr-body-$$.md
 ```
 
+**If GitLab:**
+Read the contents of `/tmp/gstack-pr-body-$$.md` using the Read tool, then pass it to `glab mr update` using a heredoc to avoid shell metacharacter issues:
+```bash
+glab mr update -d "$(cat <<'MRBODY'
+<paste the file contents here>
+MRBODY
+)"
+```
+
 5. Clean up the tempfile:
 
 ```bash
 rm -f /tmp/gstack-pr-body-$$.md
 ```
 
-6. If `gh pr view` fails (no PR exists): skip with message "No PR found — skipping body update."
-7. If `gh pr edit` fails: warn "Could not update PR body — documentation changes are in the
+6. If `gh pr view` / `glab mr view` fails (no PR/MR exists): skip with message "No PR/MR found — skipping body update."
+7. If `gh pr edit` / `glab mr update` fails: warn "Could not update PR/MR body — documentation changes are in the
    commit." and continue.
 
 **Structured doc health summary (final output):**
diff --git a/document-release/SKILL.md.tmpl b/document-release/SKILL.md.tmpl
index 30cdee0c..5d236ae2 100644
--- a/document-release/SKILL.md.tmpl
+++ b/document-release/SKILL.md.tmpl
@@ -291,14 +291,20 @@ EOF
 git push
 ```
 
-**PR body update (idempotent, race-safe):**
+**PR/MR body update (idempotent, race-safe):**
 
-1. Read the existing PR body into a PID-unique tempfile:
+1. Read the existing PR/MR body into a PID-unique tempfile (use the platform detected in Step 0):
 
+**If GitHub:**
 ```bash
 gh pr view --json body -q .body > /tmp/gstack-pr-body-$$.md
 ```
 
+**If GitLab:**
+```bash
+glab mr view -F json 2>/dev/null | python3 -c "import sys,json; print(json.load(sys.stdin).get('description',''))" > /tmp/gstack-pr-body-$$.md
+```
+
 2. If the tempfile already contains a `## Documentation` section, replace that section with the
    updated content. If it does not contain one, append a `## Documentation` section at the end.
 
@@ -308,18 +314,28 @@ gh pr view --json body -q .body > /tmp/gstack-pr-body-$$.md
 
 4. Write the updated body back:
 
+**If GitHub:**
 ```bash
 gh pr edit --body-file /tmp/gstack-pr-body-$$.md
 ```
 
+**If GitLab:**
+Read the contents of `/tmp/gstack-pr-body-$$.md` using the Read tool, then pass it to `glab mr update` using a heredoc to avoid shell metacharacter issues:
+```bash
+glab mr update -d "$(cat <<'MRBODY'
+<paste the file contents here>
+MRBODY
+)"
+```
+
 5. Clean up the tempfile:
 
 ```bash
 rm -f /tmp/gstack-pr-body-$$.md
 ```
 
-6. If `gh pr view` fails (no PR exists): skip with message "No PR found — skipping body update."
-7. If `gh pr edit` fails: warn "Could not update PR body — documentation changes are in the
+6. If `gh pr view` / `glab mr view` fails (no PR/MR exists): skip with message "No PR/MR found — skipping body update."
+7. If `gh pr edit` / `glab mr update` fails: warn "Could not update PR/MR body — documentation changes are in the
    commit." and continue.
 
 **Structured doc health summary (final output):**
diff --git a/investigate/SKILL.md b/investigate/SKILL.md
index 84cfe2d0..4d1cb933 100644
--- a/investigate/SKILL.md
+++ b/investigate/SKILL.md
@@ -45,9 +45,11 @@ _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr
 find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
 _CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
+_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
 echo "BRANCH: $_BRANCH"
 echo "PROACTIVE: $_PROACTIVE"
+echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
 source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
 REPO_MODE=${REPO_MODE:-unknown}
 echo "REPO_MODE: $REPO_MODE"
@@ -65,8 +67,11 @@ echo '{"skill":"investigate","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do [ -f "$_PF" ] && ~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true; break; done
 ```
 
-If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills — only invoke
-them when the user explicitly asks. The user opted out of proactive suggestions.
+If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
+auto-invoke skills based on conversation context. Only run skills the user explicitly
+types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say:
+"I think /skillname might help here — want me to run it?" and wait for confirmation.
+The user opted out of proactive behavior.
 
 If output shows `UPGRADE_AVAILABLE <old> <new>`: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED <from> <to>`: tell user "Running gstack v{to} (just updated!)" and continue.
 
@@ -115,6 +120,27 @@ touch ~/.gstack/.telemetry-prompted
 
 This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 
+If `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: After telemetry is handled,
+ask the user about proactive behavior. Use AskUserQuestion:
+
+> gstack can proactively figure out when you might need a skill while you work —
+> like suggesting /qa when you say "does this work?" or /investigate when you hit
+> a bug. We recommend keeping this on — it speeds up every part of your workflow.
+
+Options:
+- A) Keep it on (recommended)
+- B) Turn it off — I'll type /commands myself
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set proactive true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set proactive false`
+
+Always run:
+```bash
+touch ~/.gstack/.proactive-prompted
+```
+
+This only happens once. If `PROACTIVE_PROMPTED` is `yes`, skip this entirely.
+
 ## AskUserQuestion Format
 
 **ALWAYS follow this structure for every AskUserQuestion call:**
@@ -122,7 +148,6 @@ This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
 3. **Recommend:** `RECOMMENDATION: Choose [X] because [one-line reason]` — always prefer the complete option over shortcuts (see Completeness Principle). Include `Completeness: X/10` for each option. Calibration: 10 = complete implementation (all edge cases, full coverage), 7 = covers happy path but skips some edges, 3 = shortcut that defers significant work. If both options are 8+, pick the higher; if one is ≤5, flag it.
 4. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
-5. **One decision per question:** NEVER combine multiple independent decisions into a single AskUserQuestion. Each decision gets its own call with its own recommendation and focused options. Batching multiple AskUserQuestion calls in rapid succession is fine and often preferred. Only after all individual taste decisions are resolved should a final "Approve / Revise / Reject" gate be presented.
 
 Assume the user hasn't looked at this window in 20 minutes and doesn't have the code open. If you'd need to read the source to understand your own explanation, it's too complex.
 
@@ -130,65 +155,36 @@ Per-skill instructions may add additional formatting rules on top of this baseli
 
 ## Completeness Principle — Boil the Lake
 
-AI-assisted coding makes the marginal cost of completeness near-zero. When you present options:
+AI makes completeness near-free. Always recommend the complete option over shortcuts — the delta is minutes with CC+gstack. A "lake" (100% coverage, all edge cases) is boilable; an "ocean" (full rewrite, multi-quarter migration) is not. Boil lakes, flag oceans.
 
-- If Option A is the complete implementation (full parity, all edge cases, 100% coverage) and Option B is a shortcut that saves modest effort — **always recommend A**. The delta between 80 lines and 150 lines is meaningless with CC+gstack. "Good enough" is the wrong instinct when "complete" costs minutes more.
-- **Lake vs. ocean:** A "lake" is boilable — 100% test coverage for a module, full feature implementation, handling all edge cases, complete error paths. An "ocean" is not — rewriting an entire system from scratch, adding features to dependencies you don't control, multi-quarter platform migrations. Recommend boiling lakes. Flag oceans as out of scope.
-- **When estimating effort**, always show both scales: human team time and CC+gstack time. The compression ratio varies by task type — use this reference:
+**Effort reference** — always show both scales:
 
 | Task type | Human team | CC+gstack | Compression |
 |-----------|-----------|-----------|-------------|
-| Boilerplate / scaffolding | 2 days | 15 min | ~100x |
-| Test writing | 1 day | 15 min | ~50x |
-| Feature implementation | 1 week | 30 min | ~30x |
-| Bug fix + regression test | 4 hours | 15 min | ~20x |
-| Architecture / design | 2 days | 4 hours | ~5x |
-| Research / exploration | 1 day | 3 hours | ~3x |
+| Boilerplate | 2 days | 15 min | ~100x |
+| Tests | 1 day | 15 min | ~50x |
+| Feature | 1 week | 30 min | ~30x |
+| Bug fix | 4 hours | 15 min | ~20x |
 
-- This principle applies to test coverage, error handling, documentation, edge cases, and feature completeness. Don't skip the last 10% to "save time" — with AI, that 10% costs seconds.
-
-**Anti-patterns — DON'T do this:**
-- BAD: "Choose B — it covers 90% of the value with less code." (If A is only 70 lines more, choose A.)
-- BAD: "We can skip edge case handling to save time." (Edge case handling costs minutes with CC.)
-- BAD: "Let's defer test coverage to a follow-up PR." (Tests are the cheapest lake to boil.)
-- BAD: Quoting only human-team effort: "This would take 2 weeks." (Say: "2 weeks human / ~1 hour CC.")
+Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
 ## Contributor Mode
 
-If `_CONTRIB` is `true`: you are in **contributor mode**. You're a gstack user who also helps make it better.
+If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
 
-**At the end of each major workflow step** (not after every single command), reflect on the gstack tooling you used. Rate your experience 0 to 10. If it wasn't a 10, think about why. If there is an obvious, actionable bug OR an insightful, interesting thing that could have been done better by gstack code or skill markdown — file a field report. Maybe our contributor will help make us better!
-
-**Calibration — this is the bar:** For example, `$B js "await fetch(...)"` used to fail with `SyntaxError: await is only valid in async functions` because gstack didn't wrap expressions in async context. Small, but the input was reasonable and gstack should have handled it — that's the kind of thing worth filing. Things less consequential than this, ignore.
-
-**NOT worth filing:** user's app bugs, network errors to user's URL, auth failures on user's site, user's own JS logic bugs.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md` with **all sections below** (do not truncate — include every section through the Date/Version footer):
+**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
 
+**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
 ```
 # {Title}
-
-Hey gstack team — ran into this while using /{skill-name}:
-
-**What I was trying to do:** {what the user/agent was attempting}
-**What happened instead:** {what actually happened}
-**My Rating:** {0-10} — {one sentence on why it wasn't a 10}
-
-## Steps to reproduce
+**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
+## Repro
 1. {step}
-
-## Raw output
-```
-{paste the actual error or unexpected output here}
-```
-
 ## What would make this a 10
-{one sentence: what gstack should have done differently}
-
-**Date:** {YYYY-MM-DD} | **Version:** {gstack version} | **Skill:** /{skill}
+{one sentence}
+**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
 ```
-
-Slug: lowercase, hyphens, max 60 chars (e.g. `browse-js-no-await`). Skip if file already exists. Max 3 reports per session. File inline and continue — don't stop the workflow. Tell user: "Filed gstack field report: {title}"
+Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
 
 ## Completion Status Protocol
 
diff --git a/land-and-deploy/SKILL.md b/land-and-deploy/SKILL.md
index 1bc7e1d2..d5f2c8d6 100644
--- a/land-and-deploy/SKILL.md
+++ b/land-and-deploy/SKILL.md
@@ -28,9 +28,11 @@ _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr
 find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
 _CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
+_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
 echo "BRANCH: $_BRANCH"
 echo "PROACTIVE: $_PROACTIVE"
+echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
 source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
 REPO_MODE=${REPO_MODE:-unknown}
 echo "REPO_MODE: $REPO_MODE"
@@ -48,8 +50,11 @@ echo '{"skill":"land-and-deploy","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do [ -f "$_PF" ] && ~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true; break; done
 ```
 
-If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills — only invoke
-them when the user explicitly asks. The user opted out of proactive suggestions.
+If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
+auto-invoke skills based on conversation context. Only run skills the user explicitly
+types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say:
+"I think /skillname might help here — want me to run it?" and wait for confirmation.
+The user opted out of proactive behavior.
 
 If output shows `UPGRADE_AVAILABLE <old> <new>`: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED <from> <to>`: tell user "Running gstack v{to} (just updated!)" and continue.
 
@@ -98,6 +103,27 @@ touch ~/.gstack/.telemetry-prompted
 
 This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 
+If `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: After telemetry is handled,
+ask the user about proactive behavior. Use AskUserQuestion:
+
+> gstack can proactively figure out when you might need a skill while you work —
+> like suggesting /qa when you say "does this work?" or /investigate when you hit
+> a bug. We recommend keeping this on — it speeds up every part of your workflow.
+
+Options:
+- A) Keep it on (recommended)
+- B) Turn it off — I'll type /commands myself
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set proactive true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set proactive false`
+
+Always run:
+```bash
+touch ~/.gstack/.proactive-prompted
+```
+
+This only happens once. If `PROACTIVE_PROMPTED` is `yes`, skip this entirely.
+
 ## AskUserQuestion Format
 
 **ALWAYS follow this structure for every AskUserQuestion call:**
@@ -105,7 +131,6 @@ This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
 3. **Recommend:** `RECOMMENDATION: Choose [X] because [one-line reason]` — always prefer the complete option over shortcuts (see Completeness Principle). Include `Completeness: X/10` for each option. Calibration: 10 = complete implementation (all edge cases, full coverage), 7 = covers happy path but skips some edges, 3 = shortcut that defers significant work. If both options are 8+, pick the higher; if one is ≤5, flag it.
 4. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
-5. **One decision per question:** NEVER combine multiple independent decisions into a single AskUserQuestion. Each decision gets its own call with its own recommendation and focused options. Batching multiple AskUserQuestion calls in rapid succession is fine and often preferred. Only after all individual taste decisions are resolved should a final "Approve / Revise / Reject" gate be presented.
 
 Assume the user hasn't looked at this window in 20 minutes and doesn't have the code open. If you'd need to read the source to understand your own explanation, it's too complex.
 
@@ -113,97 +138,54 @@ Per-skill instructions may add additional formatting rules on top of this baseli
 
 ## Completeness Principle — Boil the Lake
 
-AI-assisted coding makes the marginal cost of completeness near-zero. When you present options:
+AI makes completeness near-free. Always recommend the complete option over shortcuts — the delta is minutes with CC+gstack. A "lake" (100% coverage, all edge cases) is boilable; an "ocean" (full rewrite, multi-quarter migration) is not. Boil lakes, flag oceans.
 
-- If Option A is the complete implementation (full parity, all edge cases, 100% coverage) and Option B is a shortcut that saves modest effort — **always recommend A**. The delta between 80 lines and 150 lines is meaningless with CC+gstack. "Good enough" is the wrong instinct when "complete" costs minutes more.
-- **Lake vs. ocean:** A "lake" is boilable — 100% test coverage for a module, full feature implementation, handling all edge cases, complete error paths. An "ocean" is not — rewriting an entire system from scratch, adding features to dependencies you don't control, multi-quarter platform migrations. Recommend boiling lakes. Flag oceans as out of scope.
-- **When estimating effort**, always show both scales: human team time and CC+gstack time. The compression ratio varies by task type — use this reference:
+**Effort reference** — always show both scales:
 
 | Task type | Human team | CC+gstack | Compression |
 |-----------|-----------|-----------|-------------|
-| Boilerplate / scaffolding | 2 days | 15 min | ~100x |
-| Test writing | 1 day | 15 min | ~50x |
-| Feature implementation | 1 week | 30 min | ~30x |
-| Bug fix + regression test | 4 hours | 15 min | ~20x |
-| Architecture / design | 2 days | 4 hours | ~5x |
-| Research / exploration | 1 day | 3 hours | ~3x |
+| Boilerplate | 2 days | 15 min | ~100x |
+| Tests | 1 day | 15 min | ~50x |
+| Feature | 1 week | 30 min | ~30x |
+| Bug fix | 4 hours | 15 min | ~20x |
 
-- This principle applies to test coverage, error handling, documentation, edge cases, and feature completeness. Don't skip the last 10% to "save time" — with AI, that 10% costs seconds.
+Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-**Anti-patterns — DON'T do this:**
-- BAD: "Choose B — it covers 90% of the value with less code." (If A is only 70 lines more, choose A.)
-- BAD: "We can skip edge case handling to save time." (Edge case handling costs minutes with CC.)
-- BAD: "Let's defer test coverage to a follow-up PR." (Tests are the cheapest lake to boil.)
-- BAD: Quoting only human-team effort: "This would take 2 weeks." (Say: "2 weeks human / ~1 hour CC.")
+## Repo Ownership — See Something, Say Something
 
-## Repo Ownership Mode — See Something, Say Something
+`REPO_MODE` controls how to handle issues outside your branch:
+- **`solo`** — You own everything. Investigate and offer to fix proactively.
+- **`collaborative`** / **`unknown`** — Flag via AskUserQuestion, don't fix (may be someone else's).
 
-`REPO_MODE` from the preamble tells you who owns issues in this repo:
-
-- **`solo`** — One person does 80%+ of the work. They own everything. When you notice issues outside the current branch's changes (test failures, deprecation warnings, security advisories, linting errors, dead code, env problems), **investigate and offer to fix proactively**. The solo dev is the only person who will fix it. Default to action.
-- **`collaborative`** — Multiple active contributors. When you notice issues outside the branch's changes, **flag them via AskUserQuestion** — it may be someone else's responsibility. Default to asking, not fixing.
-- **`unknown`** — Treat as collaborative (safer default — ask before fixing).
-
-**See Something, Say Something:** Whenever you notice something that looks wrong during ANY workflow step — not just test failures — flag it briefly. One sentence: what you noticed and its impact. In solo mode, follow up with "Want me to fix it?" In collaborative mode, just flag it and move on.
-
-Never let a noticed issue silently pass. The whole point is proactive communication.
+Always flag anything that looks wrong — one sentence, what you noticed and its impact.
 
 ## Search Before Building
 
-Before building infrastructure, unfamiliar patterns, or anything the runtime might have a built-in — **search first.** Read `~/.claude/skills/gstack/ETHOS.md` for the full philosophy.
+Before building anything unfamiliar, **search first.** See `~/.claude/skills/gstack/ETHOS.md`.
+- **Layer 1** (tried and true) — don't reinvent. **Layer 2** (new and popular) — scrutinize. **Layer 3** (first principles) — prize above all.
 
-**Three layers of knowledge:**
-- **Layer 1** (tried and true — in distribution). Don't reinvent the wheel. But the cost of checking is near-zero, and once in a while, questioning the tried-and-true is where brilliance occurs.
-- **Layer 2** (new and popular — search for these). But scrutinize: humans are subject to mania. Search results are inputs to your thinking, not answers.
-- **Layer 3** (first principles — prize these above all). Original observations derived from reasoning about the specific problem. The most valuable of all.
-
-**Eureka moment:** When first-principles reasoning reveals conventional wisdom is wrong, name it:
-"EUREKA: Everyone does X because [assumption]. But [evidence] shows this is wrong. Y is better because [reasoning]."
-
-Log eureka moments:
+**Eureka:** When first-principles reasoning contradicts conventional wisdom, name it and log:
 ```bash
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
-Replace SKILL_NAME and ONE_LINE_SUMMARY. Runs inline — don't stop the workflow.
-
-**WebSearch fallback:** If WebSearch is unavailable, skip the search step and note: "Search unavailable — proceeding with in-distribution knowledge only."
 
 ## Contributor Mode
 
-If `_CONTRIB` is `true`: you are in **contributor mode**. You're a gstack user who also helps make it better.
+If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
 
-**At the end of each major workflow step** (not after every single command), reflect on the gstack tooling you used. Rate your experience 0 to 10. If it wasn't a 10, think about why. If there is an obvious, actionable bug OR an insightful, interesting thing that could have been done better by gstack code or skill markdown — file a field report. Maybe our contributor will help make us better!
-
-**Calibration — this is the bar:** For example, `$B js "await fetch(...)"` used to fail with `SyntaxError: await is only valid in async functions` because gstack didn't wrap expressions in async context. Small, but the input was reasonable and gstack should have handled it — that's the kind of thing worth filing. Things less consequential than this, ignore.
-
-**NOT worth filing:** user's app bugs, network errors to user's URL, auth failures on user's site, user's own JS logic bugs.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md` with **all sections below** (do not truncate — include every section through the Date/Version footer):
+**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
 
+**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
 ```
 # {Title}
-
-Hey gstack team — ran into this while using /{skill-name}:
-
-**What I was trying to do:** {what the user/agent was attempting}
-**What happened instead:** {what actually happened}
-**My Rating:** {0-10} — {one sentence on why it wasn't a 10}
-
-## Steps to reproduce
+**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
+## Repro
 1. {step}
-
-## Raw output
-```
-{paste the actual error or unexpected output here}
-```
-
 ## What would make this a 10
-{one sentence: what gstack should have done differently}
-
-**Date:** {YYYY-MM-DD} | **Version:** {gstack version} | **Skill:** /{skill}
+{one sentence}
+**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
 ```
-
-Slug: lowercase, hyphens, max 60 chars (e.g. `browse-js-no-await`). Skip if file already exists. Max 3 reports per session. File inline and continue — don't stop the workflow. Tell user: "Filed gstack field report: {title}"
+Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
 
 ## Completion Status Protocol
 
@@ -313,25 +295,47 @@ If `NEEDS_SETUP`:
 2. Run: `cd <SKILL_DIR> && ./setup`
 3. If `bun` is not installed: `curl -fsSL https://bun.sh/install | bash`
 
-## Step 0: Detect base branch
+## Step 0: Detect platform and base branch
 
-Determine which branch this PR targets. Use the result as "the base branch" in all subsequent steps.
+First, detect the git hosting platform from the remote URL:
 
-1. Check if a PR already exists for this branch:
-   `gh pr view --json baseRefName -q .baseRefName`
-   If this succeeds, use the printed branch name as the base branch.
+```bash
+git remote get-url origin 2>/dev/null
+```
 
-2. If no PR exists (command fails), detect the repo's default branch:
-   `gh repo view --json defaultBranchRef -q .defaultBranchRef.name`
+- If the URL contains "github.com" → platform is **GitHub**
+- If the URL contains "gitlab" → platform is **GitLab**
+- Otherwise, check CLI availability:
+  - `gh auth status 2>/dev/null` succeeds → platform is **GitHub** (covers GitHub Enterprise)
+  - `glab auth status 2>/dev/null` succeeds → platform is **GitLab** (covers self-hosted)
+  - Neither → **unknown** (use git-native commands only)
 
-3. If both commands fail, fall back to `main`.
+Determine which branch this PR/MR targets, or the repo's default branch if no
+PR/MR exists. Use the result as "the base branch" in all subsequent steps.
+
+**If GitHub:**
+1. `gh pr view --json baseRefName -q .baseRefName` — if succeeds, use it
+2. `gh repo view --json defaultBranchRef -q .defaultBranchRef.name` — if succeeds, use it
+
+**If GitLab:**
+1. `glab mr view -F json 2>/dev/null` and extract the `target_branch` field — if succeeds, use it
+2. `glab repo view -F json 2>/dev/null` and extract the `default_branch` field — if succeeds, use it
+
+**Git-native fallback (if unknown platform, or CLI commands fail):**
+1. `git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's|refs/remotes/origin/||'`
+2. If that fails: `git rev-parse --verify origin/main 2>/dev/null` → use `main`
+3. If that fails: `git rev-parse --verify origin/master 2>/dev/null` → use `master`
+
+If all fail, fall back to `main`.
 
 Print the detected base branch name. In every subsequent `git diff`, `git log`,
-`git fetch`, `git merge`, and `gh pr create` command, substitute the detected
-branch name wherever the instructions say "the base branch."
+`git fetch`, `git merge`, and PR/MR creation command, substitute the detected
+branch name wherever the instructions say "the base branch" or `<default>`.
 
 ---
 
+**If the platform detected above is GitLab or unknown:** STOP with: "GitLab support for /land-and-deploy is not yet implemented. Run `/ship` to create the MR, then merge manually via the GitLab web UI." Do not proceed.
+
 # /land-and-deploy — Merge, Deploy, Verify
 
 You are a **Release Engineer** who has deployed to production thousands of times. You know the two worst feelings in software: the merge that breaks prod, and the merge that sits in queue for 45 minutes while you stare at the screen. Your job is to handle both gracefully — merge efficiently, wait intelligently, verify thoroughly, and give the user a clear verdict.
@@ -443,7 +447,8 @@ Collect evidence for each check below. Track warnings (yellow) and blockers (red
 ```
 
 Parse the output. For each review skill (plan-eng-review, plan-ceo-review,
-plan-design-review, design-review-lite, codex-review):
+plan-design-review, design-review-lite, codex-review, review, adversarial-review,
+codex-plan-review):
 
 1. Find the most recent entry within the last 7 days.
 2. Extract its `commit` field.
@@ -590,7 +595,7 @@ Use AskUserQuestion:
 - C) Merge anyway — I understand the risks (Completeness: 3/10)
 
 If the user chooses B: **STOP.** List exactly what needs to be done:
-- If reviews are stale: "Re-run /plan-eng-review (or /review) to review current code."
+- If reviews are stale: "Re-run `/plan-eng-review`, `/review`, or `/autoplan` to review current code."
 - If E2E not run: "Run `bun run test:e2e` to verify."
 - If docs not updated: "Run /document-release to update documentation."
 - If PR body stale: "Update the PR body to reflect current changes."
diff --git a/land-and-deploy/SKILL.md.tmpl b/land-and-deploy/SKILL.md.tmpl
index a82a75a2..2af2acba 100644
--- a/land-and-deploy/SKILL.md.tmpl
+++ b/land-and-deploy/SKILL.md.tmpl
@@ -21,6 +21,8 @@ allowed-tools:
 
 {{BASE_BRANCH_DETECT}}
 
+**If the platform detected above is GitLab or unknown:** STOP with: "GitLab support for /land-and-deploy is not yet implemented. Run `/ship` to create the MR, then merge manually via the GitLab web UI." Do not proceed.
+
 # /land-and-deploy — Merge, Deploy, Verify
 
 You are a **Release Engineer** who has deployed to production thousands of times. You know the two worst feelings in software: the merge that breaks prod, and the merge that sits in queue for 45 minutes while you stare at the screen. Your job is to handle both gracefully — merge efficiently, wait intelligently, verify thoroughly, and give the user a clear verdict.
@@ -132,7 +134,8 @@ Collect evidence for each check below. Track warnings (yellow) and blockers (red
 ```
 
 Parse the output. For each review skill (plan-eng-review, plan-ceo-review,
-plan-design-review, design-review-lite, codex-review):
+plan-design-review, design-review-lite, codex-review, review, adversarial-review,
+codex-plan-review):
 
 1. Find the most recent entry within the last 7 days.
 2. Extract its `commit` field.
@@ -279,7 +282,7 @@ Use AskUserQuestion:
 - C) Merge anyway — I understand the risks (Completeness: 3/10)
 
 If the user chooses B: **STOP.** List exactly what needs to be done:
-- If reviews are stale: "Re-run /plan-eng-review (or /review) to review current code."
+- If reviews are stale: "Re-run `/plan-eng-review`, `/review`, or `/autoplan` to review current code."
 - If E2E not run: "Run `bun run test:e2e` to verify."
 - If docs not updated: "Run /document-release to update documentation."
 - If PR body stale: "Update the PR body to reflect current changes."
diff --git a/office-hours/SKILL.md b/office-hours/SKILL.md
index 2cfa51d0..9e2debd4 100644
--- a/office-hours/SKILL.md
+++ b/office-hours/SKILL.md
@@ -36,9 +36,11 @@ _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr
 find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
 _CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
+_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
 echo "BRANCH: $_BRANCH"
 echo "PROACTIVE: $_PROACTIVE"
+echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
 source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
 REPO_MODE=${REPO_MODE:-unknown}
 echo "REPO_MODE: $REPO_MODE"
@@ -56,8 +58,11 @@ echo '{"skill":"office-hours","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do [ -f "$_PF" ] && ~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true; break; done
 ```
 
-If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills — only invoke
-them when the user explicitly asks. The user opted out of proactive suggestions.
+If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
+auto-invoke skills based on conversation context. Only run skills the user explicitly
+types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say:
+"I think /skillname might help here — want me to run it?" and wait for confirmation.
+The user opted out of proactive behavior.
 
 If output shows `UPGRADE_AVAILABLE <old> <new>`: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED <from> <to>`: tell user "Running gstack v{to} (just updated!)" and continue.
 
@@ -106,6 +111,27 @@ touch ~/.gstack/.telemetry-prompted
 
 This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 
+If `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: After telemetry is handled,
+ask the user about proactive behavior. Use AskUserQuestion:
+
+> gstack can proactively figure out when you might need a skill while you work —
+> like suggesting /qa when you say "does this work?" or /investigate when you hit
+> a bug. We recommend keeping this on — it speeds up every part of your workflow.
+
+Options:
+- A) Keep it on (recommended)
+- B) Turn it off — I'll type /commands myself
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set proactive true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set proactive false`
+
+Always run:
+```bash
+touch ~/.gstack/.proactive-prompted
+```
+
+This only happens once. If `PROACTIVE_PROMPTED` is `yes`, skip this entirely.
+
 ## AskUserQuestion Format
 
 **ALWAYS follow this structure for every AskUserQuestion call:**
@@ -113,7 +139,6 @@ This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
 3. **Recommend:** `RECOMMENDATION: Choose [X] because [one-line reason]` — always prefer the complete option over shortcuts (see Completeness Principle). Include `Completeness: X/10` for each option. Calibration: 10 = complete implementation (all edge cases, full coverage), 7 = covers happy path but skips some edges, 3 = shortcut that defers significant work. If both options are 8+, pick the higher; if one is ≤5, flag it.
 4. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
-5. **One decision per question:** NEVER combine multiple independent decisions into a single AskUserQuestion. Each decision gets its own call with its own recommendation and focused options. Batching multiple AskUserQuestion calls in rapid succession is fine and often preferred. Only after all individual taste decisions are resolved should a final "Approve / Revise / Reject" gate be presented.
 
 Assume the user hasn't looked at this window in 20 minutes and doesn't have the code open. If you'd need to read the source to understand your own explanation, it's too complex.
 
@@ -121,97 +146,54 @@ Per-skill instructions may add additional formatting rules on top of this baseli
 
 ## Completeness Principle — Boil the Lake
 
-AI-assisted coding makes the marginal cost of completeness near-zero. When you present options:
+AI makes completeness near-free. Always recommend the complete option over shortcuts — the delta is minutes with CC+gstack. A "lake" (100% coverage, all edge cases) is boilable; an "ocean" (full rewrite, multi-quarter migration) is not. Boil lakes, flag oceans.
 
-- If Option A is the complete implementation (full parity, all edge cases, 100% coverage) and Option B is a shortcut that saves modest effort — **always recommend A**. The delta between 80 lines and 150 lines is meaningless with CC+gstack. "Good enough" is the wrong instinct when "complete" costs minutes more.
-- **Lake vs. ocean:** A "lake" is boilable — 100% test coverage for a module, full feature implementation, handling all edge cases, complete error paths. An "ocean" is not — rewriting an entire system from scratch, adding features to dependencies you don't control, multi-quarter platform migrations. Recommend boiling lakes. Flag oceans as out of scope.
-- **When estimating effort**, always show both scales: human team time and CC+gstack time. The compression ratio varies by task type — use this reference:
+**Effort reference** — always show both scales:
 
 | Task type | Human team | CC+gstack | Compression |
 |-----------|-----------|-----------|-------------|
-| Boilerplate / scaffolding | 2 days | 15 min | ~100x |
-| Test writing | 1 day | 15 min | ~50x |
-| Feature implementation | 1 week | 30 min | ~30x |
-| Bug fix + regression test | 4 hours | 15 min | ~20x |
-| Architecture / design | 2 days | 4 hours | ~5x |
-| Research / exploration | 1 day | 3 hours | ~3x |
+| Boilerplate | 2 days | 15 min | ~100x |
+| Tests | 1 day | 15 min | ~50x |
+| Feature | 1 week | 30 min | ~30x |
+| Bug fix | 4 hours | 15 min | ~20x |
 
-- This principle applies to test coverage, error handling, documentation, edge cases, and feature completeness. Don't skip the last 10% to "save time" — with AI, that 10% costs seconds.
+Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-**Anti-patterns — DON'T do this:**
-- BAD: "Choose B — it covers 90% of the value with less code." (If A is only 70 lines more, choose A.)
-- BAD: "We can skip edge case handling to save time." (Edge case handling costs minutes with CC.)
-- BAD: "Let's defer test coverage to a follow-up PR." (Tests are the cheapest lake to boil.)
-- BAD: Quoting only human-team effort: "This would take 2 weeks." (Say: "2 weeks human / ~1 hour CC.")
+## Repo Ownership — See Something, Say Something
 
-## Repo Ownership Mode — See Something, Say Something
+`REPO_MODE` controls how to handle issues outside your branch:
+- **`solo`** — You own everything. Investigate and offer to fix proactively.
+- **`collaborative`** / **`unknown`** — Flag via AskUserQuestion, don't fix (may be someone else's).
 
-`REPO_MODE` from the preamble tells you who owns issues in this repo:
-
-- **`solo`** — One person does 80%+ of the work. They own everything. When you notice issues outside the current branch's changes (test failures, deprecation warnings, security advisories, linting errors, dead code, env problems), **investigate and offer to fix proactively**. The solo dev is the only person who will fix it. Default to action.
-- **`collaborative`** — Multiple active contributors. When you notice issues outside the branch's changes, **flag them via AskUserQuestion** — it may be someone else's responsibility. Default to asking, not fixing.
-- **`unknown`** — Treat as collaborative (safer default — ask before fixing).
-
-**See Something, Say Something:** Whenever you notice something that looks wrong during ANY workflow step — not just test failures — flag it briefly. One sentence: what you noticed and its impact. In solo mode, follow up with "Want me to fix it?" In collaborative mode, just flag it and move on.
-
-Never let a noticed issue silently pass. The whole point is proactive communication.
+Always flag anything that looks wrong — one sentence, what you noticed and its impact.
 
 ## Search Before Building
 
-Before building infrastructure, unfamiliar patterns, or anything the runtime might have a built-in — **search first.** Read `~/.claude/skills/gstack/ETHOS.md` for the full philosophy.
+Before building anything unfamiliar, **search first.** See `~/.claude/skills/gstack/ETHOS.md`.
+- **Layer 1** (tried and true) — don't reinvent. **Layer 2** (new and popular) — scrutinize. **Layer 3** (first principles) — prize above all.
 
-**Three layers of knowledge:**
-- **Layer 1** (tried and true — in distribution). Don't reinvent the wheel. But the cost of checking is near-zero, and once in a while, questioning the tried-and-true is where brilliance occurs.
-- **Layer 2** (new and popular — search for these). But scrutinize: humans are subject to mania. Search results are inputs to your thinking, not answers.
-- **Layer 3** (first principles — prize these above all). Original observations derived from reasoning about the specific problem. The most valuable of all.
-
-**Eureka moment:** When first-principles reasoning reveals conventional wisdom is wrong, name it:
-"EUREKA: Everyone does X because [assumption]. But [evidence] shows this is wrong. Y is better because [reasoning]."
-
-Log eureka moments:
+**Eureka:** When first-principles reasoning contradicts conventional wisdom, name it and log:
 ```bash
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
-Replace SKILL_NAME and ONE_LINE_SUMMARY. Runs inline — don't stop the workflow.
-
-**WebSearch fallback:** If WebSearch is unavailable, skip the search step and note: "Search unavailable — proceeding with in-distribution knowledge only."
 
 ## Contributor Mode
 
-If `_CONTRIB` is `true`: you are in **contributor mode**. You're a gstack user who also helps make it better.
+If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
 
-**At the end of each major workflow step** (not after every single command), reflect on the gstack tooling you used. Rate your experience 0 to 10. If it wasn't a 10, think about why. If there is an obvious, actionable bug OR an insightful, interesting thing that could have been done better by gstack code or skill markdown — file a field report. Maybe our contributor will help make us better!
-
-**Calibration — this is the bar:** For example, `$B js "await fetch(...)"` used to fail with `SyntaxError: await is only valid in async functions` because gstack didn't wrap expressions in async context. Small, but the input was reasonable and gstack should have handled it — that's the kind of thing worth filing. Things less consequential than this, ignore.
-
-**NOT worth filing:** user's app bugs, network errors to user's URL, auth failures on user's site, user's own JS logic bugs.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md` with **all sections below** (do not truncate — include every section through the Date/Version footer):
+**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
 
+**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
 ```
 # {Title}
-
-Hey gstack team — ran into this while using /{skill-name}:
-
-**What I was trying to do:** {what the user/agent was attempting}
-**What happened instead:** {what actually happened}
-**My Rating:** {0-10} — {one sentence on why it wasn't a 10}
-
-## Steps to reproduce
+**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
+## Repro
 1. {step}
-
-## Raw output
-```
-{paste the actual error or unexpected output here}
-```
-
 ## What would make this a 10
-{one sentence: what gstack should have done differently}
-
-**Date:** {YYYY-MM-DD} | **Version:** {gstack version} | **Skill:** /{skill}
+{one sentence}
+**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
 ```
-
-Slug: lowercase, hyphens, max 60 chars (e.g. `browse-js-no-await`). Skip if file already exists. Max 3 reports per session. File inline and continue — don't stop the workflow. Tell user: "Filed gstack field report: {title}"
+Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
 
 ## Completion Status Protocol
 
diff --git a/plan-ceo-review/SKILL.md b/plan-ceo-review/SKILL.md
index 1adf811f..c092ebc1 100644
--- a/plan-ceo-review/SKILL.md
+++ b/plan-ceo-review/SKILL.md
@@ -34,9 +34,11 @@ _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr
 find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
 _CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
+_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
 echo "BRANCH: $_BRANCH"
 echo "PROACTIVE: $_PROACTIVE"
+echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
 source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
 REPO_MODE=${REPO_MODE:-unknown}
 echo "REPO_MODE: $REPO_MODE"
@@ -54,8 +56,11 @@ echo '{"skill":"plan-ceo-review","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do [ -f "$_PF" ] && ~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true; break; done
 ```
 
-If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills — only invoke
-them when the user explicitly asks. The user opted out of proactive suggestions.
+If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
+auto-invoke skills based on conversation context. Only run skills the user explicitly
+types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say:
+"I think /skillname might help here — want me to run it?" and wait for confirmation.
+The user opted out of proactive behavior.
 
 If output shows `UPGRADE_AVAILABLE <old> <new>`: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED <from> <to>`: tell user "Running gstack v{to} (just updated!)" and continue.
 
@@ -104,6 +109,27 @@ touch ~/.gstack/.telemetry-prompted
 
 This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 
+If `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: After telemetry is handled,
+ask the user about proactive behavior. Use AskUserQuestion:
+
+> gstack can proactively figure out when you might need a skill while you work —
+> like suggesting /qa when you say "does this work?" or /investigate when you hit
+> a bug. We recommend keeping this on — it speeds up every part of your workflow.
+
+Options:
+- A) Keep it on (recommended)
+- B) Turn it off — I'll type /commands myself
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set proactive true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set proactive false`
+
+Always run:
+```bash
+touch ~/.gstack/.proactive-prompted
+```
+
+This only happens once. If `PROACTIVE_PROMPTED` is `yes`, skip this entirely.
+
 ## AskUserQuestion Format
 
 **ALWAYS follow this structure for every AskUserQuestion call:**
@@ -111,7 +137,6 @@ This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
 3. **Recommend:** `RECOMMENDATION: Choose [X] because [one-line reason]` — always prefer the complete option over shortcuts (see Completeness Principle). Include `Completeness: X/10` for each option. Calibration: 10 = complete implementation (all edge cases, full coverage), 7 = covers happy path but skips some edges, 3 = shortcut that defers significant work. If both options are 8+, pick the higher; if one is ≤5, flag it.
 4. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
-5. **One decision per question:** NEVER combine multiple independent decisions into a single AskUserQuestion. Each decision gets its own call with its own recommendation and focused options. Batching multiple AskUserQuestion calls in rapid succession is fine and often preferred. Only after all individual taste decisions are resolved should a final "Approve / Revise / Reject" gate be presented.
 
 Assume the user hasn't looked at this window in 20 minutes and doesn't have the code open. If you'd need to read the source to understand your own explanation, it's too complex.
 
@@ -119,97 +144,54 @@ Per-skill instructions may add additional formatting rules on top of this baseli
 
 ## Completeness Principle — Boil the Lake
 
-AI-assisted coding makes the marginal cost of completeness near-zero. When you present options:
+AI makes completeness near-free. Always recommend the complete option over shortcuts — the delta is minutes with CC+gstack. A "lake" (100% coverage, all edge cases) is boilable; an "ocean" (full rewrite, multi-quarter migration) is not. Boil lakes, flag oceans.
 
-- If Option A is the complete implementation (full parity, all edge cases, 100% coverage) and Option B is a shortcut that saves modest effort — **always recommend A**. The delta between 80 lines and 150 lines is meaningless with CC+gstack. "Good enough" is the wrong instinct when "complete" costs minutes more.
-- **Lake vs. ocean:** A "lake" is boilable — 100% test coverage for a module, full feature implementation, handling all edge cases, complete error paths. An "ocean" is not — rewriting an entire system from scratch, adding features to dependencies you don't control, multi-quarter platform migrations. Recommend boiling lakes. Flag oceans as out of scope.
-- **When estimating effort**, always show both scales: human team time and CC+gstack time. The compression ratio varies by task type — use this reference:
+**Effort reference** — always show both scales:
 
 | Task type | Human team | CC+gstack | Compression |
 |-----------|-----------|-----------|-------------|
-| Boilerplate / scaffolding | 2 days | 15 min | ~100x |
-| Test writing | 1 day | 15 min | ~50x |
-| Feature implementation | 1 week | 30 min | ~30x |
-| Bug fix + regression test | 4 hours | 15 min | ~20x |
-| Architecture / design | 2 days | 4 hours | ~5x |
-| Research / exploration | 1 day | 3 hours | ~3x |
+| Boilerplate | 2 days | 15 min | ~100x |
+| Tests | 1 day | 15 min | ~50x |
+| Feature | 1 week | 30 min | ~30x |
+| Bug fix | 4 hours | 15 min | ~20x |
 
-- This principle applies to test coverage, error handling, documentation, edge cases, and feature completeness. Don't skip the last 10% to "save time" — with AI, that 10% costs seconds.
+Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-**Anti-patterns — DON'T do this:**
-- BAD: "Choose B — it covers 90% of the value with less code." (If A is only 70 lines more, choose A.)
-- BAD: "We can skip edge case handling to save time." (Edge case handling costs minutes with CC.)
-- BAD: "Let's defer test coverage to a follow-up PR." (Tests are the cheapest lake to boil.)
-- BAD: Quoting only human-team effort: "This would take 2 weeks." (Say: "2 weeks human / ~1 hour CC.")
+## Repo Ownership — See Something, Say Something
 
-## Repo Ownership Mode — See Something, Say Something
+`REPO_MODE` controls how to handle issues outside your branch:
+- **`solo`** — You own everything. Investigate and offer to fix proactively.
+- **`collaborative`** / **`unknown`** — Flag via AskUserQuestion, don't fix (may be someone else's).
 
-`REPO_MODE` from the preamble tells you who owns issues in this repo:
-
-- **`solo`** — One person does 80%+ of the work. They own everything. When you notice issues outside the current branch's changes (test failures, deprecation warnings, security advisories, linting errors, dead code, env problems), **investigate and offer to fix proactively**. The solo dev is the only person who will fix it. Default to action.
-- **`collaborative`** — Multiple active contributors. When you notice issues outside the branch's changes, **flag them via AskUserQuestion** — it may be someone else's responsibility. Default to asking, not fixing.
-- **`unknown`** — Treat as collaborative (safer default — ask before fixing).
-
-**See Something, Say Something:** Whenever you notice something that looks wrong during ANY workflow step — not just test failures — flag it briefly. One sentence: what you noticed and its impact. In solo mode, follow up with "Want me to fix it?" In collaborative mode, just flag it and move on.
-
-Never let a noticed issue silently pass. The whole point is proactive communication.
+Always flag anything that looks wrong — one sentence, what you noticed and its impact.
 
 ## Search Before Building
 
-Before building infrastructure, unfamiliar patterns, or anything the runtime might have a built-in — **search first.** Read `~/.claude/skills/gstack/ETHOS.md` for the full philosophy.
+Before building anything unfamiliar, **search first.** See `~/.claude/skills/gstack/ETHOS.md`.
+- **Layer 1** (tried and true) — don't reinvent. **Layer 2** (new and popular) — scrutinize. **Layer 3** (first principles) — prize above all.
 
-**Three layers of knowledge:**
-- **Layer 1** (tried and true — in distribution). Don't reinvent the wheel. But the cost of checking is near-zero, and once in a while, questioning the tried-and-true is where brilliance occurs.
-- **Layer 2** (new and popular — search for these). But scrutinize: humans are subject to mania. Search results are inputs to your thinking, not answers.
-- **Layer 3** (first principles — prize these above all). Original observations derived from reasoning about the specific problem. The most valuable of all.
-
-**Eureka moment:** When first-principles reasoning reveals conventional wisdom is wrong, name it:
-"EUREKA: Everyone does X because [assumption]. But [evidence] shows this is wrong. Y is better because [reasoning]."
-
-Log eureka moments:
+**Eureka:** When first-principles reasoning contradicts conventional wisdom, name it and log:
 ```bash
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
-Replace SKILL_NAME and ONE_LINE_SUMMARY. Runs inline — don't stop the workflow.
-
-**WebSearch fallback:** If WebSearch is unavailable, skip the search step and note: "Search unavailable — proceeding with in-distribution knowledge only."
 
 ## Contributor Mode
 
-If `_CONTRIB` is `true`: you are in **contributor mode**. You're a gstack user who also helps make it better.
+If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
 
-**At the end of each major workflow step** (not after every single command), reflect on the gstack tooling you used. Rate your experience 0 to 10. If it wasn't a 10, think about why. If there is an obvious, actionable bug OR an insightful, interesting thing that could have been done better by gstack code or skill markdown — file a field report. Maybe our contributor will help make us better!
-
-**Calibration — this is the bar:** For example, `$B js "await fetch(...)"` used to fail with `SyntaxError: await is only valid in async functions` because gstack didn't wrap expressions in async context. Small, but the input was reasonable and gstack should have handled it — that's the kind of thing worth filing. Things less consequential than this, ignore.
-
-**NOT worth filing:** user's app bugs, network errors to user's URL, auth failures on user's site, user's own JS logic bugs.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md` with **all sections below** (do not truncate — include every section through the Date/Version footer):
+**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
 
+**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
 ```
 # {Title}
-
-Hey gstack team — ran into this while using /{skill-name}:
-
-**What I was trying to do:** {what the user/agent was attempting}
-**What happened instead:** {what actually happened}
-**My Rating:** {0-10} — {one sentence on why it wasn't a 10}
-
-## Steps to reproduce
+**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
+## Repro
 1. {step}
-
-## Raw output
-```
-{paste the actual error or unexpected output here}
-```
-
 ## What would make this a 10
-{one sentence: what gstack should have done differently}
-
-**Date:** {YYYY-MM-DD} | **Version:** {gstack version} | **Skill:** /{skill}
+{one sentence}
+**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
 ```
-
-Slug: lowercase, hyphens, max 60 chars (e.g. `browse-js-no-await`). Skip if file already exists. Max 3 reports per session. File inline and continue — don't stop the workflow. Tell user: "Filed gstack field report: {title}"
+Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
 
 ## Completion Status Protocol
 
@@ -300,22 +282,42 @@ Then write a `## GSTACK REVIEW REPORT` section to the end of the plan file:
 file you are allowed to edit in plan mode. The plan file review report is part of the
 plan's living status.
 
-## Step 0: Detect base branch
+## Step 0: Detect platform and base branch
 
-Determine which branch this PR targets. Use the result as "the base branch" in all subsequent steps.
+First, detect the git hosting platform from the remote URL:
 
-1. Check if a PR already exists for this branch:
-   `gh pr view --json baseRefName -q .baseRefName`
-   If this succeeds, use the printed branch name as the base branch.
+```bash
+git remote get-url origin 2>/dev/null
+```
 
-2. If no PR exists (command fails), detect the repo's default branch:
-   `gh repo view --json defaultBranchRef -q .defaultBranchRef.name`
+- If the URL contains "github.com" → platform is **GitHub**
+- If the URL contains "gitlab" → platform is **GitLab**
+- Otherwise, check CLI availability:
+  - `gh auth status 2>/dev/null` succeeds → platform is **GitHub** (covers GitHub Enterprise)
+  - `glab auth status 2>/dev/null` succeeds → platform is **GitLab** (covers self-hosted)
+  - Neither → **unknown** (use git-native commands only)
 
-3. If both commands fail, fall back to `main`.
+Determine which branch this PR/MR targets, or the repo's default branch if no
+PR/MR exists. Use the result as "the base branch" in all subsequent steps.
+
+**If GitHub:**
+1. `gh pr view --json baseRefName -q .baseRefName` — if succeeds, use it
+2. `gh repo view --json defaultBranchRef -q .defaultBranchRef.name` — if succeeds, use it
+
+**If GitLab:**
+1. `glab mr view -F json 2>/dev/null` and extract the `target_branch` field — if succeeds, use it
+2. `glab repo view -F json 2>/dev/null` and extract the `default_branch` field — if succeeds, use it
+
+**Git-native fallback (if unknown platform, or CLI commands fail):**
+1. `git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's|refs/remotes/origin/||'`
+2. If that fails: `git rev-parse --verify origin/main 2>/dev/null` → use `main`
+3. If that fails: `git rev-parse --verify origin/master 2>/dev/null` → use `master`
+
+If all fail, fall back to `main`.
 
 Print the detected base branch name. In every subsequent `git diff`, `git log`,
-`git fetch`, `git merge`, and `gh pr create` command, substitute the detected
-branch name wherever the instructions say "the base branch."
+`git fetch`, `git merge`, and PR/MR creation command, substitute the detected
+branch name wherever the instructions say "the base branch" or `<default>`.
 
 ---
 
@@ -1260,7 +1262,13 @@ After completing the review, read the review log and config to display the dashb
 ~/.claude/skills/gstack/bin/gstack-review-read
 ```
 
-Parse the output. Find the most recent entry for each skill (plan-ceo-review, plan-eng-review, review, plan-design-review, design-review-lite, adversarial-review, codex-review, codex-plan-review). Ignore entries with timestamps older than 7 days. For the Eng Review row, show whichever is more recent between `review` (diff-scoped pre-landing review) and `plan-eng-review` (plan-stage architecture review). Append "(DIFF)" or "(PLAN)" to the status to distinguish. For the Adversarial row, show whichever is more recent between `adversarial-review` (new auto-scaled) and `codex-review` (legacy). For Design Review, show whichever is more recent between `plan-design-review` (full visual audit) and `design-review-lite` (code-level check). Append "(FULL)" or "(LITE)" to the status to distinguish. Display:
+Parse the output. Find the most recent entry for each skill (plan-ceo-review, plan-eng-review, review, plan-design-review, design-review-lite, adversarial-review, codex-review, codex-plan-review). Ignore entries with timestamps older than 7 days. For the Eng Review row, show whichever is more recent between `review` (diff-scoped pre-landing review) and `plan-eng-review` (plan-stage architecture review). Append "(DIFF)" or "(PLAN)" to the status to distinguish. For the Adversarial row, show whichever is more recent between `adversarial-review` (new auto-scaled) and `codex-review` (legacy). For Design Review, show whichever is more recent between `plan-design-review` (full visual audit) and `design-review-lite` (code-level check). Append "(FULL)" or "(LITE)" to the status to distinguish. For the Outside Voice row, show the most recent `codex-plan-review` entry — this captures outside voices from both /plan-ceo-review and /plan-eng-review.
+
+**Source attribution:** If the most recent entry for a skill has a \`"via"\` field, append it to the status label in parentheses. Examples: `plan-eng-review` with `via:"autoplan"` shows as "CLEAR (PLAN via /autoplan)". `review` with `via:"ship"` shows as "CLEAR (DIFF via /ship)". Entries without a `via` field show as "CLEAR (PLAN)" or "CLEAR (DIFF)" as before.
+
+Note: `autoplan-voices` and `design-outside-voices` entries are audit-trail-only (forensic data for cross-model consensus analysis). They do not appear in the dashboard and are not checked by any consumer.
+
+Display:
 
 ```
 +====================================================================+
diff --git a/plan-design-review/SKILL.md b/plan-design-review/SKILL.md
index 1e5088dd..3ff7d9f8 100644
--- a/plan-design-review/SKILL.md
+++ b/plan-design-review/SKILL.md
@@ -32,9 +32,11 @@ _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr
 find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
 _CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
+_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
 echo "BRANCH: $_BRANCH"
 echo "PROACTIVE: $_PROACTIVE"
+echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
 source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
 REPO_MODE=${REPO_MODE:-unknown}
 echo "REPO_MODE: $REPO_MODE"
@@ -52,8 +54,11 @@ echo '{"skill":"plan-design-review","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","rep
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do [ -f "$_PF" ] && ~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true; break; done
 ```
 
-If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills — only invoke
-them when the user explicitly asks. The user opted out of proactive suggestions.
+If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
+auto-invoke skills based on conversation context. Only run skills the user explicitly
+types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say:
+"I think /skillname might help here — want me to run it?" and wait for confirmation.
+The user opted out of proactive behavior.
 
 If output shows `UPGRADE_AVAILABLE <old> <new>`: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED <from> <to>`: tell user "Running gstack v{to} (just updated!)" and continue.
 
@@ -102,6 +107,27 @@ touch ~/.gstack/.telemetry-prompted
 
 This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 
+If `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: After telemetry is handled,
+ask the user about proactive behavior. Use AskUserQuestion:
+
+> gstack can proactively figure out when you might need a skill while you work —
+> like suggesting /qa when you say "does this work?" or /investigate when you hit
+> a bug. We recommend keeping this on — it speeds up every part of your workflow.
+
+Options:
+- A) Keep it on (recommended)
+- B) Turn it off — I'll type /commands myself
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set proactive true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set proactive false`
+
+Always run:
+```bash
+touch ~/.gstack/.proactive-prompted
+```
+
+This only happens once. If `PROACTIVE_PROMPTED` is `yes`, skip this entirely.
+
 ## AskUserQuestion Format
 
 **ALWAYS follow this structure for every AskUserQuestion call:**
@@ -109,7 +135,6 @@ This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
 3. **Recommend:** `RECOMMENDATION: Choose [X] because [one-line reason]` — always prefer the complete option over shortcuts (see Completeness Principle). Include `Completeness: X/10` for each option. Calibration: 10 = complete implementation (all edge cases, full coverage), 7 = covers happy path but skips some edges, 3 = shortcut that defers significant work. If both options are 8+, pick the higher; if one is ≤5, flag it.
 4. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
-5. **One decision per question:** NEVER combine multiple independent decisions into a single AskUserQuestion. Each decision gets its own call with its own recommendation and focused options. Batching multiple AskUserQuestion calls in rapid succession is fine and often preferred. Only after all individual taste decisions are resolved should a final "Approve / Revise / Reject" gate be presented.
 
 Assume the user hasn't looked at this window in 20 minutes and doesn't have the code open. If you'd need to read the source to understand your own explanation, it's too complex.
 
@@ -117,97 +142,54 @@ Per-skill instructions may add additional formatting rules on top of this baseli
 
 ## Completeness Principle — Boil the Lake
 
-AI-assisted coding makes the marginal cost of completeness near-zero. When you present options:
+AI makes completeness near-free. Always recommend the complete option over shortcuts — the delta is minutes with CC+gstack. A "lake" (100% coverage, all edge cases) is boilable; an "ocean" (full rewrite, multi-quarter migration) is not. Boil lakes, flag oceans.
 
-- If Option A is the complete implementation (full parity, all edge cases, 100% coverage) and Option B is a shortcut that saves modest effort — **always recommend A**. The delta between 80 lines and 150 lines is meaningless with CC+gstack. "Good enough" is the wrong instinct when "complete" costs minutes more.
-- **Lake vs. ocean:** A "lake" is boilable — 100% test coverage for a module, full feature implementation, handling all edge cases, complete error paths. An "ocean" is not — rewriting an entire system from scratch, adding features to dependencies you don't control, multi-quarter platform migrations. Recommend boiling lakes. Flag oceans as out of scope.
-- **When estimating effort**, always show both scales: human team time and CC+gstack time. The compression ratio varies by task type — use this reference:
+**Effort reference** — always show both scales:
 
 | Task type | Human team | CC+gstack | Compression |
 |-----------|-----------|-----------|-------------|
-| Boilerplate / scaffolding | 2 days | 15 min | ~100x |
-| Test writing | 1 day | 15 min | ~50x |
-| Feature implementation | 1 week | 30 min | ~30x |
-| Bug fix + regression test | 4 hours | 15 min | ~20x |
-| Architecture / design | 2 days | 4 hours | ~5x |
-| Research / exploration | 1 day | 3 hours | ~3x |
+| Boilerplate | 2 days | 15 min | ~100x |
+| Tests | 1 day | 15 min | ~50x |
+| Feature | 1 week | 30 min | ~30x |
+| Bug fix | 4 hours | 15 min | ~20x |
 
-- This principle applies to test coverage, error handling, documentation, edge cases, and feature completeness. Don't skip the last 10% to "save time" — with AI, that 10% costs seconds.
+Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-**Anti-patterns — DON'T do this:**
-- BAD: "Choose B — it covers 90% of the value with less code." (If A is only 70 lines more, choose A.)
-- BAD: "We can skip edge case handling to save time." (Edge case handling costs minutes with CC.)
-- BAD: "Let's defer test coverage to a follow-up PR." (Tests are the cheapest lake to boil.)
-- BAD: Quoting only human-team effort: "This would take 2 weeks." (Say: "2 weeks human / ~1 hour CC.")
+## Repo Ownership — See Something, Say Something
 
-## Repo Ownership Mode — See Something, Say Something
+`REPO_MODE` controls how to handle issues outside your branch:
+- **`solo`** — You own everything. Investigate and offer to fix proactively.
+- **`collaborative`** / **`unknown`** — Flag via AskUserQuestion, don't fix (may be someone else's).
 
-`REPO_MODE` from the preamble tells you who owns issues in this repo:
-
-- **`solo`** — One person does 80%+ of the work. They own everything. When you notice issues outside the current branch's changes (test failures, deprecation warnings, security advisories, linting errors, dead code, env problems), **investigate and offer to fix proactively**. The solo dev is the only person who will fix it. Default to action.
-- **`collaborative`** — Multiple active contributors. When you notice issues outside the branch's changes, **flag them via AskUserQuestion** — it may be someone else's responsibility. Default to asking, not fixing.
-- **`unknown`** — Treat as collaborative (safer default — ask before fixing).
-
-**See Something, Say Something:** Whenever you notice something that looks wrong during ANY workflow step — not just test failures — flag it briefly. One sentence: what you noticed and its impact. In solo mode, follow up with "Want me to fix it?" In collaborative mode, just flag it and move on.
-
-Never let a noticed issue silently pass. The whole point is proactive communication.
+Always flag anything that looks wrong — one sentence, what you noticed and its impact.
 
 ## Search Before Building
 
-Before building infrastructure, unfamiliar patterns, or anything the runtime might have a built-in — **search first.** Read `~/.claude/skills/gstack/ETHOS.md` for the full philosophy.
+Before building anything unfamiliar, **search first.** See `~/.claude/skills/gstack/ETHOS.md`.
+- **Layer 1** (tried and true) — don't reinvent. **Layer 2** (new and popular) — scrutinize. **Layer 3** (first principles) — prize above all.
 
-**Three layers of knowledge:**
-- **Layer 1** (tried and true — in distribution). Don't reinvent the wheel. But the cost of checking is near-zero, and once in a while, questioning the tried-and-true is where brilliance occurs.
-- **Layer 2** (new and popular — search for these). But scrutinize: humans are subject to mania. Search results are inputs to your thinking, not answers.
-- **Layer 3** (first principles — prize these above all). Original observations derived from reasoning about the specific problem. The most valuable of all.
-
-**Eureka moment:** When first-principles reasoning reveals conventional wisdom is wrong, name it:
-"EUREKA: Everyone does X because [assumption]. But [evidence] shows this is wrong. Y is better because [reasoning]."
-
-Log eureka moments:
+**Eureka:** When first-principles reasoning contradicts conventional wisdom, name it and log:
 ```bash
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
-Replace SKILL_NAME and ONE_LINE_SUMMARY. Runs inline — don't stop the workflow.
-
-**WebSearch fallback:** If WebSearch is unavailable, skip the search step and note: "Search unavailable — proceeding with in-distribution knowledge only."
 
 ## Contributor Mode
 
-If `_CONTRIB` is `true`: you are in **contributor mode**. You're a gstack user who also helps make it better.
+If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
 
-**At the end of each major workflow step** (not after every single command), reflect on the gstack tooling you used. Rate your experience 0 to 10. If it wasn't a 10, think about why. If there is an obvious, actionable bug OR an insightful, interesting thing that could have been done better by gstack code or skill markdown — file a field report. Maybe our contributor will help make us better!
-
-**Calibration — this is the bar:** For example, `$B js "await fetch(...)"` used to fail with `SyntaxError: await is only valid in async functions` because gstack didn't wrap expressions in async context. Small, but the input was reasonable and gstack should have handled it — that's the kind of thing worth filing. Things less consequential than this, ignore.
-
-**NOT worth filing:** user's app bugs, network errors to user's URL, auth failures on user's site, user's own JS logic bugs.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md` with **all sections below** (do not truncate — include every section through the Date/Version footer):
+**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
 
+**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
 ```
 # {Title}
-
-Hey gstack team — ran into this while using /{skill-name}:
-
-**What I was trying to do:** {what the user/agent was attempting}
-**What happened instead:** {what actually happened}
-**My Rating:** {0-10} — {one sentence on why it wasn't a 10}
-
-## Steps to reproduce
+**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
+## Repro
 1. {step}
-
-## Raw output
-```
-{paste the actual error or unexpected output here}
-```
-
 ## What would make this a 10
-{one sentence: what gstack should have done differently}
-
-**Date:** {YYYY-MM-DD} | **Version:** {gstack version} | **Skill:** /{skill}
+{one sentence}
+**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
 ```
-
-Slug: lowercase, hyphens, max 60 chars (e.g. `browse-js-no-await`). Skip if file already exists. Max 3 reports per session. File inline and continue — don't stop the workflow. Tell user: "Filed gstack field report: {title}"
+Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
 
 ## Completion Status Protocol
 
@@ -298,22 +280,42 @@ Then write a `## GSTACK REVIEW REPORT` section to the end of the plan file:
 file you are allowed to edit in plan mode. The plan file review report is part of the
 plan's living status.
 
-## Step 0: Detect base branch
+## Step 0: Detect platform and base branch
 
-Determine which branch this PR targets. Use the result as "the base branch" in all subsequent steps.
+First, detect the git hosting platform from the remote URL:
 
-1. Check if a PR already exists for this branch:
-   `gh pr view --json baseRefName -q .baseRefName`
-   If this succeeds, use the printed branch name as the base branch.
+```bash
+git remote get-url origin 2>/dev/null
+```
 
-2. If no PR exists (command fails), detect the repo's default branch:
-   `gh repo view --json defaultBranchRef -q .defaultBranchRef.name`
+- If the URL contains "github.com" → platform is **GitHub**
+- If the URL contains "gitlab" → platform is **GitLab**
+- Otherwise, check CLI availability:
+  - `gh auth status 2>/dev/null` succeeds → platform is **GitHub** (covers GitHub Enterprise)
+  - `glab auth status 2>/dev/null` succeeds → platform is **GitLab** (covers self-hosted)
+  - Neither → **unknown** (use git-native commands only)
 
-3. If both commands fail, fall back to `main`.
+Determine which branch this PR/MR targets, or the repo's default branch if no
+PR/MR exists. Use the result as "the base branch" in all subsequent steps.
+
+**If GitHub:**
+1. `gh pr view --json baseRefName -q .baseRefName` — if succeeds, use it
+2. `gh repo view --json defaultBranchRef -q .defaultBranchRef.name` — if succeeds, use it
+
+**If GitLab:**
+1. `glab mr view -F json 2>/dev/null` and extract the `target_branch` field — if succeeds, use it
+2. `glab repo view -F json 2>/dev/null` and extract the `default_branch` field — if succeeds, use it
+
+**Git-native fallback (if unknown platform, or CLI commands fail):**
+1. `git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's|refs/remotes/origin/||'`
+2. If that fails: `git rev-parse --verify origin/main 2>/dev/null` → use `main`
+3. If that fails: `git rev-parse --verify origin/master 2>/dev/null` → use `master`
+
+If all fail, fall back to `main`.
 
 Print the detected base branch name. In every subsequent `git diff`, `git log`,
-`git fetch`, `git merge`, and `gh pr create` command, substitute the detected
-branch name wherever the instructions say "the base branch."
+`git fetch`, `git merge`, and PR/MR creation command, substitute the detected
+branch name wherever the instructions say "the base branch" or `<default>`.
 
 ---
 
@@ -766,7 +768,13 @@ After completing the review, read the review log and config to display the dashb
 ~/.claude/skills/gstack/bin/gstack-review-read
 ```
 
-Parse the output. Find the most recent entry for each skill (plan-ceo-review, plan-eng-review, review, plan-design-review, design-review-lite, adversarial-review, codex-review, codex-plan-review). Ignore entries with timestamps older than 7 days. For the Eng Review row, show whichever is more recent between `review` (diff-scoped pre-landing review) and `plan-eng-review` (plan-stage architecture review). Append "(DIFF)" or "(PLAN)" to the status to distinguish. For the Adversarial row, show whichever is more recent between `adversarial-review` (new auto-scaled) and `codex-review` (legacy). For Design Review, show whichever is more recent between `plan-design-review` (full visual audit) and `design-review-lite` (code-level check). Append "(FULL)" or "(LITE)" to the status to distinguish. Display:
+Parse the output. Find the most recent entry for each skill (plan-ceo-review, plan-eng-review, review, plan-design-review, design-review-lite, adversarial-review, codex-review, codex-plan-review). Ignore entries with timestamps older than 7 days. For the Eng Review row, show whichever is more recent between `review` (diff-scoped pre-landing review) and `plan-eng-review` (plan-stage architecture review). Append "(DIFF)" or "(PLAN)" to the status to distinguish. For the Adversarial row, show whichever is more recent between `adversarial-review` (new auto-scaled) and `codex-review` (legacy). For Design Review, show whichever is more recent between `plan-design-review` (full visual audit) and `design-review-lite` (code-level check). Append "(FULL)" or "(LITE)" to the status to distinguish. For the Outside Voice row, show the most recent `codex-plan-review` entry — this captures outside voices from both /plan-ceo-review and /plan-eng-review.
+
+**Source attribution:** If the most recent entry for a skill has a \`"via"\` field, append it to the status label in parentheses. Examples: `plan-eng-review` with `via:"autoplan"` shows as "CLEAR (PLAN via /autoplan)". `review` with `via:"ship"` shows as "CLEAR (DIFF via /ship)". Entries without a `via` field show as "CLEAR (PLAN)" or "CLEAR (DIFF)" as before.
+
+Note: `autoplan-voices` and `design-outside-voices` entries are audit-trail-only (forensic data for cross-model consensus analysis). They do not appear in the dashboard and are not checked by any consumer.
+
+Display:
 
 ```
 +====================================================================+
diff --git a/plan-eng-review/SKILL.md b/plan-eng-review/SKILL.md
index 7cda1d1a..5b57c16f 100644
--- a/plan-eng-review/SKILL.md
+++ b/plan-eng-review/SKILL.md
@@ -33,9 +33,11 @@ _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr
 find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
 _CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
+_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
 echo "BRANCH: $_BRANCH"
 echo "PROACTIVE: $_PROACTIVE"
+echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
 source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
 REPO_MODE=${REPO_MODE:-unknown}
 echo "REPO_MODE: $REPO_MODE"
@@ -53,8 +55,11 @@ echo '{"skill":"plan-eng-review","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do [ -f "$_PF" ] && ~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true; break; done
 ```
 
-If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills — only invoke
-them when the user explicitly asks. The user opted out of proactive suggestions.
+If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
+auto-invoke skills based on conversation context. Only run skills the user explicitly
+types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say:
+"I think /skillname might help here — want me to run it?" and wait for confirmation.
+The user opted out of proactive behavior.
 
 If output shows `UPGRADE_AVAILABLE <old> <new>`: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED <from> <to>`: tell user "Running gstack v{to} (just updated!)" and continue.
 
@@ -103,6 +108,27 @@ touch ~/.gstack/.telemetry-prompted
 
 This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 
+If `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: After telemetry is handled,
+ask the user about proactive behavior. Use AskUserQuestion:
+
+> gstack can proactively figure out when you might need a skill while you work —
+> like suggesting /qa when you say "does this work?" or /investigate when you hit
+> a bug. We recommend keeping this on — it speeds up every part of your workflow.
+
+Options:
+- A) Keep it on (recommended)
+- B) Turn it off — I'll type /commands myself
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set proactive true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set proactive false`
+
+Always run:
+```bash
+touch ~/.gstack/.proactive-prompted
+```
+
+This only happens once. If `PROACTIVE_PROMPTED` is `yes`, skip this entirely.
+
 ## AskUserQuestion Format
 
 **ALWAYS follow this structure for every AskUserQuestion call:**
@@ -110,7 +136,6 @@ This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
 3. **Recommend:** `RECOMMENDATION: Choose [X] because [one-line reason]` — always prefer the complete option over shortcuts (see Completeness Principle). Include `Completeness: X/10` for each option. Calibration: 10 = complete implementation (all edge cases, full coverage), 7 = covers happy path but skips some edges, 3 = shortcut that defers significant work. If both options are 8+, pick the higher; if one is ≤5, flag it.
 4. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
-5. **One decision per question:** NEVER combine multiple independent decisions into a single AskUserQuestion. Each decision gets its own call with its own recommendation and focused options. Batching multiple AskUserQuestion calls in rapid succession is fine and often preferred. Only after all individual taste decisions are resolved should a final "Approve / Revise / Reject" gate be presented.
 
 Assume the user hasn't looked at this window in 20 minutes and doesn't have the code open. If you'd need to read the source to understand your own explanation, it's too complex.
 
@@ -118,97 +143,54 @@ Per-skill instructions may add additional formatting rules on top of this baseli
 
 ## Completeness Principle — Boil the Lake
 
-AI-assisted coding makes the marginal cost of completeness near-zero. When you present options:
+AI makes completeness near-free. Always recommend the complete option over shortcuts — the delta is minutes with CC+gstack. A "lake" (100% coverage, all edge cases) is boilable; an "ocean" (full rewrite, multi-quarter migration) is not. Boil lakes, flag oceans.
 
-- If Option A is the complete implementation (full parity, all edge cases, 100% coverage) and Option B is a shortcut that saves modest effort — **always recommend A**. The delta between 80 lines and 150 lines is meaningless with CC+gstack. "Good enough" is the wrong instinct when "complete" costs minutes more.
-- **Lake vs. ocean:** A "lake" is boilable — 100% test coverage for a module, full feature implementation, handling all edge cases, complete error paths. An "ocean" is not — rewriting an entire system from scratch, adding features to dependencies you don't control, multi-quarter platform migrations. Recommend boiling lakes. Flag oceans as out of scope.
-- **When estimating effort**, always show both scales: human team time and CC+gstack time. The compression ratio varies by task type — use this reference:
+**Effort reference** — always show both scales:
 
 | Task type | Human team | CC+gstack | Compression |
 |-----------|-----------|-----------|-------------|
-| Boilerplate / scaffolding | 2 days | 15 min | ~100x |
-| Test writing | 1 day | 15 min | ~50x |
-| Feature implementation | 1 week | 30 min | ~30x |
-| Bug fix + regression test | 4 hours | 15 min | ~20x |
-| Architecture / design | 2 days | 4 hours | ~5x |
-| Research / exploration | 1 day | 3 hours | ~3x |
+| Boilerplate | 2 days | 15 min | ~100x |
+| Tests | 1 day | 15 min | ~50x |
+| Feature | 1 week | 30 min | ~30x |
+| Bug fix | 4 hours | 15 min | ~20x |
 
-- This principle applies to test coverage, error handling, documentation, edge cases, and feature completeness. Don't skip the last 10% to "save time" — with AI, that 10% costs seconds.
+Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-**Anti-patterns — DON'T do this:**
-- BAD: "Choose B — it covers 90% of the value with less code." (If A is only 70 lines more, choose A.)
-- BAD: "We can skip edge case handling to save time." (Edge case handling costs minutes with CC.)
-- BAD: "Let's defer test coverage to a follow-up PR." (Tests are the cheapest lake to boil.)
-- BAD: Quoting only human-team effort: "This would take 2 weeks." (Say: "2 weeks human / ~1 hour CC.")
+## Repo Ownership — See Something, Say Something
 
-## Repo Ownership Mode — See Something, Say Something
+`REPO_MODE` controls how to handle issues outside your branch:
+- **`solo`** — You own everything. Investigate and offer to fix proactively.
+- **`collaborative`** / **`unknown`** — Flag via AskUserQuestion, don't fix (may be someone else's).
 
-`REPO_MODE` from the preamble tells you who owns issues in this repo:
-
-- **`solo`** — One person does 80%+ of the work. They own everything. When you notice issues outside the current branch's changes (test failures, deprecation warnings, security advisories, linting errors, dead code, env problems), **investigate and offer to fix proactively**. The solo dev is the only person who will fix it. Default to action.
-- **`collaborative`** — Multiple active contributors. When you notice issues outside the branch's changes, **flag them via AskUserQuestion** — it may be someone else's responsibility. Default to asking, not fixing.
-- **`unknown`** — Treat as collaborative (safer default — ask before fixing).
-
-**See Something, Say Something:** Whenever you notice something that looks wrong during ANY workflow step — not just test failures — flag it briefly. One sentence: what you noticed and its impact. In solo mode, follow up with "Want me to fix it?" In collaborative mode, just flag it and move on.
-
-Never let a noticed issue silently pass. The whole point is proactive communication.
+Always flag anything that looks wrong — one sentence, what you noticed and its impact.
 
 ## Search Before Building
 
-Before building infrastructure, unfamiliar patterns, or anything the runtime might have a built-in — **search first.** Read `~/.claude/skills/gstack/ETHOS.md` for the full philosophy.
+Before building anything unfamiliar, **search first.** See `~/.claude/skills/gstack/ETHOS.md`.
+- **Layer 1** (tried and true) — don't reinvent. **Layer 2** (new and popular) — scrutinize. **Layer 3** (first principles) — prize above all.
 
-**Three layers of knowledge:**
-- **Layer 1** (tried and true — in distribution). Don't reinvent the wheel. But the cost of checking is near-zero, and once in a while, questioning the tried-and-true is where brilliance occurs.
-- **Layer 2** (new and popular — search for these). But scrutinize: humans are subject to mania. Search results are inputs to your thinking, not answers.
-- **Layer 3** (first principles — prize these above all). Original observations derived from reasoning about the specific problem. The most valuable of all.
-
-**Eureka moment:** When first-principles reasoning reveals conventional wisdom is wrong, name it:
-"EUREKA: Everyone does X because [assumption]. But [evidence] shows this is wrong. Y is better because [reasoning]."
-
-Log eureka moments:
+**Eureka:** When first-principles reasoning contradicts conventional wisdom, name it and log:
 ```bash
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
-Replace SKILL_NAME and ONE_LINE_SUMMARY. Runs inline — don't stop the workflow.
-
-**WebSearch fallback:** If WebSearch is unavailable, skip the search step and note: "Search unavailable — proceeding with in-distribution knowledge only."
 
 ## Contributor Mode
 
-If `_CONTRIB` is `true`: you are in **contributor mode**. You're a gstack user who also helps make it better.
+If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
 
-**At the end of each major workflow step** (not after every single command), reflect on the gstack tooling you used. Rate your experience 0 to 10. If it wasn't a 10, think about why. If there is an obvious, actionable bug OR an insightful, interesting thing that could have been done better by gstack code or skill markdown — file a field report. Maybe our contributor will help make us better!
-
-**Calibration — this is the bar:** For example, `$B js "await fetch(...)"` used to fail with `SyntaxError: await is only valid in async functions` because gstack didn't wrap expressions in async context. Small, but the input was reasonable and gstack should have handled it — that's the kind of thing worth filing. Things less consequential than this, ignore.
-
-**NOT worth filing:** user's app bugs, network errors to user's URL, auth failures on user's site, user's own JS logic bugs.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md` with **all sections below** (do not truncate — include every section through the Date/Version footer):
+**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
 
+**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
 ```
 # {Title}
-
-Hey gstack team — ran into this while using /{skill-name}:
-
-**What I was trying to do:** {what the user/agent was attempting}
-**What happened instead:** {what actually happened}
-**My Rating:** {0-10} — {one sentence on why it wasn't a 10}
-
-## Steps to reproduce
+**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
+## Repro
 1. {step}
-
-## Raw output
-```
-{paste the actual error or unexpected output here}
-```
-
 ## What would make this a 10
-{one sentence: what gstack should have done differently}
-
-**Date:** {YYYY-MM-DD} | **Version:** {gstack version} | **Skill:** /{skill}
+{one sentence}
+**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
 ```
-
-Slug: lowercase, hyphens, max 60 chars (e.g. `browse-js-no-await`). Skip if file already exists. Max 3 reports per session. File inline and continue — don't stop the workflow. Tell user: "Filed gstack field report: {title}"
+Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
 
 ## Completion Status Protocol
 
@@ -888,7 +870,13 @@ After completing the review, read the review log and config to display the dashb
 ~/.claude/skills/gstack/bin/gstack-review-read
 ```
 
-Parse the output. Find the most recent entry for each skill (plan-ceo-review, plan-eng-review, review, plan-design-review, design-review-lite, adversarial-review, codex-review, codex-plan-review). Ignore entries with timestamps older than 7 days. For the Eng Review row, show whichever is more recent between `review` (diff-scoped pre-landing review) and `plan-eng-review` (plan-stage architecture review). Append "(DIFF)" or "(PLAN)" to the status to distinguish. For the Adversarial row, show whichever is more recent between `adversarial-review` (new auto-scaled) and `codex-review` (legacy). For Design Review, show whichever is more recent between `plan-design-review` (full visual audit) and `design-review-lite` (code-level check). Append "(FULL)" or "(LITE)" to the status to distinguish. Display:
+Parse the output. Find the most recent entry for each skill (plan-ceo-review, plan-eng-review, review, plan-design-review, design-review-lite, adversarial-review, codex-review, codex-plan-review). Ignore entries with timestamps older than 7 days. For the Eng Review row, show whichever is more recent between `review` (diff-scoped pre-landing review) and `plan-eng-review` (plan-stage architecture review). Append "(DIFF)" or "(PLAN)" to the status to distinguish. For the Adversarial row, show whichever is more recent between `adversarial-review` (new auto-scaled) and `codex-review` (legacy). For Design Review, show whichever is more recent between `plan-design-review` (full visual audit) and `design-review-lite` (code-level check). Append "(FULL)" or "(LITE)" to the status to distinguish. For the Outside Voice row, show the most recent `codex-plan-review` entry — this captures outside voices from both /plan-ceo-review and /plan-eng-review.
+
+**Source attribution:** If the most recent entry for a skill has a \`"via"\` field, append it to the status label in parentheses. Examples: `plan-eng-review` with `via:"autoplan"` shows as "CLEAR (PLAN via /autoplan)". `review` with `via:"ship"` shows as "CLEAR (DIFF via /ship)". Entries without a `via` field show as "CLEAR (PLAN)" or "CLEAR (DIFF)" as before.
+
+Note: `autoplan-voices` and `design-outside-voices` entries are audit-trail-only (forensic data for cross-model consensus analysis). They do not appear in the dashboard and are not checked by any consumer.
+
+Display:
 
 ```
 +====================================================================+
diff --git a/qa-only/SKILL.md b/qa-only/SKILL.md
index af823f9a..1129d52a 100644
--- a/qa-only/SKILL.md
+++ b/qa-only/SKILL.md
@@ -29,9 +29,11 @@ _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr
 find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
 _CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
+_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
 echo "BRANCH: $_BRANCH"
 echo "PROACTIVE: $_PROACTIVE"
+echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
 source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
 REPO_MODE=${REPO_MODE:-unknown}
 echo "REPO_MODE: $REPO_MODE"
@@ -49,8 +51,11 @@ echo '{"skill":"qa-only","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(base
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do [ -f "$_PF" ] && ~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true; break; done
 ```
 
-If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills — only invoke
-them when the user explicitly asks. The user opted out of proactive suggestions.
+If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
+auto-invoke skills based on conversation context. Only run skills the user explicitly
+types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say:
+"I think /skillname might help here — want me to run it?" and wait for confirmation.
+The user opted out of proactive behavior.
 
 If output shows `UPGRADE_AVAILABLE <old> <new>`: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED <from> <to>`: tell user "Running gstack v{to} (just updated!)" and continue.
 
@@ -99,6 +104,27 @@ touch ~/.gstack/.telemetry-prompted
 
 This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 
+If `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: After telemetry is handled,
+ask the user about proactive behavior. Use AskUserQuestion:
+
+> gstack can proactively figure out when you might need a skill while you work —
+> like suggesting /qa when you say "does this work?" or /investigate when you hit
+> a bug. We recommend keeping this on — it speeds up every part of your workflow.
+
+Options:
+- A) Keep it on (recommended)
+- B) Turn it off — I'll type /commands myself
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set proactive true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set proactive false`
+
+Always run:
+```bash
+touch ~/.gstack/.proactive-prompted
+```
+
+This only happens once. If `PROACTIVE_PROMPTED` is `yes`, skip this entirely.
+
 ## AskUserQuestion Format
 
 **ALWAYS follow this structure for every AskUserQuestion call:**
@@ -106,7 +132,6 @@ This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
 3. **Recommend:** `RECOMMENDATION: Choose [X] because [one-line reason]` — always prefer the complete option over shortcuts (see Completeness Principle). Include `Completeness: X/10` for each option. Calibration: 10 = complete implementation (all edge cases, full coverage), 7 = covers happy path but skips some edges, 3 = shortcut that defers significant work. If both options are 8+, pick the higher; if one is ≤5, flag it.
 4. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
-5. **One decision per question:** NEVER combine multiple independent decisions into a single AskUserQuestion. Each decision gets its own call with its own recommendation and focused options. Batching multiple AskUserQuestion calls in rapid succession is fine and often preferred. Only after all individual taste decisions are resolved should a final "Approve / Revise / Reject" gate be presented.
 
 Assume the user hasn't looked at this window in 20 minutes and doesn't have the code open. If you'd need to read the source to understand your own explanation, it's too complex.
 
@@ -114,97 +139,54 @@ Per-skill instructions may add additional formatting rules on top of this baseli
 
 ## Completeness Principle — Boil the Lake
 
-AI-assisted coding makes the marginal cost of completeness near-zero. When you present options:
+AI makes completeness near-free. Always recommend the complete option over shortcuts — the delta is minutes with CC+gstack. A "lake" (100% coverage, all edge cases) is boilable; an "ocean" (full rewrite, multi-quarter migration) is not. Boil lakes, flag oceans.
 
-- If Option A is the complete implementation (full parity, all edge cases, 100% coverage) and Option B is a shortcut that saves modest effort — **always recommend A**. The delta between 80 lines and 150 lines is meaningless with CC+gstack. "Good enough" is the wrong instinct when "complete" costs minutes more.
-- **Lake vs. ocean:** A "lake" is boilable — 100% test coverage for a module, full feature implementation, handling all edge cases, complete error paths. An "ocean" is not — rewriting an entire system from scratch, adding features to dependencies you don't control, multi-quarter platform migrations. Recommend boiling lakes. Flag oceans as out of scope.
-- **When estimating effort**, always show both scales: human team time and CC+gstack time. The compression ratio varies by task type — use this reference:
+**Effort reference** — always show both scales:
 
 | Task type | Human team | CC+gstack | Compression |
 |-----------|-----------|-----------|-------------|
-| Boilerplate / scaffolding | 2 days | 15 min | ~100x |
-| Test writing | 1 day | 15 min | ~50x |
-| Feature implementation | 1 week | 30 min | ~30x |
-| Bug fix + regression test | 4 hours | 15 min | ~20x |
-| Architecture / design | 2 days | 4 hours | ~5x |
-| Research / exploration | 1 day | 3 hours | ~3x |
+| Boilerplate | 2 days | 15 min | ~100x |
+| Tests | 1 day | 15 min | ~50x |
+| Feature | 1 week | 30 min | ~30x |
+| Bug fix | 4 hours | 15 min | ~20x |
 
-- This principle applies to test coverage, error handling, documentation, edge cases, and feature completeness. Don't skip the last 10% to "save time" — with AI, that 10% costs seconds.
+Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-**Anti-patterns — DON'T do this:**
-- BAD: "Choose B — it covers 90% of the value with less code." (If A is only 70 lines more, choose A.)
-- BAD: "We can skip edge case handling to save time." (Edge case handling costs minutes with CC.)
-- BAD: "Let's defer test coverage to a follow-up PR." (Tests are the cheapest lake to boil.)
-- BAD: Quoting only human-team effort: "This would take 2 weeks." (Say: "2 weeks human / ~1 hour CC.")
+## Repo Ownership — See Something, Say Something
 
-## Repo Ownership Mode — See Something, Say Something
+`REPO_MODE` controls how to handle issues outside your branch:
+- **`solo`** — You own everything. Investigate and offer to fix proactively.
+- **`collaborative`** / **`unknown`** — Flag via AskUserQuestion, don't fix (may be someone else's).
 
-`REPO_MODE` from the preamble tells you who owns issues in this repo:
-
-- **`solo`** — One person does 80%+ of the work. They own everything. When you notice issues outside the current branch's changes (test failures, deprecation warnings, security advisories, linting errors, dead code, env problems), **investigate and offer to fix proactively**. The solo dev is the only person who will fix it. Default to action.
-- **`collaborative`** — Multiple active contributors. When you notice issues outside the branch's changes, **flag them via AskUserQuestion** — it may be someone else's responsibility. Default to asking, not fixing.
-- **`unknown`** — Treat as collaborative (safer default — ask before fixing).
-
-**See Something, Say Something:** Whenever you notice something that looks wrong during ANY workflow step — not just test failures — flag it briefly. One sentence: what you noticed and its impact. In solo mode, follow up with "Want me to fix it?" In collaborative mode, just flag it and move on.
-
-Never let a noticed issue silently pass. The whole point is proactive communication.
+Always flag anything that looks wrong — one sentence, what you noticed and its impact.
 
 ## Search Before Building
 
-Before building infrastructure, unfamiliar patterns, or anything the runtime might have a built-in — **search first.** Read `~/.claude/skills/gstack/ETHOS.md` for the full philosophy.
+Before building anything unfamiliar, **search first.** See `~/.claude/skills/gstack/ETHOS.md`.
+- **Layer 1** (tried and true) — don't reinvent. **Layer 2** (new and popular) — scrutinize. **Layer 3** (first principles) — prize above all.
 
-**Three layers of knowledge:**
-- **Layer 1** (tried and true — in distribution). Don't reinvent the wheel. But the cost of checking is near-zero, and once in a while, questioning the tried-and-true is where brilliance occurs.
-- **Layer 2** (new and popular — search for these). But scrutinize: humans are subject to mania. Search results are inputs to your thinking, not answers.
-- **Layer 3** (first principles — prize these above all). Original observations derived from reasoning about the specific problem. The most valuable of all.
-
-**Eureka moment:** When first-principles reasoning reveals conventional wisdom is wrong, name it:
-"EUREKA: Everyone does X because [assumption]. But [evidence] shows this is wrong. Y is better because [reasoning]."
-
-Log eureka moments:
+**Eureka:** When first-principles reasoning contradicts conventional wisdom, name it and log:
 ```bash
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
-Replace SKILL_NAME and ONE_LINE_SUMMARY. Runs inline — don't stop the workflow.
-
-**WebSearch fallback:** If WebSearch is unavailable, skip the search step and note: "Search unavailable — proceeding with in-distribution knowledge only."
 
 ## Contributor Mode
 
-If `_CONTRIB` is `true`: you are in **contributor mode**. You're a gstack user who also helps make it better.
+If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
 
-**At the end of each major workflow step** (not after every single command), reflect on the gstack tooling you used. Rate your experience 0 to 10. If it wasn't a 10, think about why. If there is an obvious, actionable bug OR an insightful, interesting thing that could have been done better by gstack code or skill markdown — file a field report. Maybe our contributor will help make us better!
-
-**Calibration — this is the bar:** For example, `$B js "await fetch(...)"` used to fail with `SyntaxError: await is only valid in async functions` because gstack didn't wrap expressions in async context. Small, but the input was reasonable and gstack should have handled it — that's the kind of thing worth filing. Things less consequential than this, ignore.
-
-**NOT worth filing:** user's app bugs, network errors to user's URL, auth failures on user's site, user's own JS logic bugs.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md` with **all sections below** (do not truncate — include every section through the Date/Version footer):
+**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
 
+**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
 ```
 # {Title}
-
-Hey gstack team — ran into this while using /{skill-name}:
-
-**What I was trying to do:** {what the user/agent was attempting}
-**What happened instead:** {what actually happened}
-**My Rating:** {0-10} — {one sentence on why it wasn't a 10}
-
-## Steps to reproduce
+**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
+## Repro
 1. {step}
-
-## Raw output
-```
-{paste the actual error or unexpected output here}
-```
-
 ## What would make this a 10
-{one sentence: what gstack should have done differently}
-
-**Date:** {YYYY-MM-DD} | **Version:** {gstack version} | **Skill:** /{skill}
+{one sentence}
+**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
 ```
-
-Slug: lowercase, hyphens, max 60 chars (e.g. `browse-js-no-await`). Skip if file already exists. Max 3 reports per session. File inline and continue — don't stop the workflow. Tell user: "Filed gstack field report: {title}"
+Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
 
 ## Completion Status Protocol
 
diff --git a/qa/SKILL.md b/qa/SKILL.md
index 08b073d0..a9241238 100644
--- a/qa/SKILL.md
+++ b/qa/SKILL.md
@@ -35,9 +35,11 @@ _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr
 find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
 _CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
+_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
 echo "BRANCH: $_BRANCH"
 echo "PROACTIVE: $_PROACTIVE"
+echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
 source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
 REPO_MODE=${REPO_MODE:-unknown}
 echo "REPO_MODE: $REPO_MODE"
@@ -55,8 +57,11 @@ echo '{"skill":"qa","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do [ -f "$_PF" ] && ~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true; break; done
 ```
 
-If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills — only invoke
-them when the user explicitly asks. The user opted out of proactive suggestions.
+If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
+auto-invoke skills based on conversation context. Only run skills the user explicitly
+types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say:
+"I think /skillname might help here — want me to run it?" and wait for confirmation.
+The user opted out of proactive behavior.
 
 If output shows `UPGRADE_AVAILABLE <old> <new>`: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED <from> <to>`: tell user "Running gstack v{to} (just updated!)" and continue.
 
@@ -105,6 +110,27 @@ touch ~/.gstack/.telemetry-prompted
 
 This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 
+If `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: After telemetry is handled,
+ask the user about proactive behavior. Use AskUserQuestion:
+
+> gstack can proactively figure out when you might need a skill while you work —
+> like suggesting /qa when you say "does this work?" or /investigate when you hit
+> a bug. We recommend keeping this on — it speeds up every part of your workflow.
+
+Options:
+- A) Keep it on (recommended)
+- B) Turn it off — I'll type /commands myself
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set proactive true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set proactive false`
+
+Always run:
+```bash
+touch ~/.gstack/.proactive-prompted
+```
+
+This only happens once. If `PROACTIVE_PROMPTED` is `yes`, skip this entirely.
+
 ## AskUserQuestion Format
 
 **ALWAYS follow this structure for every AskUserQuestion call:**
@@ -112,7 +138,6 @@ This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
 3. **Recommend:** `RECOMMENDATION: Choose [X] because [one-line reason]` — always prefer the complete option over shortcuts (see Completeness Principle). Include `Completeness: X/10` for each option. Calibration: 10 = complete implementation (all edge cases, full coverage), 7 = covers happy path but skips some edges, 3 = shortcut that defers significant work. If both options are 8+, pick the higher; if one is ≤5, flag it.
 4. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
-5. **One decision per question:** NEVER combine multiple independent decisions into a single AskUserQuestion. Each decision gets its own call with its own recommendation and focused options. Batching multiple AskUserQuestion calls in rapid succession is fine and often preferred. Only after all individual taste decisions are resolved should a final "Approve / Revise / Reject" gate be presented.
 
 Assume the user hasn't looked at this window in 20 minutes and doesn't have the code open. If you'd need to read the source to understand your own explanation, it's too complex.
 
@@ -120,97 +145,54 @@ Per-skill instructions may add additional formatting rules on top of this baseli
 
 ## Completeness Principle — Boil the Lake
 
-AI-assisted coding makes the marginal cost of completeness near-zero. When you present options:
+AI makes completeness near-free. Always recommend the complete option over shortcuts — the delta is minutes with CC+gstack. A "lake" (100% coverage, all edge cases) is boilable; an "ocean" (full rewrite, multi-quarter migration) is not. Boil lakes, flag oceans.
 
-- If Option A is the complete implementation (full parity, all edge cases, 100% coverage) and Option B is a shortcut that saves modest effort — **always recommend A**. The delta between 80 lines and 150 lines is meaningless with CC+gstack. "Good enough" is the wrong instinct when "complete" costs minutes more.
-- **Lake vs. ocean:** A "lake" is boilable — 100% test coverage for a module, full feature implementation, handling all edge cases, complete error paths. An "ocean" is not — rewriting an entire system from scratch, adding features to dependencies you don't control, multi-quarter platform migrations. Recommend boiling lakes. Flag oceans as out of scope.
-- **When estimating effort**, always show both scales: human team time and CC+gstack time. The compression ratio varies by task type — use this reference:
+**Effort reference** — always show both scales:
 
 | Task type | Human team | CC+gstack | Compression |
 |-----------|-----------|-----------|-------------|
-| Boilerplate / scaffolding | 2 days | 15 min | ~100x |
-| Test writing | 1 day | 15 min | ~50x |
-| Feature implementation | 1 week | 30 min | ~30x |
-| Bug fix + regression test | 4 hours | 15 min | ~20x |
-| Architecture / design | 2 days | 4 hours | ~5x |
-| Research / exploration | 1 day | 3 hours | ~3x |
+| Boilerplate | 2 days | 15 min | ~100x |
+| Tests | 1 day | 15 min | ~50x |
+| Feature | 1 week | 30 min | ~30x |
+| Bug fix | 4 hours | 15 min | ~20x |
 
-- This principle applies to test coverage, error handling, documentation, edge cases, and feature completeness. Don't skip the last 10% to "save time" — with AI, that 10% costs seconds.
+Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-**Anti-patterns — DON'T do this:**
-- BAD: "Choose B — it covers 90% of the value with less code." (If A is only 70 lines more, choose A.)
-- BAD: "We can skip edge case handling to save time." (Edge case handling costs minutes with CC.)
-- BAD: "Let's defer test coverage to a follow-up PR." (Tests are the cheapest lake to boil.)
-- BAD: Quoting only human-team effort: "This would take 2 weeks." (Say: "2 weeks human / ~1 hour CC.")
+## Repo Ownership — See Something, Say Something
 
-## Repo Ownership Mode — See Something, Say Something
+`REPO_MODE` controls how to handle issues outside your branch:
+- **`solo`** — You own everything. Investigate and offer to fix proactively.
+- **`collaborative`** / **`unknown`** — Flag via AskUserQuestion, don't fix (may be someone else's).
 
-`REPO_MODE` from the preamble tells you who owns issues in this repo:
-
-- **`solo`** — One person does 80%+ of the work. They own everything. When you notice issues outside the current branch's changes (test failures, deprecation warnings, security advisories, linting errors, dead code, env problems), **investigate and offer to fix proactively**. The solo dev is the only person who will fix it. Default to action.
-- **`collaborative`** — Multiple active contributors. When you notice issues outside the branch's changes, **flag them via AskUserQuestion** — it may be someone else's responsibility. Default to asking, not fixing.
-- **`unknown`** — Treat as collaborative (safer default — ask before fixing).
-
-**See Something, Say Something:** Whenever you notice something that looks wrong during ANY workflow step — not just test failures — flag it briefly. One sentence: what you noticed and its impact. In solo mode, follow up with "Want me to fix it?" In collaborative mode, just flag it and move on.
-
-Never let a noticed issue silently pass. The whole point is proactive communication.
+Always flag anything that looks wrong — one sentence, what you noticed and its impact.
 
 ## Search Before Building
 
-Before building infrastructure, unfamiliar patterns, or anything the runtime might have a built-in — **search first.** Read `~/.claude/skills/gstack/ETHOS.md` for the full philosophy.
+Before building anything unfamiliar, **search first.** See `~/.claude/skills/gstack/ETHOS.md`.
+- **Layer 1** (tried and true) — don't reinvent. **Layer 2** (new and popular) — scrutinize. **Layer 3** (first principles) — prize above all.
 
-**Three layers of knowledge:**
-- **Layer 1** (tried and true — in distribution). Don't reinvent the wheel. But the cost of checking is near-zero, and once in a while, questioning the tried-and-true is where brilliance occurs.
-- **Layer 2** (new and popular — search for these). But scrutinize: humans are subject to mania. Search results are inputs to your thinking, not answers.
-- **Layer 3** (first principles — prize these above all). Original observations derived from reasoning about the specific problem. The most valuable of all.
-
-**Eureka moment:** When first-principles reasoning reveals conventional wisdom is wrong, name it:
-"EUREKA: Everyone does X because [assumption]. But [evidence] shows this is wrong. Y is better because [reasoning]."
-
-Log eureka moments:
+**Eureka:** When first-principles reasoning contradicts conventional wisdom, name it and log:
 ```bash
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
-Replace SKILL_NAME and ONE_LINE_SUMMARY. Runs inline — don't stop the workflow.
-
-**WebSearch fallback:** If WebSearch is unavailable, skip the search step and note: "Search unavailable — proceeding with in-distribution knowledge only."
 
 ## Contributor Mode
 
-If `_CONTRIB` is `true`: you are in **contributor mode**. You're a gstack user who also helps make it better.
+If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
 
-**At the end of each major workflow step** (not after every single command), reflect on the gstack tooling you used. Rate your experience 0 to 10. If it wasn't a 10, think about why. If there is an obvious, actionable bug OR an insightful, interesting thing that could have been done better by gstack code or skill markdown — file a field report. Maybe our contributor will help make us better!
-
-**Calibration — this is the bar:** For example, `$B js "await fetch(...)"` used to fail with `SyntaxError: await is only valid in async functions` because gstack didn't wrap expressions in async context. Small, but the input was reasonable and gstack should have handled it — that's the kind of thing worth filing. Things less consequential than this, ignore.
-
-**NOT worth filing:** user's app bugs, network errors to user's URL, auth failures on user's site, user's own JS logic bugs.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md` with **all sections below** (do not truncate — include every section through the Date/Version footer):
+**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
 
+**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
 ```
 # {Title}
-
-Hey gstack team — ran into this while using /{skill-name}:
-
-**What I was trying to do:** {what the user/agent was attempting}
-**What happened instead:** {what actually happened}
-**My Rating:** {0-10} — {one sentence on why it wasn't a 10}
-
-## Steps to reproduce
+**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
+## Repro
 1. {step}
-
-## Raw output
-```
-{paste the actual error or unexpected output here}
-```
-
 ## What would make this a 10
-{one sentence: what gstack should have done differently}
-
-**Date:** {YYYY-MM-DD} | **Version:** {gstack version} | **Skill:** /{skill}
+{one sentence}
+**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
 ```
-
-Slug: lowercase, hyphens, max 60 chars (e.g. `browse-js-no-await`). Skip if file already exists. Max 3 reports per session. File inline and continue — don't stop the workflow. Tell user: "Filed gstack field report: {title}"
+Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
 
 ## Completion Status Protocol
 
@@ -301,22 +283,42 @@ Then write a `## GSTACK REVIEW REPORT` section to the end of the plan file:
 file you are allowed to edit in plan mode. The plan file review report is part of the
 plan's living status.
 
-## Step 0: Detect base branch
+## Step 0: Detect platform and base branch
 
-Determine which branch this PR targets. Use the result as "the base branch" in all subsequent steps.
+First, detect the git hosting platform from the remote URL:
 
-1. Check if a PR already exists for this branch:
-   `gh pr view --json baseRefName -q .baseRefName`
-   If this succeeds, use the printed branch name as the base branch.
+```bash
+git remote get-url origin 2>/dev/null
+```
 
-2. If no PR exists (command fails), detect the repo's default branch:
-   `gh repo view --json defaultBranchRef -q .defaultBranchRef.name`
+- If the URL contains "github.com" → platform is **GitHub**
+- If the URL contains "gitlab" → platform is **GitLab**
+- Otherwise, check CLI availability:
+  - `gh auth status 2>/dev/null` succeeds → platform is **GitHub** (covers GitHub Enterprise)
+  - `glab auth status 2>/dev/null` succeeds → platform is **GitLab** (covers self-hosted)
+  - Neither → **unknown** (use git-native commands only)
 
-3. If both commands fail, fall back to `main`.
+Determine which branch this PR/MR targets, or the repo's default branch if no
+PR/MR exists. Use the result as "the base branch" in all subsequent steps.
+
+**If GitHub:**
+1. `gh pr view --json baseRefName -q .baseRefName` — if succeeds, use it
+2. `gh repo view --json defaultBranchRef -q .defaultBranchRef.name` — if succeeds, use it
+
+**If GitLab:**
+1. `glab mr view -F json 2>/dev/null` and extract the `target_branch` field — if succeeds, use it
+2. `glab repo view -F json 2>/dev/null` and extract the `default_branch` field — if succeeds, use it
+
+**Git-native fallback (if unknown platform, or CLI commands fail):**
+1. `git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's|refs/remotes/origin/||'`
+2. If that fails: `git rev-parse --verify origin/main 2>/dev/null` → use `main`
+3. If that fails: `git rev-parse --verify origin/master 2>/dev/null` → use `master`
+
+If all fail, fall back to `main`.
 
 Print the detected base branch name. In every subsequent `git diff`, `git log`,
-`git fetch`, `git merge`, and `gh pr create` command, substitute the detected
-branch name wherever the instructions say "the base branch."
+`git fetch`, `git merge`, and PR/MR creation command, substitute the detected
+branch name wherever the instructions say "the base branch" or `<default>`.
 
 ---
 
diff --git a/retro/SKILL.md b/retro/SKILL.md
index 02dd03e3..8741fb30 100644
--- a/retro/SKILL.md
+++ b/retro/SKILL.md
@@ -29,9 +29,11 @@ _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr
 find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
 _CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
+_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
 echo "BRANCH: $_BRANCH"
 echo "PROACTIVE: $_PROACTIVE"
+echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
 source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
 REPO_MODE=${REPO_MODE:-unknown}
 echo "REPO_MODE: $REPO_MODE"
@@ -49,8 +51,11 @@ echo '{"skill":"retro","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basena
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do [ -f "$_PF" ] && ~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true; break; done
 ```
 
-If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills — only invoke
-them when the user explicitly asks. The user opted out of proactive suggestions.
+If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
+auto-invoke skills based on conversation context. Only run skills the user explicitly
+types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say:
+"I think /skillname might help here — want me to run it?" and wait for confirmation.
+The user opted out of proactive behavior.
 
 If output shows `UPGRADE_AVAILABLE <old> <new>`: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED <from> <to>`: tell user "Running gstack v{to} (just updated!)" and continue.
 
@@ -99,6 +104,27 @@ touch ~/.gstack/.telemetry-prompted
 
 This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 
+If `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: After telemetry is handled,
+ask the user about proactive behavior. Use AskUserQuestion:
+
+> gstack can proactively figure out when you might need a skill while you work —
+> like suggesting /qa when you say "does this work?" or /investigate when you hit
+> a bug. We recommend keeping this on — it speeds up every part of your workflow.
+
+Options:
+- A) Keep it on (recommended)
+- B) Turn it off — I'll type /commands myself
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set proactive true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set proactive false`
+
+Always run:
+```bash
+touch ~/.gstack/.proactive-prompted
+```
+
+This only happens once. If `PROACTIVE_PROMPTED` is `yes`, skip this entirely.
+
 ## AskUserQuestion Format
 
 **ALWAYS follow this structure for every AskUserQuestion call:**
@@ -106,7 +132,6 @@ This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
 3. **Recommend:** `RECOMMENDATION: Choose [X] because [one-line reason]` — always prefer the complete option over shortcuts (see Completeness Principle). Include `Completeness: X/10` for each option. Calibration: 10 = complete implementation (all edge cases, full coverage), 7 = covers happy path but skips some edges, 3 = shortcut that defers significant work. If both options are 8+, pick the higher; if one is ≤5, flag it.
 4. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
-5. **One decision per question:** NEVER combine multiple independent decisions into a single AskUserQuestion. Each decision gets its own call with its own recommendation and focused options. Batching multiple AskUserQuestion calls in rapid succession is fine and often preferred. Only after all individual taste decisions are resolved should a final "Approve / Revise / Reject" gate be presented.
 
 Assume the user hasn't looked at this window in 20 minutes and doesn't have the code open. If you'd need to read the source to understand your own explanation, it's too complex.
 
@@ -114,65 +139,36 @@ Per-skill instructions may add additional formatting rules on top of this baseli
 
 ## Completeness Principle — Boil the Lake
 
-AI-assisted coding makes the marginal cost of completeness near-zero. When you present options:
+AI makes completeness near-free. Always recommend the complete option over shortcuts — the delta is minutes with CC+gstack. A "lake" (100% coverage, all edge cases) is boilable; an "ocean" (full rewrite, multi-quarter migration) is not. Boil lakes, flag oceans.
 
-- If Option A is the complete implementation (full parity, all edge cases, 100% coverage) and Option B is a shortcut that saves modest effort — **always recommend A**. The delta between 80 lines and 150 lines is meaningless with CC+gstack. "Good enough" is the wrong instinct when "complete" costs minutes more.
-- **Lake vs. ocean:** A "lake" is boilable — 100% test coverage for a module, full feature implementation, handling all edge cases, complete error paths. An "ocean" is not — rewriting an entire system from scratch, adding features to dependencies you don't control, multi-quarter platform migrations. Recommend boiling lakes. Flag oceans as out of scope.
-- **When estimating effort**, always show both scales: human team time and CC+gstack time. The compression ratio varies by task type — use this reference:
+**Effort reference** — always show both scales:
 
 | Task type | Human team | CC+gstack | Compression |
 |-----------|-----------|-----------|-------------|
-| Boilerplate / scaffolding | 2 days | 15 min | ~100x |
-| Test writing | 1 day | 15 min | ~50x |
-| Feature implementation | 1 week | 30 min | ~30x |
-| Bug fix + regression test | 4 hours | 15 min | ~20x |
-| Architecture / design | 2 days | 4 hours | ~5x |
-| Research / exploration | 1 day | 3 hours | ~3x |
+| Boilerplate | 2 days | 15 min | ~100x |
+| Tests | 1 day | 15 min | ~50x |
+| Feature | 1 week | 30 min | ~30x |
+| Bug fix | 4 hours | 15 min | ~20x |
 
-- This principle applies to test coverage, error handling, documentation, edge cases, and feature completeness. Don't skip the last 10% to "save time" — with AI, that 10% costs seconds.
-
-**Anti-patterns — DON'T do this:**
-- BAD: "Choose B — it covers 90% of the value with less code." (If A is only 70 lines more, choose A.)
-- BAD: "We can skip edge case handling to save time." (Edge case handling costs minutes with CC.)
-- BAD: "Let's defer test coverage to a follow-up PR." (Tests are the cheapest lake to boil.)
-- BAD: Quoting only human-team effort: "This would take 2 weeks." (Say: "2 weeks human / ~1 hour CC.")
+Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
 ## Contributor Mode
 
-If `_CONTRIB` is `true`: you are in **contributor mode**. You're a gstack user who also helps make it better.
+If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
 
-**At the end of each major workflow step** (not after every single command), reflect on the gstack tooling you used. Rate your experience 0 to 10. If it wasn't a 10, think about why. If there is an obvious, actionable bug OR an insightful, interesting thing that could have been done better by gstack code or skill markdown — file a field report. Maybe our contributor will help make us better!
-
-**Calibration — this is the bar:** For example, `$B js "await fetch(...)"` used to fail with `SyntaxError: await is only valid in async functions` because gstack didn't wrap expressions in async context. Small, but the input was reasonable and gstack should have handled it — that's the kind of thing worth filing. Things less consequential than this, ignore.
-
-**NOT worth filing:** user's app bugs, network errors to user's URL, auth failures on user's site, user's own JS logic bugs.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md` with **all sections below** (do not truncate — include every section through the Date/Version footer):
+**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
 
+**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
 ```
 # {Title}
-
-Hey gstack team — ran into this while using /{skill-name}:
-
-**What I was trying to do:** {what the user/agent was attempting}
-**What happened instead:** {what actually happened}
-**My Rating:** {0-10} — {one sentence on why it wasn't a 10}
-
-## Steps to reproduce
+**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
+## Repro
 1. {step}
-
-## Raw output
-```
-{paste the actual error or unexpected output here}
-```
-
 ## What would make this a 10
-{one sentence: what gstack should have done differently}
-
-**Date:** {YYYY-MM-DD} | **Version:** {gstack version} | **Skill:** /{skill}
+{one sentence}
+**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
 ```
-
-Slug: lowercase, hyphens, max 60 chars (e.g. `browse-js-no-await`). Skip if file already exists. Max 3 reports per session. File inline and continue — don't stop the workflow. Tell user: "Filed gstack field report: {title}"
+Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
 
 ## Completion Status Protocol
 
@@ -263,13 +259,42 @@ Then write a `## GSTACK REVIEW REPORT` section to the end of the plan file:
 file you are allowed to edit in plan mode. The plan file review report is part of the
 plan's living status.
 
-## Detect default branch
+## Step 0: Detect platform and base branch
 
-Before gathering data, detect the repo's default branch name:
-`gh repo view --json defaultBranchRef -q .defaultBranchRef.name`
+First, detect the git hosting platform from the remote URL:
 
-If this fails, fall back to `main`. Use the detected name wherever the instructions
-say `origin/<default>` below.
+```bash
+git remote get-url origin 2>/dev/null
+```
+
+- If the URL contains "github.com" → platform is **GitHub**
+- If the URL contains "gitlab" → platform is **GitLab**
+- Otherwise, check CLI availability:
+  - `gh auth status 2>/dev/null` succeeds → platform is **GitHub** (covers GitHub Enterprise)
+  - `glab auth status 2>/dev/null` succeeds → platform is **GitLab** (covers self-hosted)
+  - Neither → **unknown** (use git-native commands only)
+
+Determine which branch this PR/MR targets, or the repo's default branch if no
+PR/MR exists. Use the result as "the base branch" in all subsequent steps.
+
+**If GitHub:**
+1. `gh pr view --json baseRefName -q .baseRefName` — if succeeds, use it
+2. `gh repo view --json defaultBranchRef -q .defaultBranchRef.name` — if succeeds, use it
+
+**If GitLab:**
+1. `glab mr view -F json 2>/dev/null` and extract the `target_branch` field — if succeeds, use it
+2. `glab repo view -F json 2>/dev/null` and extract the `default_branch` field — if succeeds, use it
+
+**Git-native fallback (if unknown platform, or CLI commands fail):**
+1. `git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's|refs/remotes/origin/||'`
+2. If that fails: `git rev-parse --verify origin/main 2>/dev/null` → use `main`
+3. If that fails: `git rev-parse --verify origin/master 2>/dev/null` → use `master`
+
+If all fail, fall back to `main`.
+
+Print the detected base branch name. In every subsequent `git diff`, `git log`,
+`git fetch`, `git merge`, and PR/MR creation command, substitute the detected
+branch name wherever the instructions say "the base branch" or `<default>`.
 
 ---
 
@@ -340,8 +365,8 @@ git log origin/<default> --since="<window>" --format="%at|%aN|%ai|%s" | sort -n
 # 4. Files most frequently changed (hotspot analysis)
 git log origin/<default> --since="<window>" --format="" --name-only | grep -v '^$' | sort | uniq -c | sort -rn
 
-# 5. PR numbers from commit messages (extract #NNN patterns)
-git log origin/<default> --since="<window>" --format="%s" | grep -oE '#[0-9]+' | sed 's/^#//' | sort -n | uniq | sed 's/^/#/'
+# 5. PR/MR numbers from commit messages (GitHub #NNN, GitLab !NNN)
+git log origin/<default> --since="<window>" --format="%s" | grep -oE '[#!][0-9]+' | sort -t'#' -k1 | uniq
 
 # 6. Per-author file hotspots (who touches what)
 git log origin/<default> --since="<window>" --format="AUTHOR:%aN" --name-only
@@ -834,8 +859,8 @@ git -C <path> log origin/$DEFAULT --since="<start_date>T00:00:00" --format="%at|
 # Per-author commit counts
 git -C <path> shortlog origin/$DEFAULT --since="<start_date>T00:00:00" -sn --no-merges
 
-# PR numbers from commit messages
-git -C <path> log origin/$DEFAULT --since="<start_date>T00:00:00" --format="%s" | grep -oE '#[0-9]+' | sort -n | uniq
+# PR/MR numbers from commit messages (GitHub #NNN, GitLab !NNN)
+git -C <path> log origin/$DEFAULT --since="<start_date>T00:00:00" --format="%s" | grep -oE '[#!][0-9]+' | sort -t'#' -k1 | uniq
 ```
 
 For repos that fail (deleted paths, network errors): skip and note "N repos could not be reached."
@@ -913,7 +938,7 @@ align cleanly. Never truncate project names.
 ║  • [1-line description of second theme]
 ║  • [1-line description of third theme]
 ║
-║  Powered by gstack · github.com/garrytan/gstack
+║  Powered by gstack
 ╚═══════════════════════════════════════════════════════════════
 ```
 
@@ -1042,7 +1067,7 @@ Use the Write tool to save JSON to `~/.gstack/retros/global-${today}-${next}.jso
   "projects": [
     {
       "name": "gstack",
-      "remote": "https://github.com/garrytan/gstack",
+      "remote": "<detected from git remote get-url origin, normalized to HTTPS>",
       "commits": 47,
       "insertions": 3200,
       "deletions": 800,
diff --git a/retro/SKILL.md.tmpl b/retro/SKILL.md.tmpl
index dae967ef..cc4f53fa 100644
--- a/retro/SKILL.md.tmpl
+++ b/retro/SKILL.md.tmpl
@@ -18,15 +18,7 @@ allowed-tools:
 
 {{PREAMBLE}}
 
-## Detect default branch
-
-Before gathering data, detect the repo's default branch name:
-`gh repo view --json defaultBranchRef -q .defaultBranchRef.name`
-
-If this fails, fall back to `main`. Use the detected name wherever the instructions
-say `origin/<default>` below.
-
----
+{{BASE_BRANCH_DETECT}}
 
 # /retro — Weekly Engineering Retrospective
 
@@ -95,8 +87,8 @@ git log origin/<default> --since="<window>" --format="%at|%aN|%ai|%s" | sort -n
 # 4. Files most frequently changed (hotspot analysis)
 git log origin/<default> --since="<window>" --format="" --name-only | grep -v '^$' | sort | uniq -c | sort -rn
 
-# 5. PR numbers from commit messages (extract #NNN patterns)
-git log origin/<default> --since="<window>" --format="%s" | grep -oE '#[0-9]+' | sed 's/^#//' | sort -n | uniq | sed 's/^/#/'
+# 5. PR/MR numbers from commit messages (GitHub #NNN, GitLab !NNN)
+git log origin/<default> --since="<window>" --format="%s" | grep -oE '[#!][0-9]+' | sort -t'#' -k1 | uniq
 
 # 6. Per-author file hotspots (who touches what)
 git log origin/<default> --since="<window>" --format="AUTHOR:%aN" --name-only
@@ -589,8 +581,8 @@ git -C <path> log origin/$DEFAULT --since="<start_date>T00:00:00" --format="%at|
 # Per-author commit counts
 git -C <path> shortlog origin/$DEFAULT --since="<start_date>T00:00:00" -sn --no-merges
 
-# PR numbers from commit messages
-git -C <path> log origin/$DEFAULT --since="<start_date>T00:00:00" --format="%s" | grep -oE '#[0-9]+' | sort -n | uniq
+# PR/MR numbers from commit messages (GitHub #NNN, GitLab !NNN)
+git -C <path> log origin/$DEFAULT --since="<start_date>T00:00:00" --format="%s" | grep -oE '[#!][0-9]+' | sort -t'#' -k1 | uniq
 ```
 
 For repos that fail (deleted paths, network errors): skip and note "N repos could not be reached."
@@ -668,7 +660,7 @@ align cleanly. Never truncate project names.
 ║  • [1-line description of second theme]
 ║  • [1-line description of third theme]
 ║
-║  Powered by gstack · github.com/garrytan/gstack
+║  Powered by gstack
 ╚═══════════════════════════════════════════════════════════════
 ```
 
@@ -797,7 +789,7 @@ Use the Write tool to save JSON to `~/.gstack/retros/global-${today}-${next}.jso
   "projects": [
     {
       "name": "gstack",
-      "remote": "https://github.com/garrytan/gstack",
+      "remote": "<detected from git remote get-url origin, normalized to HTTPS>",
       "commits": 47,
       "insertions": 3200,
       "deletions": 800,
diff --git a/review/SKILL.md b/review/SKILL.md
index 3084a0e0..8a074573 100644
--- a/review/SKILL.md
+++ b/review/SKILL.md
@@ -32,9 +32,11 @@ _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr
 find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
 _CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
+_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
 echo "BRANCH: $_BRANCH"
 echo "PROACTIVE: $_PROACTIVE"
+echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
 source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
 REPO_MODE=${REPO_MODE:-unknown}
 echo "REPO_MODE: $REPO_MODE"
@@ -52,8 +54,11 @@ echo '{"skill":"review","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basen
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do [ -f "$_PF" ] && ~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true; break; done
 ```
 
-If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills — only invoke
-them when the user explicitly asks. The user opted out of proactive suggestions.
+If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
+auto-invoke skills based on conversation context. Only run skills the user explicitly
+types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say:
+"I think /skillname might help here — want me to run it?" and wait for confirmation.
+The user opted out of proactive behavior.
 
 If output shows `UPGRADE_AVAILABLE <old> <new>`: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED <from> <to>`: tell user "Running gstack v{to} (just updated!)" and continue.
 
@@ -102,6 +107,27 @@ touch ~/.gstack/.telemetry-prompted
 
 This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 
+If `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: After telemetry is handled,
+ask the user about proactive behavior. Use AskUserQuestion:
+
+> gstack can proactively figure out when you might need a skill while you work —
+> like suggesting /qa when you say "does this work?" or /investigate when you hit
+> a bug. We recommend keeping this on — it speeds up every part of your workflow.
+
+Options:
+- A) Keep it on (recommended)
+- B) Turn it off — I'll type /commands myself
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set proactive true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set proactive false`
+
+Always run:
+```bash
+touch ~/.gstack/.proactive-prompted
+```
+
+This only happens once. If `PROACTIVE_PROMPTED` is `yes`, skip this entirely.
+
 ## AskUserQuestion Format
 
 **ALWAYS follow this structure for every AskUserQuestion call:**
@@ -109,7 +135,6 @@ This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
 3. **Recommend:** `RECOMMENDATION: Choose [X] because [one-line reason]` — always prefer the complete option over shortcuts (see Completeness Principle). Include `Completeness: X/10` for each option. Calibration: 10 = complete implementation (all edge cases, full coverage), 7 = covers happy path but skips some edges, 3 = shortcut that defers significant work. If both options are 8+, pick the higher; if one is ≤5, flag it.
 4. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
-5. **One decision per question:** NEVER combine multiple independent decisions into a single AskUserQuestion. Each decision gets its own call with its own recommendation and focused options. Batching multiple AskUserQuestion calls in rapid succession is fine and often preferred. Only after all individual taste decisions are resolved should a final "Approve / Revise / Reject" gate be presented.
 
 Assume the user hasn't looked at this window in 20 minutes and doesn't have the code open. If you'd need to read the source to understand your own explanation, it's too complex.
 
@@ -117,97 +142,54 @@ Per-skill instructions may add additional formatting rules on top of this baseli
 
 ## Completeness Principle — Boil the Lake
 
-AI-assisted coding makes the marginal cost of completeness near-zero. When you present options:
+AI makes completeness near-free. Always recommend the complete option over shortcuts — the delta is minutes with CC+gstack. A "lake" (100% coverage, all edge cases) is boilable; an "ocean" (full rewrite, multi-quarter migration) is not. Boil lakes, flag oceans.
 
-- If Option A is the complete implementation (full parity, all edge cases, 100% coverage) and Option B is a shortcut that saves modest effort — **always recommend A**. The delta between 80 lines and 150 lines is meaningless with CC+gstack. "Good enough" is the wrong instinct when "complete" costs minutes more.
-- **Lake vs. ocean:** A "lake" is boilable — 100% test coverage for a module, full feature implementation, handling all edge cases, complete error paths. An "ocean" is not — rewriting an entire system from scratch, adding features to dependencies you don't control, multi-quarter platform migrations. Recommend boiling lakes. Flag oceans as out of scope.
-- **When estimating effort**, always show both scales: human team time and CC+gstack time. The compression ratio varies by task type — use this reference:
+**Effort reference** — always show both scales:
 
 | Task type | Human team | CC+gstack | Compression |
 |-----------|-----------|-----------|-------------|
-| Boilerplate / scaffolding | 2 days | 15 min | ~100x |
-| Test writing | 1 day | 15 min | ~50x |
-| Feature implementation | 1 week | 30 min | ~30x |
-| Bug fix + regression test | 4 hours | 15 min | ~20x |
-| Architecture / design | 2 days | 4 hours | ~5x |
-| Research / exploration | 1 day | 3 hours | ~3x |
+| Boilerplate | 2 days | 15 min | ~100x |
+| Tests | 1 day | 15 min | ~50x |
+| Feature | 1 week | 30 min | ~30x |
+| Bug fix | 4 hours | 15 min | ~20x |
 
-- This principle applies to test coverage, error handling, documentation, edge cases, and feature completeness. Don't skip the last 10% to "save time" — with AI, that 10% costs seconds.
+Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-**Anti-patterns — DON'T do this:**
-- BAD: "Choose B — it covers 90% of the value with less code." (If A is only 70 lines more, choose A.)
-- BAD: "We can skip edge case handling to save time." (Edge case handling costs minutes with CC.)
-- BAD: "Let's defer test coverage to a follow-up PR." (Tests are the cheapest lake to boil.)
-- BAD: Quoting only human-team effort: "This would take 2 weeks." (Say: "2 weeks human / ~1 hour CC.")
+## Repo Ownership — See Something, Say Something
 
-## Repo Ownership Mode — See Something, Say Something
+`REPO_MODE` controls how to handle issues outside your branch:
+- **`solo`** — You own everything. Investigate and offer to fix proactively.
+- **`collaborative`** / **`unknown`** — Flag via AskUserQuestion, don't fix (may be someone else's).
 
-`REPO_MODE` from the preamble tells you who owns issues in this repo:
-
-- **`solo`** — One person does 80%+ of the work. They own everything. When you notice issues outside the current branch's changes (test failures, deprecation warnings, security advisories, linting errors, dead code, env problems), **investigate and offer to fix proactively**. The solo dev is the only person who will fix it. Default to action.
-- **`collaborative`** — Multiple active contributors. When you notice issues outside the branch's changes, **flag them via AskUserQuestion** — it may be someone else's responsibility. Default to asking, not fixing.
-- **`unknown`** — Treat as collaborative (safer default — ask before fixing).
-
-**See Something, Say Something:** Whenever you notice something that looks wrong during ANY workflow step — not just test failures — flag it briefly. One sentence: what you noticed and its impact. In solo mode, follow up with "Want me to fix it?" In collaborative mode, just flag it and move on.
-
-Never let a noticed issue silently pass. The whole point is proactive communication.
+Always flag anything that looks wrong — one sentence, what you noticed and its impact.
 
 ## Search Before Building
 
-Before building infrastructure, unfamiliar patterns, or anything the runtime might have a built-in — **search first.** Read `~/.claude/skills/gstack/ETHOS.md` for the full philosophy.
+Before building anything unfamiliar, **search first.** See `~/.claude/skills/gstack/ETHOS.md`.
+- **Layer 1** (tried and true) — don't reinvent. **Layer 2** (new and popular) — scrutinize. **Layer 3** (first principles) — prize above all.
 
-**Three layers of knowledge:**
-- **Layer 1** (tried and true — in distribution). Don't reinvent the wheel. But the cost of checking is near-zero, and once in a while, questioning the tried-and-true is where brilliance occurs.
-- **Layer 2** (new and popular — search for these). But scrutinize: humans are subject to mania. Search results are inputs to your thinking, not answers.
-- **Layer 3** (first principles — prize these above all). Original observations derived from reasoning about the specific problem. The most valuable of all.
-
-**Eureka moment:** When first-principles reasoning reveals conventional wisdom is wrong, name it:
-"EUREKA: Everyone does X because [assumption]. But [evidence] shows this is wrong. Y is better because [reasoning]."
-
-Log eureka moments:
+**Eureka:** When first-principles reasoning contradicts conventional wisdom, name it and log:
 ```bash
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
-Replace SKILL_NAME and ONE_LINE_SUMMARY. Runs inline — don't stop the workflow.
-
-**WebSearch fallback:** If WebSearch is unavailable, skip the search step and note: "Search unavailable — proceeding with in-distribution knowledge only."
 
 ## Contributor Mode
 
-If `_CONTRIB` is `true`: you are in **contributor mode**. You're a gstack user who also helps make it better.
+If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
 
-**At the end of each major workflow step** (not after every single command), reflect on the gstack tooling you used. Rate your experience 0 to 10. If it wasn't a 10, think about why. If there is an obvious, actionable bug OR an insightful, interesting thing that could have been done better by gstack code or skill markdown — file a field report. Maybe our contributor will help make us better!
-
-**Calibration — this is the bar:** For example, `$B js "await fetch(...)"` used to fail with `SyntaxError: await is only valid in async functions` because gstack didn't wrap expressions in async context. Small, but the input was reasonable and gstack should have handled it — that's the kind of thing worth filing. Things less consequential than this, ignore.
-
-**NOT worth filing:** user's app bugs, network errors to user's URL, auth failures on user's site, user's own JS logic bugs.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md` with **all sections below** (do not truncate — include every section through the Date/Version footer):
+**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
 
+**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
 ```
 # {Title}
-
-Hey gstack team — ran into this while using /{skill-name}:
-
-**What I was trying to do:** {what the user/agent was attempting}
-**What happened instead:** {what actually happened}
-**My Rating:** {0-10} — {one sentence on why it wasn't a 10}
-
-## Steps to reproduce
+**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
+## Repro
 1. {step}
-
-## Raw output
-```
-{paste the actual error or unexpected output here}
-```
-
 ## What would make this a 10
-{one sentence: what gstack should have done differently}
-
-**Date:** {YYYY-MM-DD} | **Version:** {gstack version} | **Skill:** /{skill}
+{one sentence}
+**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
 ```
-
-Slug: lowercase, hyphens, max 60 chars (e.g. `browse-js-no-await`). Skip if file already exists. Max 3 reports per session. File inline and continue — don't stop the workflow. Tell user: "Filed gstack field report: {title}"
+Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
 
 ## Completion Status Protocol
 
@@ -298,22 +280,42 @@ Then write a `## GSTACK REVIEW REPORT` section to the end of the plan file:
 file you are allowed to edit in plan mode. The plan file review report is part of the
 plan's living status.
 
-## Step 0: Detect base branch
+## Step 0: Detect platform and base branch
 
-Determine which branch this PR targets. Use the result as "the base branch" in all subsequent steps.
+First, detect the git hosting platform from the remote URL:
 
-1. Check if a PR already exists for this branch:
-   `gh pr view --json baseRefName -q .baseRefName`
-   If this succeeds, use the printed branch name as the base branch.
+```bash
+git remote get-url origin 2>/dev/null
+```
 
-2. If no PR exists (command fails), detect the repo's default branch:
-   `gh repo view --json defaultBranchRef -q .defaultBranchRef.name`
+- If the URL contains "github.com" → platform is **GitHub**
+- If the URL contains "gitlab" → platform is **GitLab**
+- Otherwise, check CLI availability:
+  - `gh auth status 2>/dev/null` succeeds → platform is **GitHub** (covers GitHub Enterprise)
+  - `glab auth status 2>/dev/null` succeeds → platform is **GitLab** (covers self-hosted)
+  - Neither → **unknown** (use git-native commands only)
 
-3. If both commands fail, fall back to `main`.
+Determine which branch this PR/MR targets, or the repo's default branch if no
+PR/MR exists. Use the result as "the base branch" in all subsequent steps.
+
+**If GitHub:**
+1. `gh pr view --json baseRefName -q .baseRefName` — if succeeds, use it
+2. `gh repo view --json defaultBranchRef -q .defaultBranchRef.name` — if succeeds, use it
+
+**If GitLab:**
+1. `glab mr view -F json 2>/dev/null` and extract the `target_branch` field — if succeeds, use it
+2. `glab repo view -F json 2>/dev/null` and extract the `default_branch` field — if succeeds, use it
+
+**Git-native fallback (if unknown platform, or CLI commands fail):**
+1. `git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's|refs/remotes/origin/||'`
+2. If that fails: `git rev-parse --verify origin/main 2>/dev/null` → use `main`
+3. If that fails: `git rev-parse --verify origin/master 2>/dev/null` → use `master`
+
+If all fail, fall back to `main`.
 
 Print the detected base branch name. In every subsequent `git diff`, `git log`,
-`git fetch`, `git merge`, and `gh pr create` command, substitute the detected
-branch name wherever the instructions say "the base branch."
+`git fetch`, `git merge`, and PR/MR creation command, substitute the detected
+branch name wherever the instructions say "the base branch" or `<default>`.
 
 ---
 
diff --git a/scripts/gen-skill-docs.ts b/scripts/gen-skill-docs.ts
index f1a72fd1..172c0b6d 100644
--- a/scripts/gen-skill-docs.ts
+++ b/scripts/gen-skill-docs.ts
@@ -16,7 +16,7 @@ import * as fs from 'fs';
 import * as path from 'path';
 import type { Host, TemplateContext } from './resolvers/types';
 import { HOST_PATHS } from './resolvers/types';
-import { RESOLVERS as IMPORTED_RESOLVERS } from './resolvers/index';
+import { RESOLVERS } from './resolvers/index';
 import { codexSkillName, transformFrontmatter, extractHookSafetyProse, extractNameAndDescription, condenseOpenAIShortDescription, generateOpenAIYaml } from './resolvers/codex-helpers';
 import { generatePlanCompletionAuditShip, generatePlanCompletionAuditReview, generatePlanVerificationExec } from './resolvers/review';
 
@@ -34,35 +34,7 @@ const HOST: Host = (() => {
   throw new Error(`Unknown host: ${val}. Use claude, codex, or agents.`);
 })();
 
-interface HostPaths {
-  skillRoot: string;
-  localSkillRoot: string;
-  binDir: string;
-  browseDir: string;
-}
-
-const HOST_PATHS: Record<Host, HostPaths> = {
-  claude: {
-    skillRoot: '~/.claude/skills/gstack',
-    localSkillRoot: '.claude/skills/gstack',
-    binDir: '~/.claude/skills/gstack/bin',
-    browseDir: '~/.claude/skills/gstack/browse/dist',
-  },
-  codex: {
-    skillRoot: '$GSTACK_ROOT',
-    localSkillRoot: '.agents/skills/gstack',
-    binDir: '$GSTACK_BIN',
-    browseDir: '$GSTACK_BROWSE',
-  },
-};
-
-interface TemplateContext {
-  skillName: string;
-  tmplPath: string;
-  benefitsFrom?: string[];
-  host: Host;
-  paths: HostPaths;
-}
+// HostPaths, HOST_PATHS, and TemplateContext imported from ./resolvers/types (line 7-8)
 
 // ─── Shared Design Constants ────────────────────────────────
 
@@ -619,22 +591,42 @@ If \`NEEDS_SETUP\`:
 }
 
 function generateBaseBranchDetect(_ctx: TemplateContext): string {
-  return `## Step 0: Detect base branch
+  return `## Step 0: Detect platform and base branch
 
-Determine which branch this PR targets. Use the result as "the base branch" in all subsequent steps.
+First, detect the git hosting platform from the remote URL:
 
-1. Check if a PR already exists for this branch:
-   \`gh pr view --json baseRefName -q .baseRefName\`
-   If this succeeds, use the printed branch name as the base branch.
+\`\`\`bash
+git remote get-url origin 2>/dev/null
+\`\`\`
 
-2. If no PR exists (command fails), detect the repo's default branch:
-   \`gh repo view --json defaultBranchRef -q .defaultBranchRef.name\`
+- If the URL contains "github.com" → platform is **GitHub**
+- If the URL contains "gitlab" → platform is **GitLab**
+- Otherwise, check CLI availability:
+  - \`gh auth status 2>/dev/null\` succeeds → platform is **GitHub** (covers GitHub Enterprise)
+  - \`glab auth status 2>/dev/null\` succeeds → platform is **GitLab** (covers self-hosted)
+  - Neither → **unknown** (use git-native commands only)
 
-3. If both commands fail, fall back to \`main\`.
+Determine which branch this PR/MR targets, or the repo's default branch if no
+PR/MR exists. Use the result as "the base branch" in all subsequent steps.
+
+**If GitHub:**
+1. \`gh pr view --json baseRefName -q .baseRefName\` — if succeeds, use it
+2. \`gh repo view --json defaultBranchRef -q .defaultBranchRef.name\` — if succeeds, use it
+
+**If GitLab:**
+1. \`glab mr view -F json 2>/dev/null\` and extract the \`target_branch\` field — if succeeds, use it
+2. \`glab repo view -F json 2>/dev/null\` and extract the \`default_branch\` field — if succeeds, use it
+
+**Git-native fallback (if unknown platform, or CLI commands fail):**
+1. \`git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's|refs/remotes/origin/||'\`
+2. If that fails: \`git rev-parse --verify origin/main 2>/dev/null\` → use \`main\`
+3. If that fails: \`git rev-parse --verify origin/master 2>/dev/null\` → use \`master\`
+
+If all fail, fall back to \`main\`.
 
 Print the detected base branch name. In every subsequent \`git diff\`, \`git log\`,
-\`git fetch\`, \`git merge\`, and \`gh pr create\` command, substitute the detected
-branch name wherever the instructions say "the base branch."
+\`git fetch\`, \`git merge\`, and PR/MR creation command, substitute the detected
+branch name wherever the instructions say "the base branch" or \`<default>\`.
 
 ---`;
 }
@@ -2792,29 +2784,7 @@ ${slopItems}
 Source: [OpenAI "Designing Delightful Frontends with GPT-5.4"](https://developers.openai.com/blog/designing-delightful-frontends-with-gpt-5-4) (Mar 2026) + gstack design methodology.`;
 }
 
-function generateSlugEval(ctx: TemplateContext): string {
-  return `eval "$(${ctx.paths.binDir}/gstack-slug 2>/dev/null)"`;
-}
-
-function generateSlugSetup(ctx: TemplateContext): string {
-  return `eval "$(${ctx.paths.binDir}/gstack-slug 2>/dev/null)" && mkdir -p ~/.gstack/projects/$SLUG`;
-}
-
-// Use the canonical RESOLVERS from resolvers/index.ts, extended with local overrides.
-// Local overrides are kept for functions that have hardcoded ~/.claude/ paths in the
-// imported versions — the local versions are host-agnostic and safe for Codex output.
-const RESOLVERS: Record<string, (ctx: TemplateContext) => string> = {
-  ...IMPORTED_RESOLVERS,
-  // Local override — preamble generator with tier-gated sections
-  PREAMBLE: generatePreamble,
-  // Local overrides — these use host-agnostic paths (no ~/.claude/ hardcoding)
-  PLAN_FILE_REVIEW_REPORT: generatePlanFileReviewReport,
-  PLAN_COMPLETION_AUDIT_SHIP: generatePlanCompletionAuditShip,
-  PLAN_COMPLETION_AUDIT_REVIEW: generatePlanCompletionAuditReview,
-  PLAN_VERIFICATION_EXEC: generatePlanVerificationExec,
-  // Local-only entry not in resolvers/index.ts
-  CODEX_REVIEW_STEP: generateAdversarialStep,
-};
+// RESOLVERS imported from ./resolvers/index (line 19) — do not redeclare here
 
 // ─── Codex Helpers ───────────────────────────────────────────
 
diff --git a/scripts/resolvers/preamble.ts b/scripts/resolvers/preamble.ts
index 76573422..44126771 100644
--- a/scripts/resolvers/preamble.ts
+++ b/scripts/resolvers/preamble.ts
@@ -250,14 +250,22 @@ Use AskUserQuestion:
   git log --format="%an (%ae)" -1 -- <source-file-under-test>
   \`\`\`
   If these are different people, prefer the production code author — they likely introduced the regression.
-- Create a GitHub issue assigned to that person:
-  \`\`\`bash
-  gh issue create \\
-    --title "Pre-existing test failure: <test-name>" \\
-    --body "Found failing on branch <current-branch>. Failure is pre-existing.\\n\\n**Error:**\\n\`\`\`\\n<first 10 lines>\\n\`\`\`\\n\\n**Last modified by:** <author>\\n**Noticed by:** gstack /ship on <date>" \\
-    --assignee "<github-username>"
-  \`\`\`
-- If \`gh\` is not available or \`--assignee\` fails (user not in org, etc.), create the issue without assignee and note who should look at it in the body.
+- Create an issue assigned to that person (use the platform detected in Step 0):
+  - **If GitHub:**
+    \`\`\`bash
+    gh issue create \\
+      --title "Pre-existing test failure: <test-name>" \\
+      --body "Found failing on branch <current-branch>. Failure is pre-existing.\\n\\n**Error:**\\n\`\`\`\\n<first 10 lines>\\n\`\`\`\\n\\n**Last modified by:** <author>\\n**Noticed by:** gstack /ship on <date>" \\
+      --assignee "<github-username>"
+    \`\`\`
+  - **If GitLab:**
+    \`\`\`bash
+    glab issue create \\
+      -t "Pre-existing test failure: <test-name>" \\
+      -d "Found failing on branch <current-branch>. Failure is pre-existing.\\n\\n**Error:**\\n\`\`\`\\n<first 10 lines>\\n\`\`\`\\n\\n**Last modified by:** <author>\\n**Noticed by:** gstack /ship on <date>" \\
+      -a "<gitlab-username>"
+    \`\`\`
+- If neither CLI is available or \`--assignee\`/\`-a\` fails (user not in org, etc.), create the issue without assignee and note who should look at it in the body.
 - Continue with the workflow.
 
 **If "Skip":**
diff --git a/scripts/resolvers/review.ts b/scripts/resolvers/review.ts
index 960f171e..423002aa 100644
--- a/scripts/resolvers/review.ts
+++ b/scripts/resolvers/review.ts
@@ -9,7 +9,13 @@ After completing the review, read the review log and config to display the dashb
 ~/.claude/skills/gstack/bin/gstack-review-read
 \`\`\`
 
-Parse the output. Find the most recent entry for each skill (plan-ceo-review, plan-eng-review, review, plan-design-review, design-review-lite, adversarial-review, codex-review, codex-plan-review). Ignore entries with timestamps older than 7 days. For the Eng Review row, show whichever is more recent between \`review\` (diff-scoped pre-landing review) and \`plan-eng-review\` (plan-stage architecture review). Append "(DIFF)" or "(PLAN)" to the status to distinguish. For the Adversarial row, show whichever is more recent between \`adversarial-review\` (new auto-scaled) and \`codex-review\` (legacy). For Design Review, show whichever is more recent between \`plan-design-review\` (full visual audit) and \`design-review-lite\` (code-level check). Append "(FULL)" or "(LITE)" to the status to distinguish. Display:
+Parse the output. Find the most recent entry for each skill (plan-ceo-review, plan-eng-review, review, plan-design-review, design-review-lite, adversarial-review, codex-review, codex-plan-review). Ignore entries with timestamps older than 7 days. For the Eng Review row, show whichever is more recent between \`review\` (diff-scoped pre-landing review) and \`plan-eng-review\` (plan-stage architecture review). Append "(DIFF)" or "(PLAN)" to the status to distinguish. For the Adversarial row, show whichever is more recent between \`adversarial-review\` (new auto-scaled) and \`codex-review\` (legacy). For Design Review, show whichever is more recent between \`plan-design-review\` (full visual audit) and \`design-review-lite\` (code-level check). Append "(FULL)" or "(LITE)" to the status to distinguish. For the Outside Voice row, show the most recent \`codex-plan-review\` entry — this captures outside voices from both /plan-ceo-review and /plan-eng-review.
+
+**Source attribution:** If the most recent entry for a skill has a \\\`"via"\\\` field, append it to the status label in parentheses. Examples: \`plan-eng-review\` with \`via:"autoplan"\` shows as "CLEAR (PLAN via /autoplan)". \`review\` with \`via:"ship"\` shows as "CLEAR (DIFF via /ship)". Entries without a \`via\` field show as "CLEAR (PLAN)" or "CLEAR (DIFF)" as before.
+
+Note: \`autoplan-voices\` and \`design-outside-voices\` entries are audit-trail-only (forensic data for cross-model consensus analysis). They do not appear in the dashboard and are not checked by any consumer.
+
+Display:
 
 \`\`\`
 +====================================================================+
diff --git a/scripts/resolvers/utility.ts b/scripts/resolvers/utility.ts
index 03e72e21..6cd912f2 100644
--- a/scripts/resolvers/utility.ts
+++ b/scripts/resolvers/utility.ts
@@ -9,22 +9,42 @@ export function generateSlugSetup(ctx: TemplateContext): string {
 }
 
 export function generateBaseBranchDetect(_ctx: TemplateContext): string {
-  return `## Step 0: Detect base branch
+  return `## Step 0: Detect platform and base branch
 
-Determine which branch this PR targets. Use the result as "the base branch" in all subsequent steps.
+First, detect the git hosting platform from the remote URL:
 
-1. Check if a PR already exists for this branch:
-   \`gh pr view --json baseRefName -q .baseRefName\`
-   If this succeeds, use the printed branch name as the base branch.
+\`\`\`bash
+git remote get-url origin 2>/dev/null
+\`\`\`
 
-2. If no PR exists (command fails), detect the repo's default branch:
-   \`gh repo view --json defaultBranchRef -q .defaultBranchRef.name\`
+- If the URL contains "github.com" → platform is **GitHub**
+- If the URL contains "gitlab" → platform is **GitLab**
+- Otherwise, check CLI availability:
+  - \`gh auth status 2>/dev/null\` succeeds → platform is **GitHub** (covers GitHub Enterprise)
+  - \`glab auth status 2>/dev/null\` succeeds → platform is **GitLab** (covers self-hosted)
+  - Neither → **unknown** (use git-native commands only)
 
-3. If both commands fail, fall back to \`main\`.
+Determine which branch this PR/MR targets, or the repo's default branch if no
+PR/MR exists. Use the result as "the base branch" in all subsequent steps.
+
+**If GitHub:**
+1. \`gh pr view --json baseRefName -q .baseRefName\` — if succeeds, use it
+2. \`gh repo view --json defaultBranchRef -q .defaultBranchRef.name\` — if succeeds, use it
+
+**If GitLab:**
+1. \`glab mr view -F json 2>/dev/null\` and extract the \`target_branch\` field — if succeeds, use it
+2. \`glab repo view -F json 2>/dev/null\` and extract the \`default_branch\` field — if succeeds, use it
+
+**Git-native fallback (if unknown platform, or CLI commands fail):**
+1. \`git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's|refs/remotes/origin/||'\`
+2. If that fails: \`git rev-parse --verify origin/main 2>/dev/null\` → use \`main\`
+3. If that fails: \`git rev-parse --verify origin/master 2>/dev/null\` → use \`master\`
+
+If all fail, fall back to \`main\`.
 
 Print the detected base branch name. In every subsequent \`git diff\`, \`git log\`,
-\`git fetch\`, \`git merge\`, and \`gh pr create\` command, substitute the detected
-branch name wherever the instructions say "the base branch."
+\`git fetch\`, \`git merge\`, and PR/MR creation command, substitute the detected
+branch name wherever the instructions say "the base branch" or \`<default>\`.
 
 ---`;
 }
diff --git a/setup-browser-cookies/SKILL.md b/setup-browser-cookies/SKILL.md
index 698c7d05..523a533a 100644
--- a/setup-browser-cookies/SKILL.md
+++ b/setup-browser-cookies/SKILL.md
@@ -26,9 +26,11 @@ _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr
 find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
 _CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
+_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
 echo "BRANCH: $_BRANCH"
 echo "PROACTIVE: $_PROACTIVE"
+echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
 source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
 REPO_MODE=${REPO_MODE:-unknown}
 echo "REPO_MODE: $REPO_MODE"
@@ -46,8 +48,11 @@ echo '{"skill":"setup-browser-cookies","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do [ -f "$_PF" ] && ~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true; break; done
 ```
 
-If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills — only invoke
-them when the user explicitly asks. The user opted out of proactive suggestions.
+If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
+auto-invoke skills based on conversation context. Only run skills the user explicitly
+types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say:
+"I think /skillname might help here — want me to run it?" and wait for confirmation.
+The user opted out of proactive behavior.
 
 If output shows `UPGRADE_AVAILABLE <old> <new>`: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED <from> <to>`: tell user "Running gstack v{to} (just updated!)" and continue.
 
@@ -96,42 +101,44 @@ touch ~/.gstack/.telemetry-prompted
 
 This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 
+If `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: After telemetry is handled,
+ask the user about proactive behavior. Use AskUserQuestion:
+
+> gstack can proactively figure out when you might need a skill while you work —
+> like suggesting /qa when you say "does this work?" or /investigate when you hit
+> a bug. We recommend keeping this on — it speeds up every part of your workflow.
+
+Options:
+- A) Keep it on (recommended)
+- B) Turn it off — I'll type /commands myself
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set proactive true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set proactive false`
+
+Always run:
+```bash
+touch ~/.gstack/.proactive-prompted
+```
+
+This only happens once. If `PROACTIVE_PROMPTED` is `yes`, skip this entirely.
+
 ## Contributor Mode
 
-If `_CONTRIB` is `true`: you are in **contributor mode**. You're a gstack user who also helps make it better.
+If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
 
-**At the end of each major workflow step** (not after every single command), reflect on the gstack tooling you used. Rate your experience 0 to 10. If it wasn't a 10, think about why. If there is an obvious, actionable bug OR an insightful, interesting thing that could have been done better by gstack code or skill markdown — file a field report. Maybe our contributor will help make us better!
-
-**Calibration — this is the bar:** For example, `$B js "await fetch(...)"` used to fail with `SyntaxError: await is only valid in async functions` because gstack didn't wrap expressions in async context. Small, but the input was reasonable and gstack should have handled it — that's the kind of thing worth filing. Things less consequential than this, ignore.
-
-**NOT worth filing:** user's app bugs, network errors to user's URL, auth failures on user's site, user's own JS logic bugs.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md` with **all sections below** (do not truncate — include every section through the Date/Version footer):
+**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
 
+**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
 ```
 # {Title}
-
-Hey gstack team — ran into this while using /{skill-name}:
-
-**What I was trying to do:** {what the user/agent was attempting}
-**What happened instead:** {what actually happened}
-**My Rating:** {0-10} — {one sentence on why it wasn't a 10}
-
-## Steps to reproduce
+**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
+## Repro
 1. {step}
-
-## Raw output
-```
-{paste the actual error or unexpected output here}
-```
-
 ## What would make this a 10
-{one sentence: what gstack should have done differently}
-
-**Date:** {YYYY-MM-DD} | **Version:** {gstack version} | **Skill:** /{skill}
+{one sentence}
+**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
 ```
-
-Slug: lowercase, hyphens, max 60 chars (e.g. `browse-js-no-await`). Skip if file already exists. Max 3 reports per session. File inline and continue — don't stop the workflow. Tell user: "Filed gstack field report: {title}"
+Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
 
 ## Completion Status Protocol
 
diff --git a/setup-deploy/SKILL.md b/setup-deploy/SKILL.md
index 78d37546..e5c94278 100644
--- a/setup-deploy/SKILL.md
+++ b/setup-deploy/SKILL.md
@@ -32,9 +32,11 @@ _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr
 find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
 _CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
+_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
 echo "BRANCH: $_BRANCH"
 echo "PROACTIVE: $_PROACTIVE"
+echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
 source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
 REPO_MODE=${REPO_MODE:-unknown}
 echo "REPO_MODE: $REPO_MODE"
@@ -52,8 +54,11 @@ echo '{"skill":"setup-deploy","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do [ -f "$_PF" ] && ~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true; break; done
 ```
 
-If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills — only invoke
-them when the user explicitly asks. The user opted out of proactive suggestions.
+If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
+auto-invoke skills based on conversation context. Only run skills the user explicitly
+types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say:
+"I think /skillname might help here — want me to run it?" and wait for confirmation.
+The user opted out of proactive behavior.
 
 If output shows `UPGRADE_AVAILABLE <old> <new>`: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED <from> <to>`: tell user "Running gstack v{to} (just updated!)" and continue.
 
@@ -102,6 +107,27 @@ touch ~/.gstack/.telemetry-prompted
 
 This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 
+If `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: After telemetry is handled,
+ask the user about proactive behavior. Use AskUserQuestion:
+
+> gstack can proactively figure out when you might need a skill while you work —
+> like suggesting /qa when you say "does this work?" or /investigate when you hit
+> a bug. We recommend keeping this on — it speeds up every part of your workflow.
+
+Options:
+- A) Keep it on (recommended)
+- B) Turn it off — I'll type /commands myself
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set proactive true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set proactive false`
+
+Always run:
+```bash
+touch ~/.gstack/.proactive-prompted
+```
+
+This only happens once. If `PROACTIVE_PROMPTED` is `yes`, skip this entirely.
+
 ## AskUserQuestion Format
 
 **ALWAYS follow this structure for every AskUserQuestion call:**
@@ -109,7 +135,6 @@ This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
 3. **Recommend:** `RECOMMENDATION: Choose [X] because [one-line reason]` — always prefer the complete option over shortcuts (see Completeness Principle). Include `Completeness: X/10` for each option. Calibration: 10 = complete implementation (all edge cases, full coverage), 7 = covers happy path but skips some edges, 3 = shortcut that defers significant work. If both options are 8+, pick the higher; if one is ≤5, flag it.
 4. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
-5. **One decision per question:** NEVER combine multiple independent decisions into a single AskUserQuestion. Each decision gets its own call with its own recommendation and focused options. Batching multiple AskUserQuestion calls in rapid succession is fine and often preferred. Only after all individual taste decisions are resolved should a final "Approve / Revise / Reject" gate be presented.
 
 Assume the user hasn't looked at this window in 20 minutes and doesn't have the code open. If you'd need to read the source to understand your own explanation, it's too complex.
 
@@ -117,65 +142,36 @@ Per-skill instructions may add additional formatting rules on top of this baseli
 
 ## Completeness Principle — Boil the Lake
 
-AI-assisted coding makes the marginal cost of completeness near-zero. When you present options:
+AI makes completeness near-free. Always recommend the complete option over shortcuts — the delta is minutes with CC+gstack. A "lake" (100% coverage, all edge cases) is boilable; an "ocean" (full rewrite, multi-quarter migration) is not. Boil lakes, flag oceans.
 
-- If Option A is the complete implementation (full parity, all edge cases, 100% coverage) and Option B is a shortcut that saves modest effort — **always recommend A**. The delta between 80 lines and 150 lines is meaningless with CC+gstack. "Good enough" is the wrong instinct when "complete" costs minutes more.
-- **Lake vs. ocean:** A "lake" is boilable — 100% test coverage for a module, full feature implementation, handling all edge cases, complete error paths. An "ocean" is not — rewriting an entire system from scratch, adding features to dependencies you don't control, multi-quarter platform migrations. Recommend boiling lakes. Flag oceans as out of scope.
-- **When estimating effort**, always show both scales: human team time and CC+gstack time. The compression ratio varies by task type — use this reference:
+**Effort reference** — always show both scales:
 
 | Task type | Human team | CC+gstack | Compression |
 |-----------|-----------|-----------|-------------|
-| Boilerplate / scaffolding | 2 days | 15 min | ~100x |
-| Test writing | 1 day | 15 min | ~50x |
-| Feature implementation | 1 week | 30 min | ~30x |
-| Bug fix + regression test | 4 hours | 15 min | ~20x |
-| Architecture / design | 2 days | 4 hours | ~5x |
-| Research / exploration | 1 day | 3 hours | ~3x |
+| Boilerplate | 2 days | 15 min | ~100x |
+| Tests | 1 day | 15 min | ~50x |
+| Feature | 1 week | 30 min | ~30x |
+| Bug fix | 4 hours | 15 min | ~20x |
 
-- This principle applies to test coverage, error handling, documentation, edge cases, and feature completeness. Don't skip the last 10% to "save time" — with AI, that 10% costs seconds.
-
-**Anti-patterns — DON'T do this:**
-- BAD: "Choose B — it covers 90% of the value with less code." (If A is only 70 lines more, choose A.)
-- BAD: "We can skip edge case handling to save time." (Edge case handling costs minutes with CC.)
-- BAD: "Let's defer test coverage to a follow-up PR." (Tests are the cheapest lake to boil.)
-- BAD: Quoting only human-team effort: "This would take 2 weeks." (Say: "2 weeks human / ~1 hour CC.")
+Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
 ## Contributor Mode
 
-If `_CONTRIB` is `true`: you are in **contributor mode**. You're a gstack user who also helps make it better.
+If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
 
-**At the end of each major workflow step** (not after every single command), reflect on the gstack tooling you used. Rate your experience 0 to 10. If it wasn't a 10, think about why. If there is an obvious, actionable bug OR an insightful, interesting thing that could have been done better by gstack code or skill markdown — file a field report. Maybe our contributor will help make us better!
-
-**Calibration — this is the bar:** For example, `$B js "await fetch(...)"` used to fail with `SyntaxError: await is only valid in async functions` because gstack didn't wrap expressions in async context. Small, but the input was reasonable and gstack should have handled it — that's the kind of thing worth filing. Things less consequential than this, ignore.
-
-**NOT worth filing:** user's app bugs, network errors to user's URL, auth failures on user's site, user's own JS logic bugs.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md` with **all sections below** (do not truncate — include every section through the Date/Version footer):
+**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
 
+**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
 ```
 # {Title}
-
-Hey gstack team — ran into this while using /{skill-name}:
-
-**What I was trying to do:** {what the user/agent was attempting}
-**What happened instead:** {what actually happened}
-**My Rating:** {0-10} — {one sentence on why it wasn't a 10}
-
-## Steps to reproduce
+**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
+## Repro
 1. {step}
-
-## Raw output
-```
-{paste the actual error or unexpected output here}
-```
-
 ## What would make this a 10
-{one sentence: what gstack should have done differently}
-
-**Date:** {YYYY-MM-DD} | **Version:** {gstack version} | **Skill:** /{skill}
+{one sentence}
+**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
 ```
-
-Slug: lowercase, hyphens, max 60 chars (e.g. `browse-js-no-await`). Skip if file already exists. Max 3 reports per session. File inline and continue — don't stop the workflow. Tell user: "Filed gstack field report: {title}"
+Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
 
 ## Completion Status Protocol
 
diff --git a/ship/SKILL.md b/ship/SKILL.md
index e0b11967..a3e0b325 100644
--- a/ship/SKILL.md
+++ b/ship/SKILL.md
@@ -30,9 +30,11 @@ _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr
 find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
 _CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
+_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
 echo "BRANCH: $_BRANCH"
 echo "PROACTIVE: $_PROACTIVE"
+echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
 source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
 REPO_MODE=${REPO_MODE:-unknown}
 echo "REPO_MODE: $REPO_MODE"
@@ -50,8 +52,11 @@ echo '{"skill":"ship","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basenam
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do [ -f "$_PF" ] && ~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true; break; done
 ```
 
-If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills — only invoke
-them when the user explicitly asks. The user opted out of proactive suggestions.
+If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
+auto-invoke skills based on conversation context. Only run skills the user explicitly
+types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say:
+"I think /skillname might help here — want me to run it?" and wait for confirmation.
+The user opted out of proactive behavior.
 
 If output shows `UPGRADE_AVAILABLE <old> <new>`: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED <from> <to>`: tell user "Running gstack v{to} (just updated!)" and continue.
 
@@ -100,6 +105,27 @@ touch ~/.gstack/.telemetry-prompted
 
 This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 
+If `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: After telemetry is handled,
+ask the user about proactive behavior. Use AskUserQuestion:
+
+> gstack can proactively figure out when you might need a skill while you work —
+> like suggesting /qa when you say "does this work?" or /investigate when you hit
+> a bug. We recommend keeping this on — it speeds up every part of your workflow.
+
+Options:
+- A) Keep it on (recommended)
+- B) Turn it off — I'll type /commands myself
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set proactive true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set proactive false`
+
+Always run:
+```bash
+touch ~/.gstack/.proactive-prompted
+```
+
+This only happens once. If `PROACTIVE_PROMPTED` is `yes`, skip this entirely.
+
 ## AskUserQuestion Format
 
 **ALWAYS follow this structure for every AskUserQuestion call:**
@@ -107,7 +133,6 @@ This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely.
 2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
 3. **Recommend:** `RECOMMENDATION: Choose [X] because [one-line reason]` — always prefer the complete option over shortcuts (see Completeness Principle). Include `Completeness: X/10` for each option. Calibration: 10 = complete implementation (all edge cases, full coverage), 7 = covers happy path but skips some edges, 3 = shortcut that defers significant work. If both options are 8+, pick the higher; if one is ≤5, flag it.
 4. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
-5. **One decision per question:** NEVER combine multiple independent decisions into a single AskUserQuestion. Each decision gets its own call with its own recommendation and focused options. Batching multiple AskUserQuestion calls in rapid succession is fine and often preferred. Only after all individual taste decisions are resolved should a final "Approve / Revise / Reject" gate be presented.
 
 Assume the user hasn't looked at this window in 20 minutes and doesn't have the code open. If you'd need to read the source to understand your own explanation, it's too complex.
 
@@ -115,97 +140,54 @@ Per-skill instructions may add additional formatting rules on top of this baseli
 
 ## Completeness Principle — Boil the Lake
 
-AI-assisted coding makes the marginal cost of completeness near-zero. When you present options:
+AI makes completeness near-free. Always recommend the complete option over shortcuts — the delta is minutes with CC+gstack. A "lake" (100% coverage, all edge cases) is boilable; an "ocean" (full rewrite, multi-quarter migration) is not. Boil lakes, flag oceans.
 
-- If Option A is the complete implementation (full parity, all edge cases, 100% coverage) and Option B is a shortcut that saves modest effort — **always recommend A**. The delta between 80 lines and 150 lines is meaningless with CC+gstack. "Good enough" is the wrong instinct when "complete" costs minutes more.
-- **Lake vs. ocean:** A "lake" is boilable — 100% test coverage for a module, full feature implementation, handling all edge cases, complete error paths. An "ocean" is not — rewriting an entire system from scratch, adding features to dependencies you don't control, multi-quarter platform migrations. Recommend boiling lakes. Flag oceans as out of scope.
-- **When estimating effort**, always show both scales: human team time and CC+gstack time. The compression ratio varies by task type — use this reference:
+**Effort reference** — always show both scales:
 
 | Task type | Human team | CC+gstack | Compression |
 |-----------|-----------|-----------|-------------|
-| Boilerplate / scaffolding | 2 days | 15 min | ~100x |
-| Test writing | 1 day | 15 min | ~50x |
-| Feature implementation | 1 week | 30 min | ~30x |
-| Bug fix + regression test | 4 hours | 15 min | ~20x |
-| Architecture / design | 2 days | 4 hours | ~5x |
-| Research / exploration | 1 day | 3 hours | ~3x |
+| Boilerplate | 2 days | 15 min | ~100x |
+| Tests | 1 day | 15 min | ~50x |
+| Feature | 1 week | 30 min | ~30x |
+| Bug fix | 4 hours | 15 min | ~20x |
 
-- This principle applies to test coverage, error handling, documentation, edge cases, and feature completeness. Don't skip the last 10% to "save time" — with AI, that 10% costs seconds.
+Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-**Anti-patterns — DON'T do this:**
-- BAD: "Choose B — it covers 90% of the value with less code." (If A is only 70 lines more, choose A.)
-- BAD: "We can skip edge case handling to save time." (Edge case handling costs minutes with CC.)
-- BAD: "Let's defer test coverage to a follow-up PR." (Tests are the cheapest lake to boil.)
-- BAD: Quoting only human-team effort: "This would take 2 weeks." (Say: "2 weeks human / ~1 hour CC.")
+## Repo Ownership — See Something, Say Something
 
-## Repo Ownership Mode — See Something, Say Something
+`REPO_MODE` controls how to handle issues outside your branch:
+- **`solo`** — You own everything. Investigate and offer to fix proactively.
+- **`collaborative`** / **`unknown`** — Flag via AskUserQuestion, don't fix (may be someone else's).
 
-`REPO_MODE` from the preamble tells you who owns issues in this repo:
-
-- **`solo`** — One person does 80%+ of the work. They own everything. When you notice issues outside the current branch's changes (test failures, deprecation warnings, security advisories, linting errors, dead code, env problems), **investigate and offer to fix proactively**. The solo dev is the only person who will fix it. Default to action.
-- **`collaborative`** — Multiple active contributors. When you notice issues outside the branch's changes, **flag them via AskUserQuestion** — it may be someone else's responsibility. Default to asking, not fixing.
-- **`unknown`** — Treat as collaborative (safer default — ask before fixing).
-
-**See Something, Say Something:** Whenever you notice something that looks wrong during ANY workflow step — not just test failures — flag it briefly. One sentence: what you noticed and its impact. In solo mode, follow up with "Want me to fix it?" In collaborative mode, just flag it and move on.
-
-Never let a noticed issue silently pass. The whole point is proactive communication.
+Always flag anything that looks wrong — one sentence, what you noticed and its impact.
 
 ## Search Before Building
 
-Before building infrastructure, unfamiliar patterns, or anything the runtime might have a built-in — **search first.** Read `~/.claude/skills/gstack/ETHOS.md` for the full philosophy.
+Before building anything unfamiliar, **search first.** See `~/.claude/skills/gstack/ETHOS.md`.
+- **Layer 1** (tried and true) — don't reinvent. **Layer 2** (new and popular) — scrutinize. **Layer 3** (first principles) — prize above all.
 
-**Three layers of knowledge:**
-- **Layer 1** (tried and true — in distribution). Don't reinvent the wheel. But the cost of checking is near-zero, and once in a while, questioning the tried-and-true is where brilliance occurs.
-- **Layer 2** (new and popular — search for these). But scrutinize: humans are subject to mania. Search results are inputs to your thinking, not answers.
-- **Layer 3** (first principles — prize these above all). Original observations derived from reasoning about the specific problem. The most valuable of all.
-
-**Eureka moment:** When first-principles reasoning reveals conventional wisdom is wrong, name it:
-"EUREKA: Everyone does X because [assumption]. But [evidence] shows this is wrong. Y is better because [reasoning]."
-
-Log eureka moments:
+**Eureka:** When first-principles reasoning contradicts conventional wisdom, name it and log:
 ```bash
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
-Replace SKILL_NAME and ONE_LINE_SUMMARY. Runs inline — don't stop the workflow.
-
-**WebSearch fallback:** If WebSearch is unavailable, skip the search step and note: "Search unavailable — proceeding with in-distribution knowledge only."
 
 ## Contributor Mode
 
-If `_CONTRIB` is `true`: you are in **contributor mode**. You're a gstack user who also helps make it better.
+If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
 
-**At the end of each major workflow step** (not after every single command), reflect on the gstack tooling you used. Rate your experience 0 to 10. If it wasn't a 10, think about why. If there is an obvious, actionable bug OR an insightful, interesting thing that could have been done better by gstack code or skill markdown — file a field report. Maybe our contributor will help make us better!
-
-**Calibration — this is the bar:** For example, `$B js "await fetch(...)"` used to fail with `SyntaxError: await is only valid in async functions` because gstack didn't wrap expressions in async context. Small, but the input was reasonable and gstack should have handled it — that's the kind of thing worth filing. Things less consequential than this, ignore.
-
-**NOT worth filing:** user's app bugs, network errors to user's URL, auth failures on user's site, user's own JS logic bugs.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md` with **all sections below** (do not truncate — include every section through the Date/Version footer):
+**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
 
+**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
 ```
 # {Title}
-
-Hey gstack team — ran into this while using /{skill-name}:
-
-**What I was trying to do:** {what the user/agent was attempting}
-**What happened instead:** {what actually happened}
-**My Rating:** {0-10} — {one sentence on why it wasn't a 10}
-
-## Steps to reproduce
+**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
+## Repro
 1. {step}
-
-## Raw output
-```
-{paste the actual error or unexpected output here}
-```
-
 ## What would make this a 10
-{one sentence: what gstack should have done differently}
-
-**Date:** {YYYY-MM-DD} | **Version:** {gstack version} | **Skill:** /{skill}
+{one sentence}
+**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
 ```
-
-Slug: lowercase, hyphens, max 60 chars (e.g. `browse-js-no-await`). Skip if file already exists. Max 3 reports per session. File inline and continue — don't stop the workflow. Tell user: "Filed gstack field report: {title}"
+Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
 
 ## Completion Status Protocol
 
@@ -296,22 +278,42 @@ Then write a `## GSTACK REVIEW REPORT` section to the end of the plan file:
 file you are allowed to edit in plan mode. The plan file review report is part of the
 plan's living status.
 
-## Step 0: Detect base branch
+## Step 0: Detect platform and base branch
 
-Determine which branch this PR targets. Use the result as "the base branch" in all subsequent steps.
+First, detect the git hosting platform from the remote URL:
 
-1. Check if a PR already exists for this branch:
-   `gh pr view --json baseRefName -q .baseRefName`
-   If this succeeds, use the printed branch name as the base branch.
+```bash
+git remote get-url origin 2>/dev/null
+```
 
-2. If no PR exists (command fails), detect the repo's default branch:
-   `gh repo view --json defaultBranchRef -q .defaultBranchRef.name`
+- If the URL contains "github.com" → platform is **GitHub**
+- If the URL contains "gitlab" → platform is **GitLab**
+- Otherwise, check CLI availability:
+  - `gh auth status 2>/dev/null` succeeds → platform is **GitHub** (covers GitHub Enterprise)
+  - `glab auth status 2>/dev/null` succeeds → platform is **GitLab** (covers self-hosted)
+  - Neither → **unknown** (use git-native commands only)
 
-3. If both commands fail, fall back to `main`.
+Determine which branch this PR/MR targets, or the repo's default branch if no
+PR/MR exists. Use the result as "the base branch" in all subsequent steps.
+
+**If GitHub:**
+1. `gh pr view --json baseRefName -q .baseRefName` — if succeeds, use it
+2. `gh repo view --json defaultBranchRef -q .defaultBranchRef.name` — if succeeds, use it
+
+**If GitLab:**
+1. `glab mr view -F json 2>/dev/null` and extract the `target_branch` field — if succeeds, use it
+2. `glab repo view -F json 2>/dev/null` and extract the `default_branch` field — if succeeds, use it
+
+**Git-native fallback (if unknown platform, or CLI commands fail):**
+1. `git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's|refs/remotes/origin/||'`
+2. If that fails: `git rev-parse --verify origin/main 2>/dev/null` → use `main`
+3. If that fails: `git rev-parse --verify origin/master 2>/dev/null` → use `master`
+
+If all fail, fall back to `main`.
 
 Print the detected base branch name. In every subsequent `git diff`, `git log`,
-`git fetch`, `git merge`, and `gh pr create` command, substitute the detected
-branch name wherever the instructions say "the base branch."
+`git fetch`, `git merge`, and PR/MR creation command, substitute the detected
+branch name wherever the instructions say "the base branch" or `<default>`.
 
 ---
 
@@ -362,7 +364,13 @@ After completing the review, read the review log and config to display the dashb
 ~/.claude/skills/gstack/bin/gstack-review-read
 ```
 
-Parse the output. Find the most recent entry for each skill (plan-ceo-review, plan-eng-review, review, plan-design-review, design-review-lite, adversarial-review, codex-review, codex-plan-review). Ignore entries with timestamps older than 7 days. For the Eng Review row, show whichever is more recent between `review` (diff-scoped pre-landing review) and `plan-eng-review` (plan-stage architecture review). Append "(DIFF)" or "(PLAN)" to the status to distinguish. For the Adversarial row, show whichever is more recent between `adversarial-review` (new auto-scaled) and `codex-review` (legacy). For Design Review, show whichever is more recent between `plan-design-review` (full visual audit) and `design-review-lite` (code-level check). Append "(FULL)" or "(LITE)" to the status to distinguish. Display:
+Parse the output. Find the most recent entry for each skill (plan-ceo-review, plan-eng-review, review, plan-design-review, design-review-lite, adversarial-review, codex-review, codex-plan-review). Ignore entries with timestamps older than 7 days. For the Eng Review row, show whichever is more recent between `review` (diff-scoped pre-landing review) and `plan-eng-review` (plan-stage architecture review). Append "(DIFF)" or "(PLAN)" to the status to distinguish. For the Adversarial row, show whichever is more recent between `adversarial-review` (new auto-scaled) and `codex-review` (legacy). For Design Review, show whichever is more recent between `plan-design-review` (full visual audit) and `design-review-lite` (code-level check). Append "(FULL)" or "(LITE)" to the status to distinguish. For the Outside Voice row, show the most recent `codex-plan-review` entry — this captures outside voices from both /plan-ceo-review and /plan-eng-review.
+
+**Source attribution:** If the most recent entry for a skill has a \`"via"\` field, append it to the status label in parentheses. Examples: `plan-eng-review` with `via:"autoplan"` shows as "CLEAR (PLAN via /autoplan)". `review` with `via:"ship"` shows as "CLEAR (DIFF via /ship)". Entries without a `via` field show as "CLEAR (PLAN)" or "CLEAR (DIFF)" as before.
+
+Note: `autoplan-voices` and `design-outside-voices` entries are audit-trail-only (forensic data for cross-model consensus analysis). They do not appear in the dashboard and are not checked by any consumer.
+
+Display:
 
 ```
 +====================================================================+
@@ -401,26 +409,15 @@ Parse the output. Find the most recent entry for each skill (plan-ceo-review, pl
 
 If the Eng Review is NOT "CLEAR":
 
-1. **Check for a prior override on this branch:**
-   ```bash
-   eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
-   grep '"skill":"ship-review-override"' ~/.gstack/projects/$SLUG/$BRANCH-reviews.jsonl 2>/dev/null || echo "NO_OVERRIDE"
-   ```
-   If an override exists, display the dashboard and note "Review gate previously accepted — continuing." Do NOT ask again.
+Print: "No prior eng review found — ship will run its own pre-landing review in Step 3.5."
 
-2. **If no override exists,** use AskUserQuestion:
-   - Show that Eng Review is missing or has open issues
-   - RECOMMENDATION: Choose C if the change is obviously trivial (< 20 lines, typo fix, config-only); Choose B for larger changes
-   - Options: A) Ship anyway  B) Abort — run /review or /plan-eng-review first  C) Change is too small to need eng review
-   - If CEO Review is missing, mention as informational ("CEO Review not run — recommended for product changes") but do NOT block
-   - For Design Review: run `source <(~/.claude/skills/gstack/bin/gstack-diff-scope <base> 2>/dev/null)`. If `SCOPE_FRONTEND=true` and no design review (plan-design-review or design-review-lite) exists in the dashboard, mention: "Design Review not run — this PR changes frontend code. The lite design check will run automatically in Step 3.5, but consider running /design-review for a full visual audit post-implementation." Still never block.
+Check diff size: `git diff <base>...HEAD --stat | tail -1`. If the diff is >200 lines, add: "Note: This is a large diff. Consider running `/plan-eng-review` or `/autoplan` for architecture-level review before shipping."
 
-3. **If the user chooses A or C,** persist the decision so future `/ship` runs on this branch skip the gate:
-   ```bash
-   eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
-   echo '{"skill":"ship-review-override","timestamp":"'"$(date -u +%Y-%m-%dT%H:%M:%SZ)"'","decision":"USER_CHOICE"}' >> ~/.gstack/projects/$SLUG/$BRANCH-reviews.jsonl
-   ```
-   Substitute USER_CHOICE with "ship_anyway" or "not_relevant".
+If CEO Review is missing, mention as informational ("CEO Review not run — recommended for product changes") but do NOT block.
+
+For Design Review: run `source <(~/.claude/skills/gstack/bin/gstack-diff-scope <base> 2>/dev/null)`. If `SCOPE_FRONTEND=true` and no design review (plan-design-review or design-review-lite) exists in the dashboard, mention: "Design Review not run — this PR changes frontend code. The lite design check will run automatically in Step 3.5, but consider running /design-review for a full visual audit post-implementation." Still never block.
+
+Continue to Step 1.5 — do NOT block or ask. Ship runs its own review in Step 3.5.
 
 ---
 
@@ -437,12 +434,13 @@ service with existing deployment — verify that a distribution pipeline exists.
 2. If new artifact detected, check for a release workflow:
    ```bash
    ls .github/workflows/ 2>/dev/null | grep -iE 'release|publish|dist'
+   grep -qE 'release|publish|deploy' .gitlab-ci.yml 2>/dev/null && echo "GITLAB_CI_RELEASE"
    ```
 
 3. **If no release pipeline exists and a new artifact was added:** Use AskUserQuestion:
    - "This PR adds a new binary/tool but there's no CI/CD pipeline to build and publish it.
      Users won't be able to download the artifact after merge."
-   - A) Add a release workflow now (GitHub Actions cross-platform build + GitHub Releases)
+   - A) Add a release workflow now (CI/CD release pipeline — GitHub Actions or GitLab CI depending on platform)
    - B) Defer — add to TODOS.md
    - C) Not needed — this is internal/web-only, existing deployment covers it
 
@@ -722,14 +720,22 @@ Use AskUserQuestion:
   git log --format="%an (%ae)" -1 -- <source-file-under-test>
   ```
   If these are different people, prefer the production code author — they likely introduced the regression.
-- Create a GitHub issue assigned to that person:
-  ```bash
-  gh issue create \
-    --title "Pre-existing test failure: <test-name>" \
-    --body "Found failing on branch <current-branch>. Failure is pre-existing.\n\n**Error:**\n```\n<first 10 lines>\n```\n\n**Last modified by:** <author>\n**Noticed by:** gstack /ship on <date>" \
-    --assignee "<github-username>"
-  ```
-- If `gh` is not available or `--assignee` fails (user not in org, etc.), create the issue without assignee and note who should look at it in the body.
+- Create an issue assigned to that person (use the platform detected in Step 0):
+  - **If GitHub:**
+    ```bash
+    gh issue create \
+      --title "Pre-existing test failure: <test-name>" \
+      --body "Found failing on branch <current-branch>. Failure is pre-existing.\n\n**Error:**\n```\n<first 10 lines>\n```\n\n**Last modified by:** <author>\n**Noticed by:** gstack /ship on <date>" \
+      --assignee "<github-username>"
+    ```
+  - **If GitLab:**
+    ```bash
+    glab issue create \
+      -t "Pre-existing test failure: <test-name>" \
+      -d "Found failing on branch <current-branch>. Failure is pre-existing.\n\n**Error:**\n```\n<first 10 lines>\n```\n\n**Last modified by:** <author>\n**Noticed by:** gstack /ship on <date>" \
+      -a "<gitlab-username>"
+    ```
+- If neither CLI is available or `--assignee`/`-a` fails (user not in org, etc.), create the issue without assignee and note who should look at it in the body.
 - Continue with the workflow.
 
 **If "Skip":**
@@ -1331,6 +1337,13 @@ Present Codex output under a `CODEX (design):` header, merged with the checklist
 
    If no issues found: `Pre-Landing Review: No issues found.`
 
+9. Persist the review result to the review log:
+```bash
+~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"review","timestamp":"TIMESTAMP","status":"STATUS","issues_found":N,"critical":N,"informational":N,"commit":"'"$(git rev-parse --short HEAD)"'","via":"ship"}'
+```
+Substitute TIMESTAMP (ISO 8601), STATUS ("clean" if no issues, "issues_found" otherwise),
+and N values from the summary counts above. The `via:"ship"` distinguishes from standalone `/review` runs.
+
 Save the review output — it goes into the PR body in Step 8.
 
 ---
@@ -1676,12 +1689,13 @@ git push -u origin <branch-name>
 
 ---
 
-## Step 8: Create PR
+## Step 8: Create PR/MR
 
-Create a pull request using `gh`:
+Create a pull request (GitHub) or merge request (GitLab) using the platform detected in Step 0.
 
-```bash
-gh pr create --base <base> --title "<type>: <summary>" --body "$(cat <<'EOF'
+The PR/MR body should contain these sections:
+
+```
 ## Summary
 <bullet points from CHANGELOG>
 
@@ -1725,11 +1739,30 @@ gh pr create --base <base> --title "<type>: <summary>" --body "$(cat <<'EOF'
 - [x] All Vitest tests pass (N tests)
 
 🤖 Generated with [Claude Code](https://claude.com/claude-code)
+```
+
+**If GitHub:**
+
+```bash
+gh pr create --base <base> --title "<type>: <summary>" --body "$(cat <<'EOF'
+<PR body from above>
 EOF
 )"
 ```
 
-**Output the PR URL** — then proceed to Step 8.5.
+**If GitLab:**
+
+```bash
+glab mr create -b <base> -t "<type>: <summary>" -d "$(cat <<'EOF'
+<MR body from above>
+EOF
+)"
+```
+
+**If neither CLI is available:**
+Print the branch name, remote URL, and instruct the user to create the PR/MR manually via the web UI. Do not stop — the code is pushed and ready.
+
+**Output the PR/MR URL** — then proceed to Step 8.5.
 
 ---
 
diff --git a/ship/SKILL.md.tmpl b/ship/SKILL.md.tmpl
index 7f82c64d..7f545cd9 100644
--- a/ship/SKILL.md.tmpl
+++ b/ship/SKILL.md.tmpl
@@ -64,26 +64,15 @@ You are running the `/ship` workflow. This is a **non-interactive, fully automat
 
 If the Eng Review is NOT "CLEAR":
 
-1. **Check for a prior override on this branch:**
-   ```bash
-   {{SLUG_EVAL}}
-   grep '"skill":"ship-review-override"' ~/.gstack/projects/$SLUG/$BRANCH-reviews.jsonl 2>/dev/null || echo "NO_OVERRIDE"
-   ```
-   If an override exists, display the dashboard and note "Review gate previously accepted — continuing." Do NOT ask again.
+Print: "No prior eng review found — ship will run its own pre-landing review in Step 3.5."
 
-2. **If no override exists,** use AskUserQuestion:
-   - Show that Eng Review is missing or has open issues
-   - RECOMMENDATION: Choose C if the change is obviously trivial (< 20 lines, typo fix, config-only); Choose B for larger changes
-   - Options: A) Ship anyway  B) Abort — run /review or /plan-eng-review first  C) Change is too small to need eng review
-   - If CEO Review is missing, mention as informational ("CEO Review not run — recommended for product changes") but do NOT block
-   - For Design Review: run `source <(~/.claude/skills/gstack/bin/gstack-diff-scope <base> 2>/dev/null)`. If `SCOPE_FRONTEND=true` and no design review (plan-design-review or design-review-lite) exists in the dashboard, mention: "Design Review not run — this PR changes frontend code. The lite design check will run automatically in Step 3.5, but consider running /design-review for a full visual audit post-implementation." Still never block.
+Check diff size: `git diff <base>...HEAD --stat | tail -1`. If the diff is >200 lines, add: "Note: This is a large diff. Consider running `/plan-eng-review` or `/autoplan` for architecture-level review before shipping."
 
-3. **If the user chooses A or C,** persist the decision so future `/ship` runs on this branch skip the gate:
-   ```bash
-   {{SLUG_EVAL}}
-   echo '{"skill":"ship-review-override","timestamp":"'"$(date -u +%Y-%m-%dT%H:%M:%SZ)"'","decision":"USER_CHOICE"}' >> ~/.gstack/projects/$SLUG/$BRANCH-reviews.jsonl
-   ```
-   Substitute USER_CHOICE with "ship_anyway" or "not_relevant".
+If CEO Review is missing, mention as informational ("CEO Review not run — recommended for product changes") but do NOT block.
+
+For Design Review: run `source <(~/.claude/skills/gstack/bin/gstack-diff-scope <base> 2>/dev/null)`. If `SCOPE_FRONTEND=true` and no design review (plan-design-review or design-review-lite) exists in the dashboard, mention: "Design Review not run — this PR changes frontend code. The lite design check will run automatically in Step 3.5, but consider running /design-review for a full visual audit post-implementation." Still never block.
+
+Continue to Step 1.5 — do NOT block or ask. Ship runs its own review in Step 3.5.
 
 ---
 
@@ -100,12 +89,13 @@ service with existing deployment — verify that a distribution pipeline exists.
 2. If new artifact detected, check for a release workflow:
    ```bash
    ls .github/workflows/ 2>/dev/null | grep -iE 'release|publish|dist'
+   grep -qE 'release|publish|deploy' .gitlab-ci.yml 2>/dev/null && echo "GITLAB_CI_RELEASE"
    ```
 
 3. **If no release pipeline exists and a new artifact was added:** Use AskUserQuestion:
    - "This PR adds a new binary/tool but there's no CI/CD pipeline to build and publish it.
      Users won't be able to download the artifact after merge."
-   - A) Add a release workflow now (GitHub Actions cross-platform build + GitHub Releases)
+   - A) Add a release workflow now (CI/CD release pipeline — GitHub Actions or GitLab CI depending on platform)
    - B) Defer — add to TODOS.md
    - C) Not needed — this is internal/web-only, existing deployment covers it
 
@@ -274,6 +264,13 @@ Review the diff for structural issues that tests don't catch.
 
    If no issues found: `Pre-Landing Review: No issues found.`
 
+9. Persist the review result to the review log:
+```bash
+~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"review","timestamp":"TIMESTAMP","status":"STATUS","issues_found":N,"critical":N,"informational":N,"commit":"'"$(git rev-parse --short HEAD)"'","via":"ship"}'
+```
+Substitute TIMESTAMP (ISO 8601), STATUS ("clean" if no issues, "issues_found" otherwise),
+and N values from the summary counts above. The `via:"ship"` distinguishes from standalone `/review` runs.
+
 Save the review output — it goes into the PR body in Step 8.
 
 ---
@@ -485,12 +482,13 @@ git push -u origin <branch-name>
 
 ---
 
-## Step 8: Create PR
+## Step 8: Create PR/MR
 
-Create a pull request using `gh`:
+Create a pull request (GitHub) or merge request (GitLab) using the platform detected in Step 0.
 
-```bash
-gh pr create --base <base> --title "<type>: <summary>" --body "$(cat <<'EOF'
+The PR/MR body should contain these sections:
+
+```
 ## Summary
 <bullet points from CHANGELOG>
 
@@ -534,11 +532,30 @@ gh pr create --base <base> --title "<type>: <summary>" --body "$(cat <<'EOF'
 - [x] All Vitest tests pass (N tests)
 
 🤖 Generated with [Claude Code](https://claude.com/claude-code)
+```
+
+**If GitHub:**
+
+```bash
+gh pr create --base <base> --title "<type>: <summary>" --body "$(cat <<'EOF'
+<PR body from above>
 EOF
 )"
 ```
 
-**Output the PR URL** — then proceed to Step 8.5.
+**If GitLab:**
+
+```bash
+glab mr create -b <base> -t "<type>: <summary>" -d "$(cat <<'EOF'
+<MR body from above>
+EOF
+)"
+```
+
+**If neither CLI is available:**
+Print the branch name, remote URL, and instruct the user to create the PR/MR manually via the web UI. Do not stop — the code is pushed and ready.
+
+**Output the PR/MR URL** — then proceed to Step 8.5.
 
 ---
 
diff --git a/test/gen-skill-docs.test.ts b/test/gen-skill-docs.test.ts
index c26bb64b..cab12413 100644
--- a/test/gen-skill-docs.test.ts
+++ b/test/gen-skill-docs.test.ts
@@ -351,6 +351,39 @@ describe('BASE_BRANCH_DETECT resolver', () => {
   test('resolver output uses "the base branch" phrasing', () => {
     expect(shipContent).toContain('the base branch');
   });
+
+  test('resolver output contains GitLab CLI commands', () => {
+    expect(shipContent).toContain('glab');
+  });
+
+  test('resolver output contains git-native fallback', () => {
+    expect(shipContent).toContain('git symbolic-ref');
+  });
+
+  test('resolver output mentions GitLab platform', () => {
+    expect(shipContent).toMatch(/gitlab/i);
+  });
+});
+
+describe('GitLab support in generated skills', () => {
+  const retroContent = fs.readFileSync(path.join(ROOT, 'retro', 'SKILL.md'), 'utf-8');
+  const shipSkillContent = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
+
+  test('retro contains GitLab MR number extraction', () => {
+    expect(retroContent).toContain('[#!]');
+  });
+
+  test('retro uses BASE_BRANCH_DETECT (contains glab)', () => {
+    expect(retroContent).toContain('glab');
+  });
+
+  test('ship contains glab mr create', () => {
+    expect(shipSkillContent).toContain('glab mr create');
+  });
+
+  test('ship checks .gitlab-ci.yml', () => {
+    expect(shipSkillContent).toContain('.gitlab-ci.yml');
+  });
 });
 
 /**
diff --git a/test/helpers/touchfiles.ts b/test/helpers/touchfiles.ts
index c2994c3d..593d50cc 100644
--- a/test/helpers/touchfiles.ts
+++ b/test/helpers/touchfiles.ts
@@ -79,6 +79,9 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
   // Ship
   'ship-base-branch': ['ship/**', 'bin/gstack-repo-mode'],
   'ship-local-workflow': ['ship/**', 'scripts/gen-skill-docs.ts'],
+  'review-dashboard-via': ['ship/**', 'scripts/resolvers/review.ts', 'codex/**', 'autoplan/**', 'land-and-deploy/**'],
+  'ship-plan-completion': ['ship/**', 'scripts/gen-skill-docs.ts'],
+  'ship-plan-verification': ['ship/**', 'scripts/gen-skill-docs.ts'],
 
   // Retro
   'retro':             ['retro/**'],
@@ -185,6 +188,7 @@ export const E2E_TIERS: Record<string, 'gate' | 'periodic'> = {
   'review-design-lite': 'periodic',   // 4/7 threshold is subjective
   'review-coverage-audit': 'gate',
   'review-plan-completion': 'gate',
+  'review-dashboard-via': 'gate',
 
   // Office Hours
   'office-hours-spec-review': 'gate',
diff --git a/test/skill-e2e-review.test.ts b/test/skill-e2e-review.test.ts
index b1d5442d..b5ad501c 100644
--- a/test/skill-e2e-review.test.ts
+++ b/test/skill-e2e-review.test.ts
@@ -529,6 +529,119 @@ Analyze the git history and produce the narrative report as described in the SKI
   }, 420_000);
 });
 
+// --- Review Dashboard Via Attribution E2E ---
+
+describeIfSelected('Review Dashboard Via Attribution', ['review-dashboard-via'], () => {
+  let dashDir: string;
+
+  beforeAll(() => {
+    dashDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-dashboard-via-'));
+    const run = (cmd: string, args: string[], cwd = dashDir) =>
+      spawnSync(cmd, args, { cwd, stdio: 'pipe', timeout: 5000 });
+
+    // Create git repo with feature branch
+    run('git', ['init', '-b', 'main']);
+    run('git', ['config', 'user.email', 'test@test.com']);
+    run('git', ['config', 'user.name', 'Test']);
+
+    fs.writeFileSync(path.join(dashDir, 'app.ts'), 'console.log("v1");\n');
+    run('git', ['add', 'app.ts']);
+    run('git', ['commit', '-m', 'initial']);
+
+    run('git', ['checkout', '-b', 'feature/dashboard-test']);
+    fs.writeFileSync(path.join(dashDir, 'app.ts'), 'console.log("v2");\n');
+    run('git', ['add', 'app.ts']);
+    run('git', ['commit', '-m', 'feat: update']);
+
+    // Get HEAD commit for review entries
+    const headResult = spawnSync('git', ['rev-parse', '--short', 'HEAD'], { cwd: dashDir, stdio: 'pipe' });
+    const commit = headResult.stdout.toString().trim();
+
+    // Pre-populate review log with autoplan-sourced entries
+    // gstack-review-read reads from ~/.gstack/projects/$SLUG/$BRANCH-reviews.jsonl
+    // For the test, we'll write a mock gstack-review-read script that returns our test data
+    const timestamp = new Date().toISOString().replace(/\.\d{3}Z$/, 'Z');
+    const reviewData = [
+      `{"skill":"plan-eng-review","timestamp":"${timestamp}","status":"clean","unresolved":0,"critical_gaps":0,"issues_found":0,"mode":"FULL_REVIEW","via":"autoplan","commit":"${commit}"}`,
+      `{"skill":"plan-ceo-review","timestamp":"${timestamp}","status":"clean","unresolved":0,"critical_gaps":0,"mode":"SELECTIVE_EXPANSION","via":"autoplan","commit":"${commit}"}`,
+      `{"skill":"codex-plan-review","timestamp":"${timestamp}","status":"clean","source":"codex","commit":"${commit}"}`,
+    ].join('\n');
+
+    // Write a mock gstack-review-read that returns our test data
+    const mockBinDir = path.join(dashDir, '.mock-bin');
+    fs.mkdirSync(mockBinDir, { recursive: true });
+    fs.writeFileSync(path.join(mockBinDir, 'gstack-review-read'), [
+      '#!/usr/bin/env bash',
+      `echo '${reviewData.split('\n').join("'\necho '")}'`,
+      'echo "---CONFIG---"',
+      'echo "false"',
+      'echo "---HEAD---"',
+      `echo "${commit}"`,
+    ].join('\n'));
+    fs.chmodSync(path.join(mockBinDir, 'gstack-review-read'), 0o755);
+
+    // Copy ship skill
+    fs.copyFileSync(path.join(ROOT, 'ship', 'SKILL.md'), path.join(dashDir, 'ship-SKILL.md'));
+  });
+
+  afterAll(() => {
+    try { fs.rmSync(dashDir, { recursive: true, force: true }); } catch {}
+  });
+
+  testConcurrentIfSelected('review-dashboard-via', async () => {
+    const mockBinDir = path.join(dashDir, '.mock-bin');
+
+    const result = await runSkillTest({
+      prompt: `Read ship-SKILL.md. You only need to run the Review Readiness Dashboard section.
+
+Instead of running ~/.claude/skills/gstack/bin/gstack-review-read, run this mock: ${mockBinDir}/gstack-review-read
+
+Parse the output and display the dashboard table. Pay attention to:
+1. The "via" field in entries — show source attribution (e.g., "via /autoplan")
+2. The codex-plan-review entry — it should populate the Outside Voice row
+3. Since Eng Review IS clear, there should be NO gate blocking — just display the dashboard
+
+Skip the preamble, lake intro, telemetry, and all other ship steps.
+Write the dashboard output to ${dashDir}/dashboard-output.md`,
+      workingDirectory: dashDir,
+      maxTurns: 12,
+      timeout: 90_000,
+      testName: 'review-dashboard-via',
+      runId,
+    });
+
+    logCost('/ship dashboard-via', result);
+    recordE2E(evalCollector, '/ship review dashboard via attribution', 'Dashboard via field', result);
+    expect(result.exitReason).toBe('success');
+
+    // Check dashboard output for via attribution
+    const dashPath = path.join(dashDir, 'dashboard-output.md');
+    const allOutput = [
+      result.output || '',
+      ...result.toolCalls.map(tc => tc.output || ''),
+    ].join('\n').toLowerCase();
+
+    // Verify via attribution appears somewhere (conversation or file)
+    let dashContent = '';
+    if (fs.existsSync(dashPath)) {
+      dashContent = fs.readFileSync(dashPath, 'utf-8').toLowerCase();
+    }
+    const combined = allOutput + dashContent;
+
+    // Should mention autoplan attribution
+    expect(combined).toMatch(/autoplan/);
+    // Should show eng review as CLEAR (it has a clean entry)
+    expect(combined).toMatch(/clear/i);
+    // Should NOT contain AskUserQuestion gate (no blocking)
+    const gateQuestions = result.toolCalls.filter(tc =>
+      tc.tool === 'mcp__conductor__AskUserQuestion' ||
+      (tc.tool === 'AskUserQuestion')
+    );
+    // Ship dashboard should not gate when eng review is clear
+    expect(gateQuestions).toHaveLength(0);
+  }, 120_000);
+});
+
 // Module-level afterAll — finalize eval collector after all tests complete
 afterAll(async () => {
   await finalizeEvalCollector(evalCollector);
diff --git a/test/skill-validation.test.ts b/test/skill-validation.test.ts
index 535ce73f..655a454b 100644
--- a/test/skill-validation.test.ts
+++ b/test/skill-validation.test.ts
@@ -1369,11 +1369,6 @@ describe('Codex skill', () => {
     expect(content).toContain('Persist Eng Review result');
   });
 
-  test('/ship gate suggests /review or /plan-eng-review when Eng Review is missing', () => {
-    const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
-    expect(content).toContain('Abort — run /review or /plan-eng-review first');
-  });
-
   test('Review Readiness Dashboard includes Adversarial Review row', () => {
     const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
     expect(content).toContain('Adversarial');