feat: integrate learnings + confidence into 9 skill templates

Add {{LEARNINGS_SEARCH}}, {{LEARNINGS_LOG}}, and {{CONFIDENCE_CALIBRATION}}
placeholders to review, ship, plan-eng-review, plan-ceo-review, office-hours,
investigate, retro, and cso templates. Regenerated all SKILL.md files.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

SKILL.md

@@ -57,6 +57,15 @@ for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null
   fi
   break
 done
+# Learnings count
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.jsonl"
+if [ -f "$_LEARN_FILE" ]; then
+  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
+  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+else
+  echo "LEARNINGS: 0"
+fi
 ```
 
 If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not

autoplan/SKILL.md

@@ -66,6 +66,15 @@ for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null
   fi
   break
 done
+# Learnings count
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.jsonl"
+if [ -f "$_LEARN_FILE" ]; then
+  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
+  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+else
+  echo "LEARNINGS: 0"
+fi
 ```
 
 If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not

benchmark/SKILL.md

@@ -59,6 +59,15 @@ for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null
   fi
   break
 done
+# Learnings count
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.jsonl"
+if [ -f "$_LEARN_FILE" ]; then
+  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
+  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+else
+  echo "LEARNINGS: 0"
+fi
 ```
 
 If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not

browse/SKILL.md

@@ -59,6 +59,15 @@ for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null
   fi
   break
 done
+# Learnings count
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.jsonl"
+if [ -f "$_LEARN_FILE" ]; then
+  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
+  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+else
+  echo "LEARNINGS: 0"
+fi
 ```
 
 If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not

canary/SKILL.md

@@ -59,6 +59,15 @@ for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null
   fi
   break
 done
+# Learnings count
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.jsonl"
+if [ -f "$_LEARN_FILE" ]; then
+  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
+  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+else
+  echo "LEARNINGS: 0"
+fi
 ```
 
 If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not

codex/SKILL.md

@@ -60,6 +60,15 @@ for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null
   fi
   break
 done
+# Learnings count
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.jsonl"
+if [ -f "$_LEARN_FILE" ]; then
+  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
+  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+else
+  echo "LEARNINGS: 0"
+fi
 ```
 
 If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not

connect-chrome/SKILL.md

@@ -57,6 +57,15 @@ for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null
   fi
   break
 done
+# Learnings count
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.jsonl"
+if [ -f "$_LEARN_FILE" ]; then
+  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
+  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+else
+  echo "LEARNINGS: 0"
+fi
 ```
 
 If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not

cso/SKILL.md

@@ -63,6 +63,15 @@ for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null
   fi
   break
 done
+# Learnings count
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.jsonl"
+if [ -f "$_LEARN_FILE" ]; then
+  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
+  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+else
+  echo "LEARNINGS: 0"
+fi
 ```
 
 If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
@@ -794,6 +803,31 @@ SECURITY FINDINGS
 4   HIGH   9/10   UNVERIFIED  Integrations     Webhook w/o signature verify     P6      api/webhooks.ts:24
 ```
 
+## Confidence Calibration
+
+Every finding MUST include a confidence score (1-10):
+
+| Score | Meaning | Display rule |
+|-------|---------|-------------|
+| 9-10 | Verified by reading specific code. Concrete bug or exploit demonstrated. | Show normally |
+| 7-8 | High confidence pattern match. Very likely correct. | Show normally |
+| 5-6 | Moderate. Could be a false positive. | Show with caveat: "Medium confidence, verify this is actually an issue" |
+| 3-4 | Low confidence. Pattern is suspicious but may be fine. | Suppress from main report. Include in appendix only. |
+| 1-2 | Speculation. | Only report if severity would be P0. |
+
+**Finding format:**
+
+\`[SEVERITY] (confidence: N/10) file:line — description\`
+
+Example:
+\`[P1] (confidence: 9/10) app/models/user.rb:42 — SQL injection via string interpolation in where clause\`
+\`[P2] (confidence: 5/10) app/controllers/api/v1/users_controller.rb:18 — Possible N+1 query, verify with production logs\`
+
+**Calibration learning:** If you report a finding with confidence < 7 and the user
+confirms it IS a real issue, that is a calibration event. Your initial confidence was
+too low. Log the corrected pattern as a learning so future reviews catch it with
+higher confidence.
+
 For each finding:
 ```
 ## Finding N: [Title] — [File:Line]

cso/SKILL.md.tmpl

@@ -487,6 +487,8 @@ SECURITY FINDINGS
 4   HIGH   9/10   UNVERIFIED  Integrations     Webhook w/o signature verify     P6      api/webhooks.ts:24
 ```
 
+{{CONFIDENCE_CALIBRATION}}
+
 For each finding:
 ```
 ## Finding N: [Title] — [File:Line]

design-consultation/SKILL.md

@@ -64,6 +64,15 @@ for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null
   fi
   break
 done
+# Learnings count
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.jsonl"
+if [ -f "$_LEARN_FILE" ]; then
+  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
+  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+else
+  echo "LEARNINGS: 0"
+fi
 ```
 
 If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not

design-review/SKILL.md

@@ -64,6 +64,15 @@ for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null
   fi
   break
 done
+# Learnings count
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.jsonl"
+if [ -f "$_LEARN_FILE" ]; then
+  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
+  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+else
+  echo "LEARNINGS: 0"
+fi
 ```
 
 If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not

design-shotgun/SKILL.md

@@ -61,6 +61,15 @@ for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null
   fi
   break
 done
+# Learnings count
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.jsonl"
+if [ -f "$_LEARN_FILE" ]; then
+  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
+  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+else
+  echo "LEARNINGS: 0"
+fi
 ```
 
 If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not

document-release/SKILL.md

@@ -61,6 +61,15 @@ for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null
   fi
   break
 done
+# Learnings count
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.jsonl"
+if [ -f "$_LEARN_FILE" ]; then
+  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
+  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+else
+  echo "LEARNINGS: 0"
+fi
 ```
 
 If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not

investigate/SKILL.md

@@ -75,6 +75,15 @@ for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null
   fi
   break
 done
+# Learnings count
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.jsonl"
+if [ -f "$_LEARN_FILE" ]; then
+  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
+  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+else
+  echo "LEARNINGS: 0"
+fi
 ```
 
 If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
@@ -367,6 +376,44 @@ Gather context before forming any hypothesis.
 
 4. **Reproduce:** Can you trigger the bug deterministically? If not, gather more evidence before proceeding.
 
+## Prior Learnings
+
+Search for relevant learnings from previous sessions:
+
+```bash
+_CROSS_PROJ=$(~/.claude/skills/gstack/bin/gstack-config get cross_project_learnings 2>/dev/null || echo "unset")
+echo "CROSS_PROJECT: $_CROSS_PROJ"
+if [ "$_CROSS_PROJ" = "true" ]; then
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 --cross-project 2>/dev/null || true
+else
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 2>/dev/null || true
+fi
+```
+
+If `CROSS_PROJECT` is `unset` (first time): Use AskUserQuestion:
+
+> gstack can search learnings from your other projects on this machine to find
+> patterns that might apply here. This stays local (no data leaves your machine).
+> Recommended for solo developers. Skip if you work on multiple client codebases
+> where cross-contamination would be a concern.
+
+Options:
+- A) Enable cross-project learnings (recommended)
+- B) Keep learnings project-scoped only
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings false`
+
+Then re-run the search with the appropriate flag.
+
+If learnings are found, incorporate them into your analysis. When a review finding
+matches a past learning, display:
+
+**"Prior learning applied: [key] (confidence N/10, from [date])"**
+
+This makes the compounding visible. The user should see that gstack is getting
+smarter on their codebase over time.
+
 Output: **"Root cause hypothesis: ..."** — a specific, testable claim about what is wrong and why.
 
 ---
@@ -490,6 +537,30 @@ Status:          DONE | DONE_WITH_CONCERNS | BLOCKED
 ════════════════════════════════════════
 ```
 
+## Capture Learnings
+
+If you discovered a non-obvious pattern, pitfall, or architectural insight during
+this session, log it for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"investigate","type":"TYPE","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"SOURCE","files":["path/to/relevant/file"]}'
+```
+
+**Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
+(user stated), `architecture` (structural decision), `tool` (library/framework insight).
+
+**Sources:** `observed` (you found this in the code), `user-stated` (user told you),
+`inferred` (AI deduction), `cross-model` (both Claude and Codex agree).
+
+**Confidence:** 1-10. Be honest. An observed pattern you verified in the code is 8-9.
+An inference you're not sure about is 4-5. A user preference they explicitly stated is 10.
+
+**files:** Include the specific file paths this learning references. This enables
+staleness detection: if those files are later deleted, the learning can be flagged.
+
+**Only log genuine discoveries.** Don't log obvious things. Don't log things the user
+already knows. A good test: would this insight save time in a future session? If yes, log it.
+
 ---
 
 ## Important Rules

investigate/SKILL.md.tmpl

@@ -60,6 +60,8 @@ Gather context before forming any hypothesis.
 
 4. **Reproduce:** Can you trigger the bug deterministically? If not, gather more evidence before proceeding.
 
+{{LEARNINGS_SEARCH}}
+
 Output: **"Root cause hypothesis: ..."** — a specific, testable claim about what is wrong and why.
 
 ---
@@ -183,6 +185,8 @@ Status:          DONE | DONE_WITH_CONCERNS | BLOCKED
 ════════════════════════════════════════
 ```
 
+{{LEARNINGS_LOG}}
+
 ---
 
 ## Important Rules

land-and-deploy/SKILL.md

@@ -58,6 +58,15 @@ for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null
   fi
   break
 done
+# Learnings count
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.jsonl"
+if [ -f "$_LEARN_FILE" ]; then
+  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
+  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+else
+  echo "LEARNINGS: 0"
+fi
 ```
 
 If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not

office-hours/SKILL.md

@@ -66,6 +66,15 @@ for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null
   fi
   break
 done
+# Learnings count
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.jsonl"
+if [ -f "$_LEARN_FILE" ]; then
+  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
+  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+else
+  echo "LEARNINGS: 0"
+fi
 ```
 
 If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
@@ -400,6 +409,44 @@ eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
    ```
    If design docs exist, list them: "Prior designs for this project: [titles + dates]"
 
+## Prior Learnings
+
+Search for relevant learnings from previous sessions:
+
+```bash
+_CROSS_PROJ=$(~/.claude/skills/gstack/bin/gstack-config get cross_project_learnings 2>/dev/null || echo "unset")
+echo "CROSS_PROJECT: $_CROSS_PROJ"
+if [ "$_CROSS_PROJ" = "true" ]; then
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 --cross-project 2>/dev/null || true
+else
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 2>/dev/null || true
+fi
+```
+
+If `CROSS_PROJECT` is `unset` (first time): Use AskUserQuestion:
+
+> gstack can search learnings from your other projects on this machine to find
+> patterns that might apply here. This stays local (no data leaves your machine).
+> Recommended for solo developers. Skip if you work on multiple client codebases
+> where cross-contamination would be a concern.
+
+Options:
+- A) Enable cross-project learnings (recommended)
+- B) Keep learnings project-scoped only
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings false`
+
+Then re-run the search with the appropriate flag.
+
+If learnings are found, incorporate them into your analysis. When a review finding
+matches a past learning, display:
+
+**"Prior learning applied: [key] (confidence N/10, from [date])"**
+
+This makes the compounding visible. The user should see that gstack is getting
+smarter on their codebase over time.
+
 5. **Ask: what's your goal with this?** This is a real question, not a formality. The answer determines everything about how the session runs.
 
    Via AskUserQuestion, ask:

office-hours/SKILL.md.tmpl

@@ -53,6 +53,8 @@ Understand the project and the area the user wants to change.
    ```
    If design docs exist, list them: "Prior designs for this project: [titles + dates]"
 
+{{LEARNINGS_SEARCH}}
+
 5. **Ask: what's your goal with this?** This is a real question, not a formality. The answer determines everything about how the session runs.
 
    Via AskUserQuestion, ask:

plan-ceo-review/SKILL.md

@@ -64,6 +64,15 @@ for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null
   fi
   break
 done
+# Learnings count
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.jsonl"
+if [ -f "$_LEARN_FILE" ]; then
+  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
+  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+else
+  echo "LEARNINGS: 0"
+fi
 ```
 
 If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
@@ -603,6 +612,44 @@ Run the three-layer synthesis:
 
 Feed into the Premise Challenge (0A) and Dream State Mapping (0C). If you find a eureka moment, surface it during the Expansion opt-in ceremony as a differentiation opportunity. Log it (see preamble).
 
+## Prior Learnings
+
+Search for relevant learnings from previous sessions:
+
+```bash
+_CROSS_PROJ=$(~/.claude/skills/gstack/bin/gstack-config get cross_project_learnings 2>/dev/null || echo "unset")
+echo "CROSS_PROJECT: $_CROSS_PROJ"
+if [ "$_CROSS_PROJ" = "true" ]; then
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 --cross-project 2>/dev/null || true
+else
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 2>/dev/null || true
+fi
+```
+
+If `CROSS_PROJECT` is `unset` (first time): Use AskUserQuestion:
+
+> gstack can search learnings from your other projects on this machine to find
+> patterns that might apply here. This stays local (no data leaves your machine).
+> Recommended for solo developers. Skip if you work on multiple client codebases
+> where cross-contamination would be a concern.
+
+Options:
+- A) Enable cross-project learnings (recommended)
+- B) Keep learnings project-scoped only
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings false`
+
+Then re-run the search with the appropriate flag.
+
+If learnings are found, incorporate them into your analysis. When a review finding
+matches a past learning, display:
+
+**"Prior learning applied: [key] (confidence N/10, from [date])"**
+
+This makes the compounding visible. The user should see that gstack is getting
+smarter on their codebase over time.
+
 ## Step 0: Nuclear Scope Challenge + Mode Selection
 
 ### 0A. Premise Challenge

plan-ceo-review/SKILL.md.tmpl

@@ -191,6 +191,8 @@ Run the three-layer synthesis:
 
 Feed into the Premise Challenge (0A) and Dream State Mapping (0C). If you find a eureka moment, surface it during the Expansion opt-in ceremony as a differentiation opportunity. Log it (see preamble).
 
+{{LEARNINGS_SEARCH}}
+
 ## Step 0: Nuclear Scope Challenge + Mode Selection
 
 ### 0A. Premise Challenge

plan-design-review/SKILL.md

@@ -62,6 +62,15 @@ for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null
   fi
   break
 done
+# Learnings count
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.jsonl"
+if [ -f "$_LEARN_FILE" ]; then
+  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
+  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+else
+  echo "LEARNINGS: 0"
+fi
 ```
 
 If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not

plan-eng-review/SKILL.md

@@ -63,6 +63,15 @@ for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null
   fi
   break
 done
+# Learnings count
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.jsonl"
+if [ -f "$_LEARN_FILE" ]; then
+  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
+  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+else
+  echo "LEARNINGS: 0"
+fi
 ```
 
 If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
@@ -485,6 +494,44 @@ Always work through the full interactive review: one section at a time (Architec
 
 ## Review Sections (after scope is agreed)
 
+## Prior Learnings
+
+Search for relevant learnings from previous sessions:
+
+```bash
+_CROSS_PROJ=$(~/.claude/skills/gstack/bin/gstack-config get cross_project_learnings 2>/dev/null || echo "unset")
+echo "CROSS_PROJECT: $_CROSS_PROJ"
+if [ "$_CROSS_PROJ" = "true" ]; then
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 --cross-project 2>/dev/null || true
+else
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 2>/dev/null || true
+fi
+```
+
+If `CROSS_PROJECT` is `unset` (first time): Use AskUserQuestion:
+
+> gstack can search learnings from your other projects on this machine to find
+> patterns that might apply here. This stays local (no data leaves your machine).
+> Recommended for solo developers. Skip if you work on multiple client codebases
+> where cross-contamination would be a concern.
+
+Options:
+- A) Enable cross-project learnings (recommended)
+- B) Keep learnings project-scoped only
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings false`
+
+Then re-run the search with the appropriate flag.
+
+If learnings are found, incorporate them into your analysis. When a review finding
+matches a past learning, display:
+
+**"Prior learning applied: [key] (confidence N/10, from [date])"**
+
+This makes the compounding visible. The user should see that gstack is getting
+smarter on their codebase over time.
+
 ### 1. Architecture review
 Evaluate:
 * Overall system design and component boundaries.
@@ -498,6 +545,31 @@ Evaluate:
 
 **STOP.** For each issue found in this section, call AskUserQuestion individually. One issue per call. Present options, state your recommendation, explain WHY. Do NOT batch multiple issues into one AskUserQuestion. Only proceed to the next section after ALL issues in this section are resolved.
 
+## Confidence Calibration
+
+Every finding MUST include a confidence score (1-10):
+
+| Score | Meaning | Display rule |
+|-------|---------|-------------|
+| 9-10 | Verified by reading specific code. Concrete bug or exploit demonstrated. | Show normally |
+| 7-8 | High confidence pattern match. Very likely correct. | Show normally |
+| 5-6 | Moderate. Could be a false positive. | Show with caveat: "Medium confidence, verify this is actually an issue" |
+| 3-4 | Low confidence. Pattern is suspicious but may be fine. | Suppress from main report. Include in appendix only. |
+| 1-2 | Speculation. | Only report if severity would be P0. |
+
+**Finding format:**
+
+\`[SEVERITY] (confidence: N/10) file:line — description\`
+
+Example:
+\`[P1] (confidence: 9/10) app/models/user.rb:42 — SQL injection via string interpolation in where clause\`
+\`[P2] (confidence: 5/10) app/controllers/api/v1/users_controller.rb:18 — Possible N+1 query, verify with production logs\`
+
+**Calibration learning:** If you report a finding with confidence < 7 and the user
+confirms it IS a real issue, that is a calibration event. Your initial confidence was
+too low. Log the corrected pattern as a learning so future reviews catch it with
+higher confidence.
+
 ### 2. Code quality review
 Evaluate:
 * Code organization and module structure.

plan-eng-review/SKILL.md.tmpl

@@ -110,6 +110,8 @@ Always work through the full interactive review: one section at a time (Architec
 
 ## Review Sections (after scope is agreed)
 
+{{LEARNINGS_SEARCH}}
+
 ### 1. Architecture review
 Evaluate:
 * Overall system design and component boundaries.
@@ -123,6 +125,8 @@ Evaluate:
 
 **STOP.** For each issue found in this section, call AskUserQuestion individually. One issue per call. Present options, state your recommendation, explain WHY. Do NOT batch multiple issues into one AskUserQuestion. Only proceed to the next section after ALL issues in this section are resolved.
 
+{{CONFIDENCE_CALIBRATION}}
+
 ### 2. Code quality review
 Evaluate:
 * Code organization and module structure.

qa-only/SKILL.md

@@ -59,6 +59,15 @@ for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null
   fi
   break
 done
+# Learnings count
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.jsonl"
+if [ -f "$_LEARN_FILE" ]; then
+  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
+  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+else
+  echo "LEARNINGS: 0"
+fi
 ```
 
 If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not

qa/SKILL.md

@@ -65,6 +65,15 @@ for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null
   fi
   break
 done
+# Learnings count
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.jsonl"
+if [ -f "$_LEARN_FILE" ]; then
+  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
+  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+else
+  echo "LEARNINGS: 0"
+fi
 ```
 
 If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not

retro/SKILL.md

@@ -59,6 +59,15 @@ for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null
   fi
   break
 done
+# Learnings count
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.jsonl"
+if [ -f "$_LEARN_FILE" ]; then
+  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
+  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+else
+  echo "LEARNINGS: 0"
+fi
 ```
 
 If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
@@ -621,6 +630,30 @@ For each contributor (including the current user), compute:
 
 **If there are Co-Authored-By trailers:** Parse `Co-Authored-By:` lines in commit messages. Credit those authors for the commit alongside the primary author. Note AI co-authors (e.g., `noreply@anthropic.com`) but do not include them as team members — instead, track "AI-assisted commits" as a separate metric.
 
+## Capture Learnings
+
+If you discovered a non-obvious pattern, pitfall, or architectural insight during
+this session, log it for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"retro","type":"TYPE","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"SOURCE","files":["path/to/relevant/file"]}'
+```
+
+**Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
+(user stated), `architecture` (structural decision), `tool` (library/framework insight).
+
+**Sources:** `observed` (you found this in the code), `user-stated` (user told you),
+`inferred` (AI deduction), `cross-model` (both Claude and Codex agree).
+
+**Confidence:** 1-10. Be honest. An observed pattern you verified in the code is 8-9.
+An inference you're not sure about is 4-5. A user preference they explicitly stated is 10.
+
+**files:** Include the specific file paths this learning references. This enables
+staleness detection: if those files are later deleted, the learning can be flagged.
+
+**Only log genuine discoveries.** Don't log obvious things. Don't log things the user
+already knows. A good test: would this insight save time in a future session? If yes, log it.
+
 ### Step 10: Week-over-Week Trends (if window >= 14d)
 
 If the time window is 14 days or more, split into weekly buckets and show trends:

retro/SKILL.md.tmpl

@@ -277,6 +277,8 @@ For each contributor (including the current user), compute:
 
 **If there are Co-Authored-By trailers:** Parse `Co-Authored-By:` lines in commit messages. Credit those authors for the commit alongside the primary author. Note AI co-authors (e.g., `noreply@anthropic.com`) but do not include them as team members — instead, track "AI-assisted commits" as a separate metric.
 
+{{LEARNINGS_LOG}}
+
 ### Step 10: Week-over-Week Trends (if window >= 14d)
 
 If the time window is 14 days or more, split into weekly buckets and show trends:

review/SKILL.md

@@ -62,6 +62,15 @@ for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null
   fi
   break
 done
+# Learnings count
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.jsonl"
+if [ -f "$_LEARN_FILE" ]; then
+  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
+  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+else
+  echo "LEARNINGS: 0"
+fi
 ```
 
 If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
@@ -582,6 +591,44 @@ Run `git diff origin/<base>` to get the full diff. This includes both committed
 
 ---
 
+## Prior Learnings
+
+Search for relevant learnings from previous sessions:
+
+```bash
+_CROSS_PROJ=$(~/.claude/skills/gstack/bin/gstack-config get cross_project_learnings 2>/dev/null || echo "unset")
+echo "CROSS_PROJECT: $_CROSS_PROJ"
+if [ "$_CROSS_PROJ" = "true" ]; then
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 --cross-project 2>/dev/null || true
+else
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 2>/dev/null || true
+fi
+```
+
+If `CROSS_PROJECT` is `unset` (first time): Use AskUserQuestion:
+
+> gstack can search learnings from your other projects on this machine to find
+> patterns that might apply here. This stays local (no data leaves your machine).
+> Recommended for solo developers. Skip if you work on multiple client codebases
+> where cross-contamination would be a concern.
+
+Options:
+- A) Enable cross-project learnings (recommended)
+- B) Keep learnings project-scoped only
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings false`
+
+Then re-run the search with the appropriate flag.
+
+If learnings are found, incorporate them into your analysis. When a review finding
+matches a past learning, display:
+
+**"Prior learning applied: [key] (confidence N/10, from [date])"**
+
+This makes the compounding visible. The user should see that gstack is getting
+smarter on their codebase over time.
+
 ## Step 4: Two-pass review
 
 Apply the checklist against the diff in two passes:
@@ -600,6 +647,31 @@ Takes seconds, prevents recommending outdated patterns. If WebSearch is unavaila
 
 Follow the output format specified in the checklist. Respect the suppressions — do NOT flag items listed in the "DO NOT flag" section.
 
+## Confidence Calibration
+
+Every finding MUST include a confidence score (1-10):
+
+| Score | Meaning | Display rule |
+|-------|---------|-------------|
+| 9-10 | Verified by reading specific code. Concrete bug or exploit demonstrated. | Show normally |
+| 7-8 | High confidence pattern match. Very likely correct. | Show normally |
+| 5-6 | Moderate. Could be a false positive. | Show with caveat: "Medium confidence, verify this is actually an issue" |
+| 3-4 | Low confidence. Pattern is suspicious but may be fine. | Suppress from main report. Include in appendix only. |
+| 1-2 | Speculation. | Only report if severity would be P0. |
+
+**Finding format:**
+
+\`[SEVERITY] (confidence: N/10) file:line — description\`
+
+Example:
+\`[P1] (confidence: 9/10) app/models/user.rb:42 — SQL injection via string interpolation in where clause\`
+\`[P2] (confidence: 5/10) app/controllers/api/v1/users_controller.rb:18 — Possible N+1 query, verify with production logs\`
+
+**Calibration learning:** If you report a finding with confidence < 7 and the user
+confirms it IS a real issue, that is a calibration event. Your initial confidence was
+too low. Log the corrected pattern as a learning so future reviews catch it with
+higher confidence.
+
 ---
 
 ## Step 4.5: Design Review (conditional)
@@ -1127,6 +1199,30 @@ Substitute:
 - `informational` = remaining unresolved informational findings
 - `COMMIT` = output of `git rev-parse --short HEAD`
 
+## Capture Learnings
+
+If you discovered a non-obvious pattern, pitfall, or architectural insight during
+this session, log it for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"review","type":"TYPE","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"SOURCE","files":["path/to/relevant/file"]}'
+```
+
+**Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
+(user stated), `architecture` (structural decision), `tool` (library/framework insight).
+
+**Sources:** `observed` (you found this in the code), `user-stated` (user told you),
+`inferred` (AI deduction), `cross-model` (both Claude and Codex agree).
+
+**Confidence:** 1-10. Be honest. An observed pattern you verified in the code is 8-9.
+An inference you're not sure about is 4-5. A user preference they explicitly stated is 10.
+
+**files:** Include the specific file paths this learning references. This enables
+staleness detection: if those files are later deleted, the learning can be flagged.
+
+**Only log genuine discoveries.** Don't log obvious things. Don't log things the user
+already knows. A good test: would this insight save time in a future session? If yes, log it.
+
 If the review exits early before a real review completes (for example, no diff against the base branch), do **not** write this entry.
 
 ## Important Rules

review/SKILL.md.tmpl

@@ -104,6 +104,8 @@ Run `git diff origin/<base>` to get the full diff. This includes both committed
 
 ---
 
+{{LEARNINGS_SEARCH}}
+
 ## Step 4: Two-pass review
 
 Apply the checklist against the diff in two passes:
@@ -122,6 +124,8 @@ Takes seconds, prevents recommending outdated patterns. If WebSearch is unavaila
 
 Follow the output format specified in the checklist. Respect the suppressions — do NOT flag items listed in the "DO NOT flag" section.
 
+{{CONFIDENCE_CALIBRATION}}
+
 ---
 
 ## Step 4.5: Design Review (conditional)
@@ -273,6 +277,8 @@ Substitute:
 - `informational` = remaining unresolved informational findings
 - `COMMIT` = output of `git rev-parse --short HEAD`
 
+{{LEARNINGS_LOG}}
+
 If the review exits early before a real review completes (for example, no diff against the base branch), do **not** write this entry.
 
 ## Important Rules

setup-browser-cookies/SKILL.md

@@ -56,6 +56,15 @@ for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null
   fi
   break
 done
+# Learnings count
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.jsonl"
+if [ -f "$_LEARN_FILE" ]; then
+  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
+  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+else
+  echo "LEARNINGS: 0"
+fi
 ```
 
 If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not

setup-deploy/SKILL.md

@@ -62,6 +62,15 @@ for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null
   fi
   break
 done
+# Learnings count
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.jsonl"
+if [ -f "$_LEARN_FILE" ]; then
+  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
+  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+else
+  echo "LEARNINGS: 0"
+fi
 ```
 
 If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not

ship/SKILL.md

@@ -60,6 +60,15 @@ for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null
   fi
   break
 done
+# Learnings count
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.jsonl"
+if [ -f "$_LEARN_FILE" ]; then
+  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
+  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+else
+  echo "LEARNINGS: 0"
+fi
 ```
 
 If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
@@ -1318,6 +1327,44 @@ Add a `## Verification Results` section to the PR body (Step 8):
 - If verification ran: summary of results (N PASS, M FAIL, K SKIPPED)
 - If skipped: reason for skipping (no plan, no server, no verification section)
 
+## Prior Learnings
+
+Search for relevant learnings from previous sessions:
+
+```bash
+_CROSS_PROJ=$(~/.claude/skills/gstack/bin/gstack-config get cross_project_learnings 2>/dev/null || echo "unset")
+echo "CROSS_PROJECT: $_CROSS_PROJ"
+if [ "$_CROSS_PROJ" = "true" ]; then
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 --cross-project 2>/dev/null || true
+else
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 2>/dev/null || true
+fi
+```
+
+If `CROSS_PROJECT` is `unset` (first time): Use AskUserQuestion:
+
+> gstack can search learnings from your other projects on this machine to find
+> patterns that might apply here. This stays local (no data leaves your machine).
+> Recommended for solo developers. Skip if you work on multiple client codebases
+> where cross-contamination would be a concern.
+
+Options:
+- A) Enable cross-project learnings (recommended)
+- B) Keep learnings project-scoped only
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings false`
+
+Then re-run the search with the appropriate flag.
+
+If learnings are found, incorporate them into your analysis. When a review finding
+matches a past learning, display:
+
+**"Prior learning applied: [key] (confidence N/10, from [date])"**
+
+This makes the compounding visible. The user should see that gstack is getting
+smarter on their codebase over time.
+
 ---
 
 ## Step 3.5: Pre-Landing Review
@@ -1332,6 +1379,31 @@ Review the diff for structural issues that tests don't catch.
    - **Pass 1 (CRITICAL):** SQL & Data Safety, LLM Output Trust Boundary
    - **Pass 2 (INFORMATIONAL):** All remaining categories
 
+## Confidence Calibration
+
+Every finding MUST include a confidence score (1-10):
+
+| Score | Meaning | Display rule |
+|-------|---------|-------------|
+| 9-10 | Verified by reading specific code. Concrete bug or exploit demonstrated. | Show normally |
+| 7-8 | High confidence pattern match. Very likely correct. | Show normally |
+| 5-6 | Moderate. Could be a false positive. | Show with caveat: "Medium confidence, verify this is actually an issue" |
+| 3-4 | Low confidence. Pattern is suspicious but may be fine. | Suppress from main report. Include in appendix only. |
+| 1-2 | Speculation. | Only report if severity would be P0. |
+
+**Finding format:**
+
+\`[SEVERITY] (confidence: N/10) file:line — description\`
+
+Example:
+\`[P1] (confidence: 9/10) app/models/user.rb:42 — SQL injection via string interpolation in where clause\`
+\`[P2] (confidence: 5/10) app/controllers/api/v1/users_controller.rb:18 — Possible N+1 query, verify with production logs\`
+
+**Calibration learning:** If you report a finding with confidence < 7 and the user
+confirms it IS a real issue, that is a calibration event. Your initial confidence was
+too low. Log the corrected pattern as a learning so future reviews catch it with
+higher confidence.
+
 ## Design Review (conditional, diff-scoped)
 
 Check if the diff touches frontend files using `gstack-diff-scope`:
@@ -1599,6 +1671,30 @@ High-confidence findings (agreed on by multiple sources) should be prioritized f
 
 ---
 
+## Capture Learnings
+
+If you discovered a non-obvious pattern, pitfall, or architectural insight during
+this session, log it for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"ship","type":"TYPE","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"SOURCE","files":["path/to/relevant/file"]}'
+```
+
+**Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
+(user stated), `architecture` (structural decision), `tool` (library/framework insight).
+
+**Sources:** `observed` (you found this in the code), `user-stated` (user told you),
+`inferred` (AI deduction), `cross-model` (both Claude and Codex agree).
+
+**Confidence:** 1-10. Be honest. An observed pattern you verified in the code is 8-9.
+An inference you're not sure about is 4-5. A user preference they explicitly stated is 10.
+
+**files:** Include the specific file paths this learning references. This enables
+staleness detection: if those files are later deleted, the learning can be flagged.
+
+**Only log genuine discoveries.** Don't log obvious things. Don't log things the user
+already knows. A good test: would this insight save time in a future session? If yes, log it.
+
 ## Step 4: Version bump (auto-decide)
 
 1. Read the current `VERSION` file (4-digit format: `MAJOR.MINOR.PATCH.MICRO`)

ship/SKILL.md.tmpl

@@ -226,6 +226,8 @@ If multiple suites need to run, run them sequentially (each needs a test lane).
 
 {{PLAN_VERIFICATION_EXEC}}
 
+{{LEARNINGS_SEARCH}}
+
 ---
 
 ## Step 3.5: Pre-Landing Review
@@ -240,6 +242,8 @@ Review the diff for structural issues that tests don't catch.
    - **Pass 1 (CRITICAL):** SQL & Data Safety, LLM Output Trust Boundary
    - **Pass 2 (INFORMATIONAL):** All remaining categories
 
+{{CONFIDENCE_CALIBRATION}}
+
 {{DESIGN_REVIEW_LITE}}
 
    Include any design findings alongside the code review findings. They follow the same Fix-First flow below.
@@ -316,6 +320,8 @@ For each classified comment:
 
 {{ADVERSARIAL_STEP}}
 
+{{LEARNINGS_LOG}}
+
 ## Step 4: Version bump (auto-decide)
 
 1. Read the current `VERSION` file (4-digit format: `MAJOR.MINOR.PATCH.MICRO`)