diff --git a/.agents/skills/gstack-autoplan/agents/openai.yaml b/.agents/skills/gstack-autoplan/agents/openai.yaml new file mode 100644 index 00000000..28794c1a --- /dev/null +++ b/.agents/skills/gstack-autoplan/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack-autoplan" + short_description: "Auto-review pipeline — reads the full CEO, design, and eng review skills from disk and runs them sequentially with..." + default_prompt: "Use gstack-autoplan for this task." +policy: + allow_implicit_invocation: true diff --git a/.agents/skills/gstack-benchmark/agents/openai.yaml b/.agents/skills/gstack-benchmark/agents/openai.yaml new file mode 100644 index 00000000..4df54f31 --- /dev/null +++ b/.agents/skills/gstack-benchmark/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack-benchmark" + short_description: "Performance regression detection using the browse daemon. Establishes baselines for page load times, Core Web..." + default_prompt: "Use gstack-benchmark for this task." +policy: + allow_implicit_invocation: true diff --git a/.agents/skills/gstack-browse/agents/openai.yaml b/.agents/skills/gstack-browse/agents/openai.yaml new file mode 100644 index 00000000..851f8083 --- /dev/null +++ b/.agents/skills/gstack-browse/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack-browse" + short_description: "Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page..." + default_prompt: "Use gstack-browse for this task." +policy: + allow_implicit_invocation: true diff --git a/.agents/skills/gstack-canary/agents/openai.yaml b/.agents/skills/gstack-canary/agents/openai.yaml new file mode 100644 index 00000000..e51e4231 --- /dev/null +++ b/.agents/skills/gstack-canary/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack-canary" + short_description: "Post-deploy canary monitoring. Watches the live app for console errors, performance regressions, and page failures..." + default_prompt: "Use gstack-canary for this task." +policy: + allow_implicit_invocation: true diff --git a/.agents/skills/gstack-careful/agents/openai.yaml b/.agents/skills/gstack-careful/agents/openai.yaml new file mode 100644 index 00000000..f470fcaa --- /dev/null +++ b/.agents/skills/gstack-careful/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack-careful" + short_description: "Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl..." + default_prompt: "Use gstack-careful for this task." +policy: + allow_implicit_invocation: true diff --git a/.agents/skills/gstack-cso/agents/openai.yaml b/.agents/skills/gstack-cso/agents/openai.yaml new file mode 100644 index 00000000..d9224815 --- /dev/null +++ b/.agents/skills/gstack-cso/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack-cso" + short_description: "Chief Security Officer mode. Performs OWASP Top 10 audit, STRIDE threat modeling, attack surface analysis, auth flow..." + default_prompt: "Use gstack-cso for this task." +policy: + allow_implicit_invocation: true diff --git a/.agents/skills/gstack-design-consultation/agents/openai.yaml b/.agents/skills/gstack-design-consultation/agents/openai.yaml new file mode 100644 index 00000000..3af30a8a --- /dev/null +++ b/.agents/skills/gstack-design-consultation/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack-design-consultation" + short_description: "Design consultation: understands your product, researches the landscape, proposes a complete design system..." + default_prompt: "Use gstack-design-consultation for this task." +policy: + allow_implicit_invocation: true diff --git a/.agents/skills/gstack-design-review/agents/openai.yaml b/.agents/skills/gstack-design-review/agents/openai.yaml new file mode 100644 index 00000000..473554d3 --- /dev/null +++ b/.agents/skills/gstack-design-review/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack-design-review" + short_description: "Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow..." + default_prompt: "Use gstack-design-review for this task." +policy: + allow_implicit_invocation: true diff --git a/.agents/skills/gstack-document-release/agents/openai.yaml b/.agents/skills/gstack-document-release/agents/openai.yaml new file mode 100644 index 00000000..453bf5bd --- /dev/null +++ b/.agents/skills/gstack-document-release/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack-document-release" + short_description: "Post-ship documentation update. Reads all project docs, cross-references the diff, updates..." + default_prompt: "Use gstack-document-release for this task." +policy: + allow_implicit_invocation: true diff --git a/.agents/skills/gstack-freeze/agents/openai.yaml b/.agents/skills/gstack-freeze/agents/openai.yaml new file mode 100644 index 00000000..0b643f68 --- /dev/null +++ b/.agents/skills/gstack-freeze/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack-freeze" + short_description: "Restrict file edits to a specific directory for the session. Blocks Edit and Write outside the allowed path. Use..." + default_prompt: "Use gstack-freeze for this task." +policy: + allow_implicit_invocation: true diff --git a/.agents/skills/gstack-guard/agents/openai.yaml b/.agents/skills/gstack-guard/agents/openai.yaml new file mode 100644 index 00000000..c7fe7902 --- /dev/null +++ b/.agents/skills/gstack-guard/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack-guard" + short_description: "Full safety mode: destructive command warnings + directory-scoped edits. Combines /careful (warns before rm -rf,..." + default_prompt: "Use gstack-guard for this task." +policy: + allow_implicit_invocation: true diff --git a/.agents/skills/gstack-investigate/agents/openai.yaml b/.agents/skills/gstack-investigate/agents/openai.yaml new file mode 100644 index 00000000..3c778414 --- /dev/null +++ b/.agents/skills/gstack-investigate/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack-investigate" + short_description: "Systematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron..." + default_prompt: "Use gstack-investigate for this task." +policy: + allow_implicit_invocation: true diff --git a/.agents/skills/gstack-land-and-deploy/agents/openai.yaml b/.agents/skills/gstack-land-and-deploy/agents/openai.yaml new file mode 100644 index 00000000..73a9d706 --- /dev/null +++ b/.agents/skills/gstack-land-and-deploy/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack-land-and-deploy" + short_description: "Land and deploy workflow. Merges the PR, waits for CI and deploy, verifies production health via canary checks...." + default_prompt: "Use gstack-land-and-deploy for this task." +policy: + allow_implicit_invocation: true diff --git a/.agents/skills/gstack-office-hours/agents/openai.yaml b/.agents/skills/gstack-office-hours/agents/openai.yaml new file mode 100644 index 00000000..51ac282d --- /dev/null +++ b/.agents/skills/gstack-office-hours/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack-office-hours" + short_description: "YC Office Hours — two modes. Startup mode: six forcing questions that expose demand reality, status quo, desperate..." + default_prompt: "Use gstack-office-hours for this task." +policy: + allow_implicit_invocation: true diff --git a/.agents/skills/gstack-plan-ceo-review/agents/openai.yaml b/.agents/skills/gstack-plan-ceo-review/agents/openai.yaml new file mode 100644 index 00000000..6927e353 --- /dev/null +++ b/.agents/skills/gstack-plan-ceo-review/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack-plan-ceo-review" + short_description: "CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when..." + default_prompt: "Use gstack-plan-ceo-review for this task." +policy: + allow_implicit_invocation: true diff --git a/.agents/skills/gstack-plan-design-review/agents/openai.yaml b/.agents/skills/gstack-plan-design-review/agents/openai.yaml new file mode 100644 index 00000000..d3948212 --- /dev/null +++ b/.agents/skills/gstack-plan-design-review/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack-plan-design-review" + short_description: "Designer's eye plan review — interactive, like CEO and Eng review. Rates each design dimension 0-10, explains what..." + default_prompt: "Use gstack-plan-design-review for this task." +policy: + allow_implicit_invocation: true diff --git a/.agents/skills/gstack-plan-eng-review/agents/openai.yaml b/.agents/skills/gstack-plan-eng-review/agents/openai.yaml new file mode 100644 index 00000000..96eefa75 --- /dev/null +++ b/.agents/skills/gstack-plan-eng-review/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack-plan-eng-review" + short_description: "Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test..." + default_prompt: "Use gstack-plan-eng-review for this task." +policy: + allow_implicit_invocation: true diff --git a/.agents/skills/gstack-qa-only/agents/openai.yaml b/.agents/skills/gstack-qa-only/agents/openai.yaml new file mode 100644 index 00000000..afbd1ee3 --- /dev/null +++ b/.agents/skills/gstack-qa-only/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack-qa-only" + short_description: "Report-only QA testing. Systematically tests a web application and produces a structured report with health score,..." + default_prompt: "Use gstack-qa-only for this task." +policy: + allow_implicit_invocation: true diff --git a/.agents/skills/gstack-qa/agents/openai.yaml b/.agents/skills/gstack-qa/agents/openai.yaml new file mode 100644 index 00000000..6d940241 --- /dev/null +++ b/.agents/skills/gstack-qa/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack-qa" + short_description: "Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source..." + default_prompt: "Use gstack-qa for this task." +policy: + allow_implicit_invocation: true diff --git a/.agents/skills/gstack-retro/agents/openai.yaml b/.agents/skills/gstack-retro/agents/openai.yaml new file mode 100644 index 00000000..dbf45f2d --- /dev/null +++ b/.agents/skills/gstack-retro/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack-retro" + short_description: "Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent..." + default_prompt: "Use gstack-retro for this task." +policy: + allow_implicit_invocation: true diff --git a/.agents/skills/gstack-review/agents/openai.yaml b/.agents/skills/gstack-review/agents/openai.yaml new file mode 100644 index 00000000..ba44751c --- /dev/null +++ b/.agents/skills/gstack-review/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack-review" + short_description: "Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations,..." + default_prompt: "Use gstack-review for this task." +policy: + allow_implicit_invocation: true diff --git a/.agents/skills/gstack-setup-browser-cookies/agents/openai.yaml b/.agents/skills/gstack-setup-browser-cookies/agents/openai.yaml new file mode 100644 index 00000000..5cab5186 --- /dev/null +++ b/.agents/skills/gstack-setup-browser-cookies/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack-setup-browser-cookies" + short_description: "Import cookies from your real browser (Comet, Chrome, Arc, Brave, Edge) into the headless browse session. Opens an..." + default_prompt: "Use gstack-setup-browser-cookies for this task." +policy: + allow_implicit_invocation: true diff --git a/.agents/skills/gstack-setup-deploy/agents/openai.yaml b/.agents/skills/gstack-setup-deploy/agents/openai.yaml new file mode 100644 index 00000000..b666712e --- /dev/null +++ b/.agents/skills/gstack-setup-deploy/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack-setup-deploy" + short_description: "Configure deployment settings for /land-and-deploy. Detects your deploy platform (Fly.io, Render, Vercel, Netlify,..." + default_prompt: "Use gstack-setup-deploy for this task." +policy: + allow_implicit_invocation: true diff --git a/.agents/skills/gstack-ship/agents/openai.yaml b/.agents/skills/gstack-ship/agents/openai.yaml new file mode 100644 index 00000000..537ab155 --- /dev/null +++ b/.agents/skills/gstack-ship/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack-ship" + short_description: "Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push,..." + default_prompt: "Use gstack-ship for this task." +policy: + allow_implicit_invocation: true diff --git a/.agents/skills/gstack-unfreeze/agents/openai.yaml b/.agents/skills/gstack-unfreeze/agents/openai.yaml new file mode 100644 index 00000000..93de8da6 --- /dev/null +++ b/.agents/skills/gstack-unfreeze/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack-unfreeze" + short_description: "Clear the freeze boundary set by /freeze, allowing edits to all directories again. Use when you want to widen edit..." + default_prompt: "Use gstack-unfreeze for this task." +policy: + allow_implicit_invocation: true diff --git a/.agents/skills/gstack-upgrade/agents/openai.yaml b/.agents/skills/gstack-upgrade/agents/openai.yaml new file mode 100644 index 00000000..ca055a01 --- /dev/null +++ b/.agents/skills/gstack-upgrade/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack-upgrade" + short_description: "Upgrade gstack to the latest version. Detects global vs vendored install, runs the upgrade, and shows what's new...." + default_prompt: "Use gstack-upgrade for this task." +policy: + allow_implicit_invocation: true diff --git a/.agents/skills/gstack/agents/openai.yaml b/.agents/skills/gstack/agents/openai.yaml new file mode 100644 index 00000000..ace5b243 --- /dev/null +++ b/.agents/skills/gstack/agents/openai.yaml @@ -0,0 +1,6 @@ +interface: + display_name: "gstack" + short_description: "Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page..." + default_prompt: "Use gstack for this task." +policy: + allow_implicit_invocation: true diff --git a/CHANGELOG.md b/CHANGELOG.md index 89d7bf18..b7105cdf 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,6 +1,6 @@ # Changelog -## [0.11.7.0] - 2026-03-23 — zsh Compatibility Fix +## [0.11.8.0] - 2026-03-23 — zsh Compatibility Fix ### Fixed @@ -10,6 +10,18 @@ - **Regression test for zsh glob safety.** New test verifies all generated SKILL.md files use `find` instead of bare shell globs for `.pending-*` pattern matching. +## [0.11.7.0] - 2026-03-23 — /review → /ship Handoff Fix + +### Fixed + +- **`/review` now satisfies the ship readiness gate.** Previously, running `/review` before `/ship` always showed "NOT CLEARED" because `/review` didn't log its result and `/ship` only looked for `/plan-eng-review`. Now `/review` persists its outcome to the review log, and all dashboards recognize both `/review` (diff-scoped) and `/plan-eng-review` (plan-stage) as valid Eng Review sources. +- **Ship abort prompt now mentions both review options.** When Eng Review is missing, `/ship` suggests "run `/review` or `/plan-eng-review`" instead of only mentioning `/plan-eng-review`. + +### For contributors + +- Based on PR #338 by @malikrohail. DRY improvement per eng review: updated the shared `REVIEW_DASHBOARD` resolver instead of creating a duplicate ship-only resolver. +- 4 new validation tests covering review-log persistence, dashboard propagation, and abort text. + ## [0.11.6.0] - 2026-03-23 — Infrastructure-First Security Audit ### Added diff --git a/VERSION b/VERSION index a9da9632..f3b6bd46 100644 --- a/VERSION +++ b/VERSION @@ -1 +1 @@ -0.11.7.0 +0.11.8.0 diff --git a/agents/openai.yaml b/agents/openai.yaml new file mode 100644 index 00000000..1bb2fd7c --- /dev/null +++ b/agents/openai.yaml @@ -0,0 +1,4 @@ +interface: + display_name: "gstack" + short_description: "Bundle of gstack Codex skills" + default_prompt: "Use $gstack to locate the bundled gstack skills." diff --git a/plan-ceo-review/SKILL.md b/plan-ceo-review/SKILL.md index f7d5c129..a6365fca 100644 --- a/plan-ceo-review/SKILL.md +++ b/plan-ceo-review/SKILL.md @@ -1258,7 +1258,7 @@ 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, plan-design-review, design-review-lite, adversarial-review, codex-review, codex-plan-review). Ignore entries with timestamps older than 7 days. 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. Display: ``` +====================================================================+ @@ -1284,7 +1284,7 @@ Parse the output. Find the most recent entry for each skill (plan-ceo-review, pl - **Outside Voice (optional):** Independent plan review from a different AI model. Offered after all review sections complete in /plan-ceo-review and /plan-eng-review. Falls back to Claude subagent if Codex is unavailable. Never gates shipping. **Verdict logic:** -- **CLEARED**: Eng Review has >= 1 entry within 7 days with status "clean" (or \`skip_eng_review\` is \`true\`) +- **CLEARED**: Eng Review has >= 1 entry within 7 days from either \`review\` or \`plan-eng-review\` with status "clean" (or \`skip_eng_review\` is \`true\`) - **NOT CLEARED**: Eng Review missing, stale (>7 days), or has open issues - CEO, Design, and Codex reviews are shown for context but never block shipping - If \`skip_eng_review\` config is \`true\`, Eng Review shows "SKIPPED (global)" and verdict is CLEARED diff --git a/plan-design-review/SKILL.md b/plan-design-review/SKILL.md index 9e89bd15..e8d9fbbe 100644 --- a/plan-design-review/SKILL.md +++ b/plan-design-review/SKILL.md @@ -764,7 +764,7 @@ 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, plan-design-review, design-review-lite, adversarial-review, codex-review, codex-plan-review). Ignore entries with timestamps older than 7 days. 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. Display: ``` +====================================================================+ @@ -790,7 +790,7 @@ Parse the output. Find the most recent entry for each skill (plan-ceo-review, pl - **Outside Voice (optional):** Independent plan review from a different AI model. Offered after all review sections complete in /plan-ceo-review and /plan-eng-review. Falls back to Claude subagent if Codex is unavailable. Never gates shipping. **Verdict logic:** -- **CLEARED**: Eng Review has >= 1 entry within 7 days with status "clean" (or \`skip_eng_review\` is \`true\`) +- **CLEARED**: Eng Review has >= 1 entry within 7 days from either \`review\` or \`plan-eng-review\` with status "clean" (or \`skip_eng_review\` is \`true\`) - **NOT CLEARED**: Eng Review missing, stale (>7 days), or has open issues - CEO, Design, and Codex reviews are shown for context but never block shipping - If \`skip_eng_review\` config is \`true\`, Eng Review shows "SKIPPED (global)" and verdict is CLEARED diff --git a/plan-eng-review/SKILL.md b/plan-eng-review/SKILL.md index d51a94c8..54d68fcc 100644 --- a/plan-eng-review/SKILL.md +++ b/plan-eng-review/SKILL.md @@ -879,7 +879,7 @@ 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, plan-design-review, design-review-lite, adversarial-review, codex-review, codex-plan-review). Ignore entries with timestamps older than 7 days. 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. Display: ``` +====================================================================+ @@ -905,7 +905,7 @@ Parse the output. Find the most recent entry for each skill (plan-ceo-review, pl - **Outside Voice (optional):** Independent plan review from a different AI model. Offered after all review sections complete in /plan-ceo-review and /plan-eng-review. Falls back to Claude subagent if Codex is unavailable. Never gates shipping. **Verdict logic:** -- **CLEARED**: Eng Review has >= 1 entry within 7 days with status "clean" (or \`skip_eng_review\` is \`true\`) +- **CLEARED**: Eng Review has >= 1 entry within 7 days from either \`review\` or \`plan-eng-review\` with status "clean" (or \`skip_eng_review\` is \`true\`) - **NOT CLEARED**: Eng Review missing, stale (>7 days), or has open issues - CEO, Design, and Codex reviews are shown for context but never block shipping - If \`skip_eng_review\` config is \`true\`, Eng Review shows "SKIPPED (global)" and verdict is CLEARED diff --git a/review/SKILL.md b/review/SKILL.md index 74e141c1..c96f5ca5 100644 --- a/review/SKILL.md +++ b/review/SKILL.md @@ -899,6 +899,27 @@ High-confidence findings (agreed on by multiple sources) should be prioritized f --- +## Step 5.8: Persist Eng Review result + +After all review passes complete, persist the final `/review` outcome so `/ship` can +recognize that Eng Review was run on this branch. + +Run: + +```bash +~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"review","timestamp":"TIMESTAMP","status":"STATUS","issues_found":N,"critical":N,"informational":N,"commit":"COMMIT"}' +``` + +Substitute: +- `TIMESTAMP` = ISO 8601 datetime +- `STATUS` = `"clean"` if there are no remaining unresolved findings after Fix-First handling and adversarial review, otherwise `"issues_found"` +- `issues_found` = total remaining unresolved findings +- `critical` = remaining unresolved critical findings +- `informational` = remaining unresolved informational findings +- `COMMIT` = output of `git rev-parse --short HEAD` + +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 - **Read the FULL diff before commenting.** Do not flag issues already addressed in the diff. diff --git a/review/SKILL.md.tmpl b/review/SKILL.md.tmpl index a33b0fa8..8ae9045a 100644 --- a/review/SKILL.md.tmpl +++ b/review/SKILL.md.tmpl @@ -250,6 +250,27 @@ If no documentation files exist, skip this step silently. {{ADVERSARIAL_STEP}} +## Step 5.8: Persist Eng Review result + +After all review passes complete, persist the final `/review` outcome so `/ship` can +recognize that Eng Review was run on this branch. + +Run: + +```bash +~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"review","timestamp":"TIMESTAMP","status":"STATUS","issues_found":N,"critical":N,"informational":N,"commit":"COMMIT"}' +``` + +Substitute: +- `TIMESTAMP` = ISO 8601 datetime +- `STATUS` = `"clean"` if there are no remaining unresolved findings after Fix-First handling and adversarial review, otherwise `"issues_found"` +- `issues_found` = total remaining unresolved findings +- `critical` = remaining unresolved critical findings +- `informational` = remaining unresolved informational findings +- `COMMIT` = output of `git rev-parse --short HEAD` + +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 - **Read the FULL diff before commenting.** Do not flag issues already addressed in the diff. diff --git a/scripts/gen-skill-docs.ts b/scripts/gen-skill-docs.ts index 1a177421..06e78099 100644 --- a/scripts/gen-skill-docs.ts +++ b/scripts/gen-skill-docs.ts @@ -20,6 +20,7 @@ const DRY_RUN = process.argv.includes('--dry-run'); // ─── Template Context ─────────────────────────────────────── type Host = 'claude' | 'codex'; +const OPENAI_SHORT_DESCRIPTION_LIMIT = 120; const HOST_ARG = process.argv.find(a => a.startsWith('--host')); const HOST: Host = (() => { @@ -1312,7 +1313,7 @@ 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, plan-design-review, design-review-lite, adversarial-review, codex-review, codex-plan-review). Ignore entries with timestamps older than 7 days. 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. Display: \`\`\` +====================================================================+ @@ -1338,7 +1339,7 @@ Parse the output. Find the most recent entry for each skill (plan-ceo-review, pl - **Outside Voice (optional):** Independent plan review from a different AI model. Offered after all review sections complete in /plan-ceo-review and /plan-eng-review. Falls back to Claude subagent if Codex is unavailable. Never gates shipping. **Verdict logic:** -- **CLEARED**: Eng Review has >= 1 entry within 7 days with status "clean" (or \\\`skip_eng_review\\\` is \\\`true\\\`) +- **CLEARED**: Eng Review has >= 1 entry within 7 days from either \\\`review\\\` or \\\`plan-eng-review\\\` with status "clean" (or \\\`skip_eng_review\\\` is \\\`true\\\`) - **NOT CLEARED**: Eng Review missing, stale (>7 days), or has open issues - CEO, Design, and Codex reviews are shown for context but never block shipping - If \\\`skip_eng_review\\\` config is \\\`true\\\`, Eng Review shows "SKIPPED (global)" and verdict is CLEARED @@ -2835,6 +2836,65 @@ function codexSkillName(skillDir: string): string { return `gstack-${skillDir}`; } +function extractNameAndDescription(content: string): { name: string; description: string } { + const fmStart = content.indexOf('---\n'); + if (fmStart !== 0) return { name: '', description: '' }; + const fmEnd = content.indexOf('\n---', fmStart + 4); + if (fmEnd === -1) return { name: '', description: '' }; + + const frontmatter = content.slice(fmStart + 4, fmEnd); + const nameMatch = frontmatter.match(/^name:\s*(.+)$/m); + const name = nameMatch ? nameMatch[1].trim() : ''; + + let description = ''; + const lines = frontmatter.split('\n'); + let inDescription = false; + const descLines: string[] = []; + for (const line of lines) { + if (line.match(/^description:\s*\|?\s*$/)) { + inDescription = true; + continue; + } + if (line.match(/^description:\s*\S/)) { + description = line.replace(/^description:\s*/, '').trim(); + break; + } + if (inDescription) { + if (line === '' || line.match(/^\s/)) { + descLines.push(line.replace(/^ /, '')); + } else { + break; + } + } + } + if (descLines.length > 0) { + description = descLines.join('\n').trim(); + } + + return { name, description }; +} + +function condenseOpenAIShortDescription(description: string): string { + const firstParagraph = description.split(/\n\s*\n/)[0] || description; + const collapsed = firstParagraph.replace(/\s+/g, ' ').trim(); + if (collapsed.length <= OPENAI_SHORT_DESCRIPTION_LIMIT) return collapsed; + + const truncated = collapsed.slice(0, OPENAI_SHORT_DESCRIPTION_LIMIT - 3); + const lastSpace = truncated.lastIndexOf(' '); + const safe = lastSpace > 40 ? truncated.slice(0, lastSpace) : truncated; + return `${safe}...`; +} + +function generateOpenAIYaml(displayName: string, shortDescription: string): string { + return `interface: + display_name: ${JSON.stringify(displayName)} + short_description: ${JSON.stringify(shortDescription)} + default_prompt: ${JSON.stringify(`Use ${displayName} for this task.`)} +policy: + allow_implicit_invocation: true +`; +} + /** * Transform frontmatter for Codex: keep only name + description. * Strips allowed-tools, hooks, version, and all other fields. @@ -2843,48 +2903,12 @@ function codexSkillName(skillDir: string): string { function transformFrontmatter(content: string, host: Host): string { if (host === 'claude') return content; - // Find frontmatter boundaries const fmStart = content.indexOf('---\n'); - if (fmStart !== 0) return content; // frontmatter must be at the start + if (fmStart !== 0) return content; const fmEnd = content.indexOf('\n---', fmStart + 4); if (fmEnd === -1) return content; - - const frontmatter = content.slice(fmStart + 4, fmEnd); const body = content.slice(fmEnd + 4); // includes the leading \n after --- - - // Parse name - const nameMatch = frontmatter.match(/^name:\s*(.+)$/m); - const name = nameMatch ? nameMatch[1].trim() : ''; - - // Parse description — handle both simple and block scalar (|) formats - let description = ''; - const lines = frontmatter.split('\n'); - let inDescription = false; - const descLines: string[] = []; - for (const line of lines) { - if (line.match(/^description:\s*\|?\s*$/)) { - // Block scalar start: "description: |" or "description:" - inDescription = true; - continue; - } - if (line.match(/^description:\s*\S/)) { - // Simple inline: "description: some text" - description = line.replace(/^description:\s*/, '').trim(); - break; - } - if (inDescription) { - // Block scalar continuation — indented lines (2 spaces) or blank lines - if (line === '' || line.match(/^\s/)) { - descLines.push(line.replace(/^ /, '')); - } else { - // End of block scalar — hit a non-indented, non-blank line - break; - } - } - } - if (descLines.length > 0) { - description = descLines.join('\n').trim(); - } + const { name, description } = extractNameAndDescription(content); // Re-emit Codex frontmatter (name + description only) const indentedDesc = description.split('\n').map(l => ` ${l}`).join('\n'); @@ -2931,6 +2955,7 @@ function processTemplate(tmplPath: string, host: Host = 'claude'): { outputPath: const tmplContent = fs.readFileSync(tmplPath, 'utf-8'); const relTmplPath = path.relative(ROOT, tmplPath); let outputPath = tmplPath.replace(/\.tmpl$/, ''); + let outputDir: string | null = null; // Determine skill directory relative to ROOT const skillDir = path.relative(ROOT, path.dirname(tmplPath)); @@ -2938,14 +2963,14 @@ function processTemplate(tmplPath: string, host: Host = 'claude'): { outputPath: // For codex host, route output to .agents/skills/{codexSkillName}/SKILL.md if (host === 'codex') { const codexName = codexSkillName(skillDir === '.' ? '' : skillDir); - const outputDir = path.join(ROOT, '.agents', 'skills', codexName); + outputDir = path.join(ROOT, '.agents', 'skills', codexName); fs.mkdirSync(outputDir, { recursive: true }); outputPath = path.join(outputDir, 'SKILL.md'); } // Extract skill name from frontmatter for TemplateContext - const nameMatch = tmplContent.match(/^name:\s*(.+)$/m); - const skillName = nameMatch ? nameMatch[1].trim() : path.basename(path.dirname(tmplPath)); + const { name: extractedName, description: extractedDescription } = extractNameAndDescription(tmplContent); + const skillName = extractedName || path.basename(path.dirname(tmplPath)); // Extract benefits-from list from frontmatter (inline YAML: benefits-from: [a, b]) const benefitsMatch = tmplContent.match(/^benefits-from:\s*\[([^\]]*)\]/m); @@ -2987,6 +3012,15 @@ function processTemplate(tmplPath: string, host: Host = 'claude'): { outputPath: content = content.replace(/\.claude\/skills\/gstack/g, ctx.paths.localSkillRoot); content = content.replace(/\.claude\/skills\/review/g, '.agents/skills/gstack/review'); content = content.replace(/\.claude\/skills/g, '.agents/skills'); + + if (outputDir) { + const codexName = codexSkillName(skillDir === '.' ? '' : skillDir); + const agentsDir = path.join(outputDir, 'agents'); + fs.mkdirSync(agentsDir, { recursive: true }); + const displayName = codexName; + const shortDescription = condenseOpenAIShortDescription(extractedDescription); + fs.writeFileSync(path.join(agentsDir, 'openai.yaml'), generateOpenAIYaml(displayName, shortDescription)); + } } // Prepend generated header (after frontmatter) diff --git a/ship/SKILL.md b/ship/SKILL.md index 8c875985..0d984f09 100644 --- a/ship/SKILL.md +++ b/ship/SKILL.md @@ -357,7 +357,7 @@ 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, plan-design-review, design-review-lite, adversarial-review, codex-review, codex-plan-review). Ignore entries with timestamps older than 7 days. 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. Display: ``` +====================================================================+ @@ -383,7 +383,7 @@ Parse the output. Find the most recent entry for each skill (plan-ceo-review, pl - **Outside Voice (optional):** Independent plan review from a different AI model. Offered after all review sections complete in /plan-ceo-review and /plan-eng-review. Falls back to Claude subagent if Codex is unavailable. Never gates shipping. **Verdict logic:** -- **CLEARED**: Eng Review has >= 1 entry within 7 days with status "clean" (or \`skip_eng_review\` is \`true\`) +- **CLEARED**: Eng Review has >= 1 entry within 7 days from either \`review\` or \`plan-eng-review\` with status "clean" (or \`skip_eng_review\` is \`true\`) - **NOT CLEARED**: Eng Review missing, stale (>7 days), or has open issues - CEO, Design, and Codex reviews are shown for context but never block shipping - If \`skip_eng_review\` config is \`true\`, Eng Review shows "SKIPPED (global)" and verdict is CLEARED @@ -406,7 +406,7 @@ If the Eng Review is NOT "CLEAR": 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 /plan-eng-review first C) Change is too small to need eng review + - 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 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. diff --git a/ship/SKILL.md.tmpl b/ship/SKILL.md.tmpl index 0308dd8b..e7709a33 100644 --- a/ship/SKILL.md.tmpl +++ b/ship/SKILL.md.tmpl @@ -70,7 +70,7 @@ If the Eng Review is NOT "CLEAR": 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 /plan-eng-review first C) Change is too small to need eng review + - 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 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. diff --git a/test/gen-skill-docs.test.ts b/test/gen-skill-docs.test.ts index 992d78d8..0e179c1e 100644 --- a/test/gen-skill-docs.test.ts +++ b/test/gen-skill-docs.test.ts @@ -410,6 +410,20 @@ describe('REVIEW_DASHBOARD resolver', () => { expect(content).toContain('REVIEW READINESS DASHBOARD'); }); + test('dashboard treats review as a valid Eng Review source', () => { + const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8'); + expect(content).toContain('plan-eng-review, review, plan-design-review'); + expect(content).toContain('`review` (diff-scoped pre-landing review)'); + expect(content).toContain('`plan-eng-review` (plan-stage architecture review)'); + expect(content).toContain('from either \\`review\\` or \\`plan-eng-review\\`'); + }); + + test('shared dashboard propagates review source to plan-eng-review', () => { + const content = fs.readFileSync(path.join(ROOT, 'plan-eng-review', 'SKILL.md'), 'utf-8'); + expect(content).toContain('plan-eng-review, review, plan-design-review'); + expect(content).toContain('`review` (diff-scoped pre-landing review)'); + }); + test('resolver output contains key dashboard elements', () => { const content = fs.readFileSync(path.join(ROOT, 'plan-ceo-review', 'SKILL.md'), 'utf-8'); expect(content).toContain('VERDICT'); @@ -939,6 +953,14 @@ describe('Codex generation (--host codex)', () => { } }); + test('root gstack bundle has OpenAI metadata for Codex skill browsing', () => { + const rootMetadata = path.join(ROOT, 'agents', 'openai.yaml'); + expect(fs.existsSync(rootMetadata)).toBe(true); + const content = fs.readFileSync(rootMetadata, 'utf-8'); + expect(content).toContain('display_name: "gstack"'); + expect(content).toContain('Use $gstack to locate the bundled gstack skills.'); + }); + test('codexSkillName mapping: root is gstack, others are gstack-{dir}', () => { // Root → gstack expect(fs.existsSync(path.join(AGENTS_DIR, 'gstack', 'SKILL.md'))).toBe(true); @@ -968,6 +990,17 @@ describe('Codex generation (--host codex)', () => { } }); + test('all Codex skills have agents/openai.yaml metadata', () => { + for (const skill of CODEX_SKILLS) { + const metadata = path.join(AGENTS_DIR, skill.codexName, 'agents', 'openai.yaml'); + expect(fs.existsSync(metadata)).toBe(true); + const content = fs.readFileSync(metadata, 'utf-8'); + expect(content).toContain(`display_name: "${skill.codexName}"`); + expect(content).toContain('short_description:'); + expect(content).toContain('allow_implicit_invocation: true'); + } + }); + test('no .claude/skills/ in Codex output', () => { for (const skill of CODEX_SKILLS) { const content = fs.readFileSync(path.join(AGENTS_DIR, skill.codexName, 'SKILL.md'), 'utf-8'); diff --git a/test/helpers/codex-session-runner.ts b/test/helpers/codex-session-runner.ts index 77b45020..ac2b9e29 100644 --- a/test/helpers/codex-session-runner.ts +++ b/test/helpers/codex-session-runner.ts @@ -98,7 +98,8 @@ export function parseCodexJSONL(lines: string[]): ParsedCodexJSONL { /** * Install a SKILL.md into a temp HOME directory for Codex to discover. - * Creates ~/.codex/skills/{skillName}/SKILL.md in the temp HOME. + * Creates ~/.codex/skills/{skillName}/SKILL.md in the temp HOME and copies + * agents/openai.yaml when present so Codex sees the same metadata as a real install. * * Returns the temp HOME path. Caller is responsible for cleanup. */ @@ -116,6 +117,13 @@ export function installSkillToTempHome( fs.copyFileSync(srcSkill, path.join(destDir, 'SKILL.md')); } + const srcOpenAIYaml = path.join(skillDir, 'agents', 'openai.yaml'); + if (fs.existsSync(srcOpenAIYaml)) { + const destAgentsDir = path.join(destDir, 'agents'); + fs.mkdirSync(destAgentsDir, { recursive: true }); + fs.copyFileSync(srcOpenAIYaml, path.join(destAgentsDir, 'openai.yaml')); + } + return home; } diff --git a/test/skill-validation.test.ts b/test/skill-validation.test.ts index 3d76ae67..c4bc99af 100644 --- a/test/skill-validation.test.ts +++ b/test/skill-validation.test.ts @@ -1369,6 +1369,18 @@ describe('Codex skill', () => { expect(content).toContain('codex exec'); }); + test('/review persists a review-log entry for ship readiness', () => { + const content = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8'); + expect(content).toContain('"skill":"review"'); + expect(content).toContain('"issues_found":N'); + 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');