From d6530583a8985139e7a044e248255e8a788ea88b Mon Sep 17 00:00:00 2001 From: Garry Tan Date: Sun, 29 Mar 2026 21:06:36 -0700 Subject: [PATCH] feat: wire learnings into all insight-producing skills Adds LEARNINGS_SEARCH and/or LEARNINGS_LOG to 10 skill templates that produce reusable insights but were previously disconnected from the learning system: - office-hours, plan-ceo-review, plan-eng-review: add LOG (had SEARCH) - plan-design-review: add both SEARCH + LOG (had neither) - design-review, design-consultation, cso, qa, qa-only: add both - retro: add SEARCH (had LOG) 13 skills now fully participate in the learning loop (read + write). Every review, QA, investigation, and design session both consults prior learnings and contributes new ones. Co-Authored-By: Claude Opus 4.6 (1M context) --- cso/SKILL.md | 63 +++++++++++++++++++++++++++++++ cso/SKILL.md.tmpl | 4 ++ design-consultation/SKILL.md | 63 +++++++++++++++++++++++++++++++ design-consultation/SKILL.md.tmpl | 4 ++ design-review/SKILL.md | 63 +++++++++++++++++++++++++++++++ design-review/SKILL.md.tmpl | 4 ++ office-hours/SKILL.md | 25 ++++++++++++ office-hours/SKILL.md.tmpl | 2 + plan-ceo-review/SKILL.md | 25 ++++++++++++ plan-ceo-review/SKILL.md.tmpl | 2 + plan-design-review/SKILL.md | 63 +++++++++++++++++++++++++++++++ plan-design-review/SKILL.md.tmpl | 4 ++ plan-eng-review/SKILL.md | 25 ++++++++++++ plan-eng-review/SKILL.md.tmpl | 2 + qa-only/SKILL.md | 63 +++++++++++++++++++++++++++++++ qa-only/SKILL.md.tmpl | 4 ++ qa/SKILL.md | 63 +++++++++++++++++++++++++++++++ qa/SKILL.md.tmpl | 4 ++ retro/SKILL.md | 38 +++++++++++++++++++ retro/SKILL.md.tmpl | 2 + 20 files changed, 523 insertions(+) diff --git a/cso/SKILL.md b/cso/SKILL.md index f5dbca09..ba801a1b 100644 --- a/cso/SKILL.md +++ b/cso/SKILL.md @@ -420,6 +420,44 @@ grep -q "laravel" composer.json 2>/dev/null && echo "FRAMEWORK: Laravel" This is NOT a checklist — it's a reasoning phase. The output is understanding, not findings. +## 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. + ### Phase 1: Attack Surface Census Map what an attacker sees — both code surface and infrastructure surface. @@ -939,6 +977,31 @@ Write findings to `.gstack/security-reports/{date}-{HHMMSS}.json` using this sch If `.gstack/` is not in `.gitignore`, note it in findings — security reports should stay local. +## 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":"cso","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), +`operational` (project environment/CLI/workflow knowledge). + +**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 - **Think like an attacker, report like a defender.** Show the exploit path, then the fix. diff --git a/cso/SKILL.md.tmpl b/cso/SKILL.md.tmpl index 5bd86a9c..8ea276bf 100644 --- a/cso/SKILL.md.tmpl +++ b/cso/SKILL.md.tmpl @@ -102,6 +102,8 @@ grep -q "laravel" composer.json 2>/dev/null && echo "FRAMEWORK: Laravel" This is NOT a checklist — it's a reasoning phase. The output is understanding, not findings. +{{LEARNINGS_SEARCH}} + ### Phase 1: Attack Surface Census Map what an attacker sees — both code surface and infrastructure surface. @@ -598,6 +600,8 @@ Write findings to `.gstack/security-reports/{date}-{HHMMSS}.json` using this sch If `.gstack/` is not in `.gitignore`, note it in findings — security reports should stay local. +{{LEARNINGS_LOG}} + ## Important Rules - **Think like an attacker, report like a defender.** Show the exploit path, then the fix. diff --git a/design-consultation/SKILL.md b/design-consultation/SKILL.md index 91325e11..aa4b36d4 100644 --- a/design-consultation/SKILL.md +++ b/design-consultation/SKILL.md @@ -478,6 +478,44 @@ If `DESIGN_NOT_AVAILABLE`: Phase 5 falls back to the HTML preview page (still go --- +## 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. + ## Phase 1: Product Context Ask the user a single question that covers everything you need to know. Pre-fill what you can infer from the codebase. @@ -961,6 +999,31 @@ List all decisions. Flag any that used agent defaults without explicit user conf --- +## 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":"design-consultation","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), +`operational` (project environment/CLI/workflow knowledge). + +**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 1. **Propose, don't present menus.** You are a consultant, not a form. Make opinionated recommendations based on the product context, then let the user adjust. diff --git a/design-consultation/SKILL.md.tmpl b/design-consultation/SKILL.md.tmpl index 2ce7c1d3..5a009555 100644 --- a/design-consultation/SKILL.md.tmpl +++ b/design-consultation/SKILL.md.tmpl @@ -79,6 +79,8 @@ If `DESIGN_NOT_AVAILABLE`: Phase 5 falls back to the HTML preview page (still go --- +{{LEARNINGS_SEARCH}} + ## Phase 1: Product Context Ask the user a single question that covers everything you need to know. Pre-fill what you can infer from the codebase. @@ -415,6 +417,8 @@ List all decisions. Flag any that used agent defaults without explicit user conf --- +{{LEARNINGS_LOG}} + ## Important Rules 1. **Propose, don't present menus.** You are a consultant, not a form. Make opinionated recommendations based on the product context, then let the user adjust. diff --git a/design-review/SKILL.md b/design-review/SKILL.md index 31519c55..d77a6a24 100644 --- a/design-review/SKILL.md +++ b/design-review/SKILL.md @@ -648,6 +648,44 @@ echo "REPORT_DIR: $REPORT_DIR" --- +## Prior Learnings + +Search for relevant learnings from previous sessions: + +```bash +_CROSS_PROJ=$(~/.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. + ## Phases 1-6: Design Audit Baseline ## Modes @@ -1314,6 +1352,31 @@ If the repo has a `TODOS.md`: --- +## 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":"design-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), +`operational` (project environment/CLI/workflow knowledge). + +**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. + ## Additional Rules (design-review specific) 11. **Clean working tree required.** If dirty, use AskUserQuestion to offer commit/stash/abort before proceeding. diff --git a/design-review/SKILL.md.tmpl b/design-review/SKILL.md.tmpl index 904a732c..c3ef7731 100644 --- a/design-review/SKILL.md.tmpl +++ b/design-review/SKILL.md.tmpl @@ -97,6 +97,8 @@ echo "REPORT_DIR: $REPORT_DIR" --- +{{LEARNINGS_SEARCH}} + ## Phases 1-6: Design Audit Baseline {{DESIGN_METHODOLOGY}} @@ -287,6 +289,8 @@ If the repo has a `TODOS.md`: --- +{{LEARNINGS_LOG}} + ## Additional Rules (design-review specific) 11. **Clean working tree required.** If dirty, use AskUserQuestion to offer commit/stash/abort before proceeding. diff --git a/office-hours/SKILL.md b/office-hours/SKILL.md index 323a63b0..8b0eeea9 100644 --- a/office-hours/SKILL.md +++ b/office-hours/SKILL.md @@ -1354,6 +1354,31 @@ The design doc at `~/.gstack/projects/` is automatically discoverable by downstr --- +## 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":"office-hours","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), +`operational` (project environment/CLI/workflow knowledge). + +**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 - **Never start implementation.** This skill produces design docs, not code. Not even scaffolding. diff --git a/office-hours/SKILL.md.tmpl b/office-hours/SKILL.md.tmpl index 358f8290..b921259e 100644 --- a/office-hours/SKILL.md.tmpl +++ b/office-hours/SKILL.md.tmpl @@ -642,6 +642,8 @@ The design doc at `~/.gstack/projects/` is automatically discoverable by downstr --- +{{LEARNINGS_LOG}} + ## Important Rules - **Never start implementation.** This skill produces design docs, not code. Not even scaffolding. diff --git a/plan-ceo-review/SKILL.md b/plan-ceo-review/SKILL.md index cffd8747..5be7dedc 100644 --- a/plan-ceo-review/SKILL.md +++ b/plan-ceo-review/SKILL.md @@ -1545,6 +1545,31 @@ If promoted, copy the CEO plan content to `docs/designs/{FEATURE}.md` (create th * After each section, pause and wait for feedback. * Use **CRITICAL GAP** / **WARNING** / **OK** for scannability. +## 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":"plan-ceo-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), +`operational` (project environment/CLI/workflow knowledge). + +**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. + ## Mode Quick Reference ``` ┌────────────────────────────────────────────────────────────────────────────────┐ diff --git a/plan-ceo-review/SKILL.md.tmpl b/plan-ceo-review/SKILL.md.tmpl index 16aea4f9..739ca8e6 100644 --- a/plan-ceo-review/SKILL.md.tmpl +++ b/plan-ceo-review/SKILL.md.tmpl @@ -782,6 +782,8 @@ If promoted, copy the CEO plan content to `docs/designs/{FEATURE}.md` (create th * After each section, pause and wait for feedback. * Use **CRITICAL GAP** / **WARNING** / **OK** for scannability. +{{LEARNINGS_LOG}} + ## Mode Quick Reference ``` ┌────────────────────────────────────────────────────────────────────────────────┐ diff --git a/plan-design-review/SKILL.md b/plan-design-review/SKILL.md index a7479bf9..38f8af75 100644 --- a/plan-design-review/SKILL.md +++ b/plan-design-review/SKILL.md @@ -860,6 +860,44 @@ descriptions of what 10/10 looks like. ## Review Sections (7 passes, 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. + ### Pass 1: Information Architecture Rate 0-10: Does the plan define what the user sees first, second, third? FIX TO 10: Add information hierarchy to the plan. Include ASCII diagram of screen/page structure and navigation flow. Apply "constraint worship" — if you can only show 3 things, which 3? @@ -1215,6 +1253,31 @@ plan's living status. - Always place it as the very last section in the plan file. If it was found mid-file, move it: delete the old location and append at the end. +## 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":"plan-design-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), +`operational` (project environment/CLI/workflow knowledge). + +**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. + ## Next Steps — Review Chaining After displaying the Review Readiness Dashboard, recommend the next review(s) based on what this design review discovered. Read the dashboard output to see which reviews have already been run and whether they are stale. diff --git a/plan-design-review/SKILL.md.tmpl b/plan-design-review/SKILL.md.tmpl index cfafa6e6..c008acf1 100644 --- a/plan-design-review/SKILL.md.tmpl +++ b/plan-design-review/SKILL.md.tmpl @@ -257,6 +257,8 @@ descriptions of what 10/10 looks like. ## Review Sections (7 passes, after scope is agreed) +{{LEARNINGS_SEARCH}} + ### Pass 1: Information Architecture Rate 0-10: Does the plan define what the user sees first, second, third? FIX TO 10: Add information hierarchy to the plan. Include ASCII diagram of screen/page structure and navigation flow. Apply "constraint worship" — if you can only show 3 things, which 3? @@ -431,6 +433,8 @@ Substitute values from the Completion Summary: {{PLAN_FILE_REVIEW_REPORT}} +{{LEARNINGS_LOG}} + ## Next Steps — Review Chaining After displaying the Review Readiness Dashboard, recommend the next review(s) based on what this design review discovered. Read the dashboard output to see which reviews have already been run and whether they are stale. diff --git a/plan-eng-review/SKILL.md b/plan-eng-review/SKILL.md index 5ecd6871..b6f117ce 100644 --- a/plan-eng-review/SKILL.md +++ b/plan-eng-review/SKILL.md @@ -1172,6 +1172,31 @@ plan's living status. - Always place it as the very last section in the plan file. If it was found mid-file, move it: delete the old location and append at the end. +## 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":"plan-eng-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), +`operational` (project environment/CLI/workflow knowledge). + +**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. + ## Next Steps — Review Chaining After displaying the Review Readiness Dashboard, check if additional reviews would be valuable. Read the dashboard output to see which reviews have already been run and whether they are stale. diff --git a/plan-eng-review/SKILL.md.tmpl b/plan-eng-review/SKILL.md.tmpl index 415315a8..c0311e09 100644 --- a/plan-eng-review/SKILL.md.tmpl +++ b/plan-eng-review/SKILL.md.tmpl @@ -287,6 +287,8 @@ Substitute values from the Completion Summary: {{PLAN_FILE_REVIEW_REPORT}} +{{LEARNINGS_LOG}} + ## Next Steps — Review Chaining After displaying the Review Readiness Dashboard, check if additional reviews would be valuable. Read the dashboard output to see which reviews have already been run and whether they are stale. diff --git a/qa-only/SKILL.md b/qa-only/SKILL.md index 4a538657..f728cd56 100644 --- a/qa-only/SKILL.md +++ b/qa-only/SKILL.md @@ -407,6 +407,44 @@ mkdir -p "$REPORT_DIR/screenshots" --- +## Prior Learnings + +Search for relevant learnings from previous sessions: + +```bash +_CROSS_PROJ=$(~/.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. + ## Test Plan Context Before falling back to git diff heuristics, check for richer test plan sources: @@ -731,6 +769,31 @@ Report filenames use the domain and date: `qa-report-myapp-com-2026-03-12.md` --- +## 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":"qa-only","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), +`operational` (project environment/CLI/workflow knowledge). + +**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. + ## Additional Rules (qa-only specific) 11. **Never fix bugs.** Find and document only. Do not read source code, edit files, or suggest fixes in the report. Your job is to report what's broken, not to fix it. Use `/qa` for the test-fix-verify loop. diff --git a/qa-only/SKILL.md.tmpl b/qa-only/SKILL.md.tmpl index 0bb59c0c..71bc0566 100644 --- a/qa-only/SKILL.md.tmpl +++ b/qa-only/SKILL.md.tmpl @@ -49,6 +49,8 @@ mkdir -p "$REPORT_DIR/screenshots" --- +{{LEARNINGS_SEARCH}} + ## Test Plan Context Before falling back to git diff heuristics, check for richer test plan sources: @@ -97,6 +99,8 @@ Report filenames use the domain and date: `qa-report-myapp-com-2026-03-12.md` --- +{{LEARNINGS_LOG}} + ## Additional Rules (qa-only specific) 11. **Never fix bugs.** Find and document only. Do not read source code, edit files, or suggest fixes in the report. Your job is to report what's broken, not to fix it. Use `/qa` for the test-fix-verify loop. diff --git a/qa/SKILL.md b/qa/SKILL.md index 0e03a4c6..32b71712 100644 --- a/qa/SKILL.md +++ b/qa/SKILL.md @@ -637,6 +637,44 @@ mkdir -p .gstack/qa-reports/screenshots --- +## Prior Learnings + +Search for relevant learnings from previous sessions: + +```bash +_CROSS_PROJ=$(~/.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. + ## Test Plan Context Before falling back to git diff heuristics, check for richer test plan sources: @@ -1138,6 +1176,31 @@ If the repo has a `TODOS.md`: --- +## 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":"qa","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), +`operational` (project environment/CLI/workflow knowledge). + +**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. + ## Additional Rules (qa-specific) 11. **Clean working tree required.** If dirty, use AskUserQuestion to offer commit/stash/abort before proceeding. diff --git a/qa/SKILL.md.tmpl b/qa/SKILL.md.tmpl index 0283ffc7..6c946e29 100644 --- a/qa/SKILL.md.tmpl +++ b/qa/SKILL.md.tmpl @@ -90,6 +90,8 @@ mkdir -p .gstack/qa-reports/screenshots --- +{{LEARNINGS_SEARCH}} + ## Test Plan Context Before falling back to git diff heuristics, check for richer test plan sources: @@ -315,6 +317,8 @@ If the repo has a `TODOS.md`: --- +{{LEARNINGS_LOG}} + ## Additional Rules (qa-specific) 11. **Clean working tree required.** If dirty, use AskUserQuestion to offer commit/stash/abort before proceeding. diff --git a/retro/SKILL.md b/retro/SKILL.md index 4d202efa..e80324a3 100644 --- a/retro/SKILL.md +++ b/retro/SKILL.md @@ -413,6 +413,44 @@ Usage: /retro [window | compare | global] **If the first argument is `global`:** Skip the normal repo-scoped retro (Steps 1-14). Instead, follow the **Global Retrospective** flow at the end of this document. The optional second argument is the time window (default 7d). This mode does NOT require being inside a git repo. +## 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 1: Gather Raw Data First, fetch origin and identify the current user: diff --git a/retro/SKILL.md.tmpl b/retro/SKILL.md.tmpl index b1b44ee1..755a6f9c 100644 --- a/retro/SKILL.md.tmpl +++ b/retro/SKILL.md.tmpl @@ -58,6 +58,8 @@ Usage: /retro [window | compare | global] **If the first argument is `global`:** Skip the normal repo-scoped retro (Steps 1-14). Instead, follow the **Global Retrospective** flow at the end of this document. The optional second argument is the time window (default 7d). This mode does NOT require being inside a git repo. +{{LEARNINGS_SEARCH}} + ### Step 1: Gather Raw Data First, fetch origin and identify the current user: