Learning consolidation and skill enhancements #376
Closed
+7,605
−59
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Include documenting-completed-implementation skill in release. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
finishing-a-development-branch now invokes documenting-completed-implementation instead of duplicating all documentation steps. This follows the single-responsibility principle and makes documentation reusable. Changes: - documenting-completed-implementation: Added Implementation History section and plan archiving (moved from finishing-a-development-branch) - finishing-a-development-branch: Step 1 now invokes documenting skill instead of duplicating the documentation workflow - CLAUDE.md: Updated skill descriptions to reflect new relationship - docs/architecture.md: Added Documenting skill to diagram, show invocation Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Based on real-world retrospective from calendar-prep-mvp Todoist implementation. Identifies 6 workflow gaps and proposes solutions. Key improvements: - Pre-flight check for uncommitted changes - Enhanced test verification (unit vs integration) - Auto-invoke verification-before-completion - Code review gate for major features - Smart README redundancy detection - Push to remote prompt after merge Includes: - Real-world evidence and examples - Backward compatibility analysis - Implementation priority (High/Medium/Low) - Questions for maintainers All enhancements are additive and composable. Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Catches uncommitted changes before starting workflow to prevent mid-flow failures during git checkout operations. Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Adds user prompt to distinguish between configuration-related test failures (safe to merge) and actual bugs (must fix). Prevents confusion when integration tests fail due to missing .env files. Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Adds code review as option 2 in the completion workflow, allowing users to explicitly request review before merging. This is an opt-in choice rather than an auto-detected gate. Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Checks for existing dedicated sections in README before adding documentation. Prevents redundant updates when comprehensive docs already exist. Uses section header detection (## or ###) rather than line counting. Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Documents which enhancements were implemented and rationale for changes from original proposal. Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Mark implementation plan as completed, update CLAUDE.md with new finishing workflow enhancement information. - Plan: Mark as completed (2026-01-11), move to completed/ - CLAUDE.md: Add to Implementation History - Skills: Enhanced finishing-a-development-branch and documenting-completed-implementation Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
The test runner now works on both Linux and macOS by: - Using native 'timeout' command on Linux - Falling back to 'gtimeout' on macOS with coreutils - Using basic bash timeout implementation as final fallback Fixes test failures on macOS where timeout command is not available. Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Adds the same portable timeout function to test-helpers.sh to ensure test helpers also work on macOS. Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
The test now asks a more specific question about the first step and plan file handling to elicit the expected workflow details, rather than asking a general 'what is' question. Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
- Add missing match-skills command to learning analyzer - Fix date mutation bug in findStaleLearnings() that was mutating 'now' - Improve YAML parser robustness: - Handle CRLF line endings properly - Support quoted values containing colons - Skip comments and empty lines gracefully - Add try-catch for malformed YAML handling All three commands (analyze, patterns, stale, match-skills) tested and working. Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Add compound-learning skill for capturing learnings immediately after verification confirms a solution works. Includes state tracker to count learnings and trigger review suggestions at 10 learnings threshold. - skills/compound-learning/SKILL.md: Main skill with capture workflow - lib/meta-learning-state.js: Counter and state management for learnings - commands/compound.md: User-facing /compound command This complements meta-learning-review skill which analyzes patterns from captured learnings to suggest improvements. Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
- Merge Step 3 (Gather Learning Information) into Step 2 (Quick Capture) to reduce from 6 to 5 steps - Renumber subsequent steps: Step 3→Create Learning File, Step 4→Increment Counter, Step 5→Commit Learning - Use lastReview consistently throughout meta-learning-state.js (line 33, 44) instead of lastRecorded - Reduce Success Criteria from 8 to 5 core checkmarks as specified in plan Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
- Add optional learning capture prompt to verification-before-completion skill - Users can now invoke compound-learning after verification success - Document meta-learning-review and compound-learning in CLAUDE.md - Add integration test verifying pattern detection across 5+ learnings - Test confirms meta-learning-review skill analysis and learning capture option Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
- Test 3: Replace flaky Claude invocation with direct analyzer test - Now tests the actual analyzer output showing yaml pattern detection - Verifies count is exactly 5 instead of vague pattern matching - More reliable since it doesn't depend on Claude's interpretation - Test 4: Improve pattern matching for compound-learning skill - More flexible regex to handle various phrasings - Verifies Claude understands purpose (knowledge capture/learning) - Test 5: Use direct file verification instead of Claude invocation - Remove dependency on Claude's file access permissions - Directly verify skill content includes compound-learning mention All tests now pass consistently across multiple runs (verified 3x). Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Mark implementation plan as completed, update CLAUDE.md and README with new meta-learning system information. - Plan: Mark as completed (2026-01-11), move to completed/ - CLAUDE.md: Add to Implementation History, existing Meta-Learning section documented - README: Add Meta-Learning category with compound-learning and meta-learning-review skills, usage examples for /compound and /review-learnings commands Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Mark implementation plan as completed, update CLAUDE.md and README with new ai-self-reflection information. - Plan: Mark as completed (2026-01-14), move to completed/ - CLAUDE.md: Add to Implementation History - README: Add ai-self-reflection to Meta-Learning skills and commands Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
- Read tool path resolution (use absolute paths not tilde) - AI self-reflection workflow discipline (follow documented steps) Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Add 'Executing Skills' section to remind AI to read and follow loaded skill content exactly, not work from memory or assumptions. Addresses learning: ai-self-reflection-requires-following-documented-workflow Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Move model selection guidance from user CLAUDE.md into the plugin. This makes it available to all users and loaded automatically via SessionStart hook. Guidelines: - Opus for design/architecture (brainstorming) - Sonnet for planning and debugging - Haiku for mechanical execution Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Meta-learning improvements based on ai-self-reflection feedback: - Skill execution discipline - Model selection guidelines Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Based on learnings from 2026-01-15 session, enhanced four skills to emphasize investigating before categorizing test failures and errors: **systematic-debugging Phase 1:** - Added emphasis: "Don't trust error messages at face value" - Verify error claims before accepting them (e.g., "file not found") **verification-before-completion:** - Added Step 4: INVESTIGATE before interpreting failures - Check paths, permissions, environment before categorizing **finishing-a-development-branch Step 2:** - Added investigation step before asking user to categorize test failures - Reference systematic-debugging Phase 1 for root cause analysis - Show investigation findings in categorization prompt **using-superpowers:** - Added "Common Trigger Phrases" table with skill invocation examples - Explicit completion triggers: "let's complete this" → finishing-a-development-branch - Debugging triggers: "tests failing" → systematic-debugging - Feature triggers: "add feature" → brainstorming first Learnings applied: - docs/learnings/2026-01-15-investigate-before-categorizing-test-failures.md - docs/learnings/2026-01-15-always-use-finishing-skill-on-completion-triggers.md Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Release includes investigation-before-categorization enhancements across systematic-debugging, verification-before-completion, finishing-a-development-branch, and using-superpowers skills. Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Added implementation notes to both learnings showing they were acted upon in the skill enhancements. Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Both learnings have been acted upon in v4.1.2 skill enhancements. Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Implements dual-reinforcement approach for suggesting next workflow steps:
1. Workflow Chains Table:
- Added "Common Workflow Chains" section to using-superpowers skill
- Maps each skill to its next logical step with clear guidance
- Always available in session context via SessionStart hook
- Provides single source of truth for workflow progression
2. Stop Hook:
- New skill-workflow-reminder.sh hook runs after each Claude response
- Injects reminder to check workflow chains table
- Ensures proactive suggestions ("Next step: Use...") not passive questions
- Works globally across all repositories where plugin is enabled
3. Enhanced ai-self-reflection:
- Added "Act on them now" workflow for immediate learning implementation
- Options: update CLAUDE.md, create/update skill, fix code, save for later
- Makes learning capture more actionable and integrated into workflow
Version bumped to 4.1.3.
Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Stop hooks don't support additionalContext output, causing JSON validation errors when the plugin loads. UserPromptSubmit hooks can inject context into user messages, which is what we need for the workflow reminder. Changes: - hooks/hooks.json: Changed hook type from Stop to UserPromptSubmit - hooks/skill-workflow-reminder.sh: Updated hookEventName to match - Bump version to 4.1.4 This fixes the error: "Stop hook error: JSON validation failed: Hook JSON output validation failed" Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
…cture Captured two key learnings from chat interface implementation: 1. Always check both worktree AND main directory when agents are involved - Don't assume agents follow path instructions - Verify with evidence (git status, ls both locations) - Prevents false failure declarations 2. Update test infrastructure after architectural changes - When moving from system-wide to per-user credentials - Update mockUserConfig to match new patterns - Test failures may indicate infrastructure lag, not bugs Session: calendar-prep-mvp chat interface implementation (2026-01-19)
…iscipline Root cause analysis before implementation, global CSS over component classes, and following skill steps exactly to avoid backtracking and incomplete work. Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Captured learning about incorrectly suggesting compound-learning instead of ai-self-reflection after verification-before-completion. Key points: - compound-learning is for quick post-solution capture - ai-self-reflection is for session retrospection - Correct chain: verification → finishing-branch → ai-self-reflection
Integrates external code-simplifier plugin into superpowers workflow: - New skill: code-simplification (optional quality step after execution) - New command: /simplify for quick invocation - Graceful failure when plugin not installed - Auto scope detection (recommends if 5+ files or 100+ lines changed) Updates: - using-superpowers: workflow chain table and trigger phrases - requesting-code-review: note to consider simplification first - CLAUDE.md: workflow chain and skills list Bumps version to 4.1.5 Co-Authored-By: Claude Opus 4.5 <[email protected]>
Infrastructure constraints must be validated before persistence if their failure would corrupt the primary data store, regardless of origin. Key insight: Where validation lives depends on consistency requirements, not whether the constraint is 'business logic' or 'infrastructure'. Example: AWS EventBridge cron limitation (infrastructure) must be validated at API layer (before MongoDB) to prevent invalid state.
- Proactive identification of redundant test files after mocking conversion - Skill tool invocation should not require permission prompts Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
…ction Learning captured: AI self-reflection should proactively categorize learnings as project-specific, skill updates, platform issues, or reference documentation, and suggest appropriate actions for each. Proposes enhancement to ai-self-reflection Step 3 to add categorization phase before asking how to handle learnings. Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
General reusable patterns captured: 1. Validate user input immediately in API endpoints (not code review fix) - Length limits, format validation, business rules - Checklist for every user input field 2. Map feature interactions before implementation - Create matrix of all config combinations - Define behavior for each cell - Prevents architectural bugs 3. Clarify mental models with diagrams before architecture - Ask about user's conceptual model first - Draw 'what goes where' diagram - Get explicit sign-off before coding 4. Audit artifacts when expanding scope (specific → general) - Field names, schemas, docs, examples, tests - Rename for broader scope - Grep for old terminology 5. Remove dead code in same commit as refactoring - Grep for function callers immediately after refactoring - Remove unused functions in same commit - Keep API surface minimal Source: Sterling calendar-prep-mvp context prompt implementation session Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
📝 WalkthroughWalkthroughThis pull request introduces a comprehensive meta-learning system with ai-self-reflection and compound-learning capabilities, adds a code-simplification skill, enhances the finishing-a-development-branch workflow with pre-flight checks and code review integration, implements learning analysis utilities, and bumps the plugin version to 4.1.5 alongside extensive supporting documentation. Changes
Estimated code review effort🎯 4 (Complex) | ⏱️ ~50 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing touches
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 5
Note
Due to the large number of review comments, Critical, Major severity comments were prioritized as inline comments.
🤖 Fix all issues with AI agents
In
`@docs/learnings/2026-01-23-running-actual-aws-cli-commands-to-verify-infrastructure-state-provides-concrete-evidence-that-assumptions-and-documentation-cannot.md`:
- Around line 34-37: The example AWS CLI invocation embeds a real email in the
JSON payload; replace the PII in the payload (the "userId" value used with the
function name calendar-prep-schedule-manager) with a non-sensitive placeholder
(e.g., "[email protected]" or "<USER_EMAIL>") so the command still demonstrates
usage but contains no personal data; update only the payload string in the shown
aws lambda invoke example.
In `@tests/claude-code/test-ai-self-reflection.sh`:
- Around line 30-68: Tests use hardcoded paths like ~/Dev/superpowers/ which
breaks portability; update the script to compute project-root-relative paths
once (e.g., set a SKILL_DIR and COMMAND_DIR based on SCRIPT_DIR or repo root)
and replace all occurrences of
"~/Dev/superpowers/skills/ai-self-reflection/SKILL.md" and
"~/Dev/superpowers/commands/ai-self-reflection.md" in the file-existence and
grep checks with those variables so Test 2 and Test 3 use repository-relative
paths; ensure the grep patterns (e.g., "name: ai-self-reflection",
"user-correction\|backtracking\|repeated-error", and "REQUIRED
SUB-SKILL.*ai-self-reflection") still reference the same filenames/variables.
In `@tests/claude-code/test-helpers.sh`:
- Around line 4-31: The fallback in run_with_timeout treats timeout_duration as
an integer but timeout/gtimeout accept suffixed values (e.g., "30s", "1m"),
causing inconsistent behavior; update run_with_timeout to normalize
timeout_duration up front: parse the input string (timeout_duration) to convert
suffixes s/m/h to an integer seconds value (store in a new timeout_seconds
variable) and reject unsupported formats with a clear error, then use
timeout_seconds in the fallback loop and comparisons (keep passing the original
string to timeout/gtimeout branches so their suffixes still work); reference
run_with_timeout, timeout_duration, and timeout_seconds when applying the
change.
In `@tests/claude-code/test-meta-learning-integration.sh`:
- Around line 3-109: The test script uses hard-coded ~/Dev/superpowers paths and
performs destructive rm -rf on docs/learnings; change it to discover the repo
root (e.g., REPO_ROOT="$(git -C "$(dirname "$0")/.." rev-parse --show-toplevel"
or REPO_ROOT="$(cd "$(dirname "$0")/.."; pwd)") and create a dedicated temp test
folder under the repo (e.g., TEST_LEARNINGS="$REPO_ROOT/test-temp-learnings"),
update all occurrences of ~/Dev/superpowers/docs/learnings to use
$TEST_LEARNINGS, and update calls that cd into the project (cd
~/Dev/superpowers) to use $REPO_ROOT; add a trap cleanup function that only
removes $TEST_LEARNINGS on exit/failure (and remove any unconditional rm -rf of
~/Dev/superpowers/docs/learnings), and ensure the test uses TEST_LEARNINGS when
invoking learning-analyzer.js and when checking SKILL.md so you only delete the
files this test created.
In `@tests/claude-code/test-meta-learning-review.sh`:
- Around line 3-90: The script currently hard-codes ~/Dev/superpowers and uses
rm -rf to delete docs/learnings; change it to create a temporary test learnings
directory under the repo root (use the variable provided by test-helpers.sh,
e.g., $REPO_ROOT or $SCRIPT_DIR) instead of ~/Dev/superpowers, update the
analyzer invocation to cd "$REPO_ROOT" && node
skills/meta-learning-review/lib/learning-analyzer.js analyze, and replace the
global rm -rf ~/Dev/superpowers/docs/learnings with a safe cleanup that only
removes the temp test files (e.g., trap cleanup; cleanup() { rm -rf
"$REPO_ROOT/tests/tmp_learnings"; } ) so only test artifacts are deleted.
🟡 Minor comments (17)
docs/learnings/2026-01-27-validate-user-input-immediately-not-in-code-review.md-48-52 (1)
48-52: Hyphenate the compound adjective.“Worst-case input” reads correctly when used adjectivally.
✏️ Proposed fix
-1. **For each user input field, ask:** "What's the worst case input?" +1. **For each user input field, ask:** "What's the worst-case input?"docs/learnings/2026-01-23-breaking-large-implementation-plans-into-batches-with-user-checkpoints-prevents-waste-and-enables-course-correction.md-11-11 (1)
11-11: Fix grammar: use "an" before vowel sound.📝 Grammar fix
-When executing a implementation plan with multiple tasks (at least 5) for the schedule manager Lambda, there was a risk of: +When executing an implementation plan with multiple tasks (at least 5) for the schedule manager Lambda, there was a risk of:docs/learnings/2026-01-23-breaking-large-implementation-plans-into-batches-with-user-checkpoints-prevents-waste-and-enables-course-correction.md-1-5 (1)
1-5: Add missingcategoryfrontmatter field.Per the PR objectives, the ai-self-reflection enhancement added
categoryfrontmatter to learning files. This consolidated learning file is missing that field, which may prevent proper integration with the categorization and ai-self-reflection systems.📝 Suggested addition
--- date: 2026-01-23 tags: [planning, batch-execution, checkpoints, workflow] workflow: [executing-plans, writing-plans] +category: workflow-pattern ---docs/learnings/2026-01-27-proactive-identification-of-redundant-test-files-after-mocking-conversion.md-48-54 (1)
48-54: Add language specifier to the code block.The example presentation is clear and demonstrates good communication with users. However, the code block is missing a language specifier.
✨ Proposed fix
-``` +```text I converted the integration tests to mocks. I also found these related test files: - packages/lambda/src/scripts/test-processor-mocked.js (manual script) - packages/lambda/src/functions/outputs/todoist/test.js (manual demo) Should we review these for cleanup?</details> As per coding guidelines: "Fenced code blocks should have a language specified." </blockquote></details> <details> <summary>docs/learnings/2026-01-27-proactive-identification-of-redundant-test-files-after-mocking-conversion.md-36-45 (1)</summary><blockquote> `36-45`: **Add language specifier and consider refining the grep command.** The bash commands are helpful, but there are two improvements: 1. Add `bash` language specifier to the code block (flagged by markdownlint). 2. The `grep -r "integration"` command on line 44 is quite broad and may produce many false positives (matching comments, variable names, etc.). <details> <summary>✨ Proposed improvements</summary> ```diff -```bash +```bash # Find manual test scripts find packages -name "test-*.js" -not -path "*/__tests__/*" -not -path "*/.aws-sam/*" # Find manual test files find packages -name "test.js" -o -name "manual-test.js" | grep -v "__tests__" # Look for integration test helpers -grep -r "integration" --include="*test*.js" +rg -n "integration.*test|test.*integration" --type js -g "!__tests__/**" -g "!*.test.js"The refined
rgcommand searches for more specific patterns and excludes standard test directories.As per coding guidelines: "Fenced code blocks should have a language specified."
skills/brainstorming/SKILL.md-55-55 (1)
55-55: Tighten wording and capitalization for clarity.Line 55 has a few grammar/capitalization issues (“lets”, “needs be”, “markdown”, “re-invent”).
✍️ Suggested wording
-- **Libraries should pull their weight** - Do look for library options but they should pull their weight, lets avoid heavy libraries for very simple solutions but also lets not re-invent the wheel. Example would be to convert markdown format to plain text. Look for very lightweight libraries that can perform this. Always offer the option of library when applicable. The decision needs be made by the user. +- **Libraries should pull their weight** - Do look for library options, but they should pull their weight. Let's avoid heavy libraries for very simple solutions, but also let's not reinvent the wheel. Example: convert Markdown format to plain text. Look for lightweight libraries that can perform this. Always offer the option of a library when applicable. The decision needs to be made by the user.skills/documenting-completed-implementation/SKILL.md-110-131 (1)
110-131: Fix nested fenced blocks to avoid premature closure.The outer
markdown blocks contain innerbash fences, which can terminate the outer block early and trigger MD040. Use a longer fence for the outer block so the inner fence is parsed correctly.🧩 Suggested fix (use 4-backtick outer fence)
-```markdown +````markdown ## Implementation History ... ```bash # Setup indexes node packages/admin-ui/scripts/setup-metrics-indexes.js-```
+```````diff -```markdown +````markdown ## Todoist Integration ... ```bash npm run output:todoist...
-```
+````</details> Also applies to: 206-225 </blockquote></details> <details> <summary>docs/learnings/2026-01-27-clarify-mental-models-with-diagrams-before-architecture.md-32-48 (1)</summary><blockquote> `32-48`: **Specify a language for the diagram fence.** MD040 flags the unlabeled fence; `text` is a good fit for ASCII diagrams. <details> <summary>✅ Suggested fix</summary> ```diff -``` +```text System Prompt (to Gemini): ┌─────────────────────────────────────┐ │ [system.md - base behavior] │ │ [user context - domain knowledge] │ │ [output schema - format rules] │ └─────────────────────────────────────┘ User Messages (to Gemini): ┌─────────────────────────────────────┐ │ Message 1: [schedule prompt - task]│ │ Message 2: [calendar instructions] │ │ Message 3: [events JSON] │ └─────────────────────────────────────┘skills/verification-before-completion/SKILL.md-137-146 (1)
137-146: Label the self-reflection block fence.MD040 flags the unlabeled fence;
textis appropriate.✅ Suggested fix
-``` +```text ✅ Verification complete! Reflect on this session and capture learnings? (optional) 1. Yes - use ai-self-reflection 2. No - skipskills/documenting-completed-implementation/SKILL.md-165-172 (1)
165-172: Add a language for the plain output block.MD040 flags the fenced block with no language. Consider
textfor the console-style snippet.✅ Suggested fix
-``` +```text ✅ README.md already has a dedicated section for <feature> Found section: [show matching header] Skipping README update. Review the existing section to ensure it's current.docs/learnings/2026-01-27-audit-artifacts-when-expanding-feature-scope.md-137-149 (1)
137-149: Add a language to the checklist fence.MD040 flags the unlabeled fence;
textkeeps the intent clear.✅ Suggested fix
-``` +```text Before: Meeting-focused After: Event-agnostic To update: - [ ] Field: meeting_preparation_prompt - [ ] Schema description - [ ] Examples (add non-meeting) - [ ] Test casesCLAUDE.md-91-96 (1)
91-96: Version mismatch between documentation sections.Line 91 states the version is "currently 4.1.5", but the example JSON at line 317 shows
"version": "4.0.4". Consider updating the example to match the current version for consistency.Suggested fix at line 317
{ - "version": "4.0.4" + "version": "4.1.5" }skills/ai-self-reflection/SKILL.md-285-289 (1)
285-289: Use$HOMEinstead of quoted tilde in FILE path.In the
FILEassignment on line 288, the quoted tilde ("~/") will not expand to the home directory—it remains a literal~character. This breaks any downstream commands that try to use$FILEas an actual path. Use$HOMEinstead.Proposed fix
-FILE="~/Dev/superpowers/docs/learnings/${DATE}-${SLUG}.md" +FILE="${HOME}/Dev/superpowers/docs/learnings/${DATE}-${SLUG}.md"skills/meta-learning-review/lib/learning-analyzer.js-32-35 (1)
32-35: Filter empty tag entries when parsing bracket arrays.
tags: []currently becomes['']due to splitting an empty string, which creates spurious empty-tag patterns in the output. WhendetectPatterns()processes these tags, empty strings are counted like regular tags and appear in the final patterns JSON as{ tag: "", count: N, ... }.🛠️ Proposed fix
- if (value.startsWith('[')) { - frontmatter[key] = value.slice(1, -1).split(',').map(t => t.trim()); + if (value.startsWith('[')) { + frontmatter[key] = value + .slice(1, -1) + .split(',') + .map(t => t.trim()) + .filter(Boolean);skills/compound-learning/SKILL.md-42-74 (1)
42-74: Fix analyzer to handleworkflowas an array, matching YAML structure andtagspattern.Documentation and actual learning files consistently use array format (
workflow: [systematic-debugging, test-driven-development]), but the analyzer incorrectly treats workflow as a scalar string on line 71 (workflow: frontmatter.workflow || ''). Update this to match howtagsare handled:workflow: frontmatter.workflow || [].docs/plans/completed/2026-01-11-meta-learning-review-skill.md-735-738 (1)
735-738: Avoid absolute paths in repo plans.
~/Dev/superpowers/CLAUDE.mdassumes a local directory layout and can mislead contributors; use a repo‑relative path instead (e.g.,CLAUDE.md).docs/plans/completed/2026-01-11-meta-learning-review-skill.md-343-351 (1)
343-351: Handle invalid or non‑ISO dates to avoid silent misses.
new Date(learning.date)can yieldInvalid Datefor unexpected formats; those learnings then skip stale handling without warning. Add a validation guard (or normalize via a strict parser) and log/skip explicitly.✅ Proposed guard
function findStaleLearnings(learnings) { const now = new Date(); const sixMonthsAgo = new Date(now.setMonth(now.getMonth() - STALE_MONTHS)); return learnings.filter(learning => { - const learningDate = new Date(learning.date); - return learningDate < sixMonthsAgo; + const learningDate = new Date(learning.date); + if (Number.isNaN(learningDate.getTime())) return false; // or log + return learningDate < sixMonthsAgo; }); }
🧹 Nitpick comments (30)
docs/learnings/2026-01-19-tailwind-preflight-button-cursor-and-workflow-discipline.md (1)
1-5: Addcategoryto frontmatter to align with updated learning schema.PR objectives indicate learning files should include
categoryfrontmatter; this file doesn’t include it yet.✅ Proposed update
--- date: 2026-01-19 tags: [tailwind, css, ui, debugging, workflow-discipline] workflow: [finishing-a-development-branch, documenting-completed-implementation] +category: ui-debugging ---docs/learnings/2026-01-26-infrastructure-constraints-validation-before-persistence.md (3)
15-18: Add a fenced code language for the flow block.MD040 requires a language tag. Use
textfor the ASCII flow.✅ Suggested fix
-``` +```text Request → API (no validation) → MongoDB UPDATE ✅ → Lambda REJECTS ❌ Result: Invalid config stored in MongoDB, EventBridge schedule never created</details> --- `79-83`: **Use a heading instead of bold text.** MD036 flags emphasis used as a heading. <details> <summary>✅ Suggested fix</summary> ```diff -**"Validate at the latest safe point, where 'safe' means no invalid state can persist."** +### "Validate at the latest safe point, where 'safe' means no invalid state can persist."
152-154: Add a space after hash in ATX-style heading.MD018 requires a space after
#in headings.✅ Suggested fix
-#validation `#clean-architecture` `#state-consistency` `#infrastructure-constraints` `#architectural-patterns` +# validation `#clean-architecture` `#state-consistency` `#infrastructure-constraints` `#architectural-patterns`docs/learnings/2026-01-27-validate-user-input-immediately-not-in-code-review.md (1)
55-65: Add a language tag to the fenced block.MD040: specify a language for the fenced code block to satisfy markdownlint.
♻️ Proposed fix
- ``` + ```text Task: Implement PATCH /api/users/[userId]/config/prompts @@ - ``` + ```docs/learnings/2026-01-27-remove-dead-code-in-same-commit-as-refactoring.md (4)
1-5: Consider addingcategoryfrontmatter field.According to the PR objectives, the ai-self-reflection skill now adds
categoryfrontmatter to learning files. This file is missing that field.📝 Suggested addition
--- date: 2026-01-27 tags: [refactoring, code-hygiene, technical-debt] +category: refactoring workflow: [refactoring] ---
24-31: Grep pattern is fragile and may produce false positives/negatives.The command filters use literal string matching that could:
- Miss actual calls in comments or with whitespace variations
- Filter out legitimate usage in test files checking exports
- Fail with different coding styles or dynamic imports
🔍 More robust alternative using ripgrep
-# Search for all calls to the function -grep -rn "functionName(" packages/ --include="*.js" \ - | grep -v "function functionName" \ - | grep -v "module.exports" +# Search for all calls to the function (more robust with ripgrep) +rg -n "functionName\(" packages/ -g "*.js" \ + --pcre2 \ + | rg -v "^\s*(function|export|//|/\*)" \ + | rg -v "module\.exports"Or use
ast-grepfor syntactically-aware searching:# Find function calls using AST matching ast-grep --pattern 'functionName($$$)'
56-64: Framework-specific directory exclusions reduce generalizability.Lines 60-61 exclude
.aws-samand.next, which are specific to AWS SAM and Next.js. A learning document should be more generic or explain these are examples.♻️ Make exclusions more generic
# Check for function calls (not just definition/export) grep -rn "functionName(" . \ | grep -v "function functionName" \ | grep -v "export.*functionName" \ - | grep -v ".aws-sam" \ - | grep -v ".next" + | grep -v "node_modules" \ + | grep -v "dist\|build\|.aws-sam\|.next" # Exclude common build directories # If no results → safe to removeOr use
--exclude-dirflags:grep -rn "functionName(" . \ --exclude-dir={node_modules,dist,build,.aws-sam,.next} \ | grep -v "function functionName" \ | grep -v "export.*functionName"
79-92: Consider mentioning ES modules alongside CommonJS.The example only shows
module.exports(CommonJS). Modern codebases increasingly use ES modules (export), and the pattern applies to both.📦 Add ES modules example
Add after the CommonJS example:
// ES modules example // Before export { functionA, functionB, functionC }; // After export { functionA, functionC };docs/learnings/2026-01-27-skill-tool-invocation-unnecessary-permission-prompts.md (1)
42-48: Optional: Add language identifiers to code blocks.The code blocks illustrating correct/incorrect flows could benefit from language identifiers for better rendering and accessibility.
♻️ Suggested enhancement
**Correct flow:** -``` +```text User: "/ai-self-reflection" AI: [Immediately invokes Skill tool] AI: [Reads skill content] AI: [Follows Step 1: Ask user for scope] ...Incorrect flow (what happened):
-+text
User: "/ai-self-reflection"
AI: [Invokes Skill tool]
System: [Permission prompt]
User: [Confirms]
AI: [Skill loads but doesn't follow it]
User: "/ai-self-reflection" (again)
AI: [Invokes Skill tool again]
System: [Permission prompt again]
...As per coding guidelines: Static analysis tool markdownlint-cli2 flagged missing language specifiers (MD040).
Also applies to: 51-61
docs/learnings/2026-01-20-workflow-chain-skill-selection-after-verification.md (1)
24-44: Optional: Add language identifiers to code blocks.The code blocks containing table content and workflow diagrams could benefit from language identifiers for consistency with markdown best practices.
♻️ Suggested enhancement
-``` +```text | After This Skill | Suggest This Next | When | |-------------------------------|---------------------------|--------------------------------| | verification-before-completion| finishing-a-development- | All tests pass | | | branch | |-
+text
verification-before-completion → finishing-a-development-branch → ai-self-reflectionNOT: -``` +```text verification-before-completion → compound-learning ❌</details> As per coding guidelines: Static analysis tool markdownlint-cli2 flagged missing language specifiers (MD040). Also applies to: 66-73 </blockquote></details> <details> <summary>skills/code-simplification/SKILL.md (2)</summary><blockquote> `26-47`: **Consider adding language identifier to workflow diagram.** The workflow diagram uses pseudocode/text format and could benefit from a language identifier for consistency. <details> <summary>♻️ Suggested enhancement</summary> ```diff ## Workflow -``` +```text 1. CHECK: Is code-simplifier plugin available? └─ NO → Inform user, suggest manual review, EXIT └─ YES → Continue 2. DETECT SCOPE: What files changed? └─ Run: git diff --name-only origin/main (or base branch) └─ Count files and estimate lines changed 3. EVALUATE: Is simplification worthwhile? └─ < 3 files, < 50 lines → Skip, too trivial └─ >= 5 files OR >= 100 lines → Recommend └─ Between → Offer as option 4. DISPATCH: Launch code-simplifier agent └─ Use Task tool with subagent_type="code-simplifier:code-simplifier" └─ Prompt: Focus on recently modified files from git diff 5. VERIFY: Check results └─ Run tests to confirm functionality preserved └─ Review changes before accepting</details> --- `53-66`: **Consider adding language identifier to pseudocode block.** The plugin availability check uses pseudocode format and could benefit from a language identifier. <details> <summary>♻️ Suggested enhancement</summary> ```diff **Before dispatching code-simplifier, verify the plugin is installed:** -``` +```text IF dispatching code-simplifier agent fails with: - "Unknown subagent type" - "code-simplifier not found" - Similar error THEN gracefully inform user: "The code-simplifier plugin is not installed. You can: 1. Install it via: /plugin install <plugin-name> 2. Skip this step and proceed to verification 3. Manually review code for simplification opportunities" DO NOT fail silently or retry repeatedly.</details> </blockquote></details> <details> <summary>tests/claude-code/test-code-simplification.sh (3)</summary><blockquote> `8-16`: **Address shell script robustness issues in `setup_git_repo`.** Several issues flagged by static analysis that could cause silent failures: 1. `name` parameter (line 9) is unused — either remove it or use it for meaningful naming 2. Line 10: Declaring and assigning in one statement masks the return value of `create_test_project` 3. Line 11: `cd` without error handling will continue even if the directory doesn't exist <details> <summary>Suggested fix</summary> ```diff setup_git_repo() { - local name="$1" - local test_dir=$(create_test_project) - cd "$test_dir" + local test_dir + test_dir=$(create_test_project) || return 1 + cd "$test_dir" || return 1 git init -q git config user.email "[email protected]" git config user.name "Test User" echo "$test_dir" }
20-89: Apply same robustness fixes intest_proactive_suggestion.Lines 22, 66, and 73 have the same issues:
- Line 22: Declare and assign
test_dirseparately- Line 66: Add
|| return 1aftercd "$test_dir"- Line 73: Declare and assign
responseseparatelySuggested fix for key lines
test_proactive_suggestion() { echo "Setting up test repo..." - local test_dir=$(setup_git_repo "code-simplification-proactive") + local test_dir + test_dir=$(setup_git_repo "code-simplification-proactive") ... - cd "$test_dir" + cd "$test_dir" || return 1 ... - local response=$(run_claude "$prompt" 90) + local response + response=$(run_claude "$prompt" 90)
93-140: Apply same robustness fixes intest_time_pressure_skip.Lines 95, 117, and 124 have the same declare/assign and
cdsafety issues. Apply the same pattern suggested above.docs/learnings/implemented/2026-01-15-investigate-before-categorizing-test-failures.md (1)
51-57: Code block language identifier mismatch.The code block is labeled as
bashbut contains a markdown-style checklist, not executable bash commands. Consider changing to a plain code block or usingmarkdownas the identifier.Suggested fix
-```bash +``` # Before categorizing, check: - Does the missing file exist elsewhere? - Is the path correct? - Are permissions correct? - Is the environment correct?lib/meta-learning-state.js (2)
6-6: Consider fallback for undefinedHOMEenvironment variable.
process.env.HOMEcan be undefined on Windows (whereUSERPROFILEis typically used) or in certain containerized environments. This could cause the path to resolve toundefined/.claude/meta-learning-state.json.Suggested fix
-const STATE_FILE = path.join(process.env.HOME, '.claude', 'meta-learning-state.json'); +const HOME = process.env.HOME || process.env.USERPROFILE || require('os').homedir(); +const STATE_FILE = path.join(HOME, '.claude', 'meta-learning-state.json');
8-18: Add defensive defaults when loading state.If the file contains valid JSON but is missing expected fields (e.g.,
{"foo": "bar"}), accessingstate.countwill returnundefined, which could cause issues (e.g.,undefined++producesNaN).Suggested fix
function loadState() { if (!fs.existsSync(STATE_FILE)) { return { count: 0, lastReview: null }; } try { - return JSON.parse(fs.readFileSync(STATE_FILE, 'utf8')); + const loaded = JSON.parse(fs.readFileSync(STATE_FILE, 'utf8')); + return { + count: typeof loaded.count === 'number' ? loaded.count : 0, + lastReview: loaded.lastReview || null + }; } catch (e) { // If file is corrupted, return default state return { count: 0, lastReview: null }; } }docs/learnings/2026-01-27-ai-self-reflection-should-distinguish-project-vs-skill-learnings-and-act-accordingly.md (1)
118-118: Consider using a proper heading instead of bold emphasis.Static analysis flagged this line for using emphasis (
**...**) as a heading. Using a proper Markdown heading (####) improves document structure and accessibility.Suggested fix
-**New Step 3: Show Summary with Categorization** +#### New Step 3: Show Summary with Categorizationskills/meta-learning-review/SKILL.md (1)
29-42: Add language identifiers to fenced code blocks.Multiple code blocks in this file lack language specifiers (lines 30, 64, 94, 115, 132, 146, 167, 218). While the bash blocks are correctly labeled, the output/template blocks should specify a language (e.g.,
text,json, or leave as empty string for plain text).Example fixes:
- Line 30: Keep as
bash(correct)- Lines 64, 132, 146: Use
textormarkdownfor template content- Lines 94, 115: Use
jsonfor JSON output examplesCLAUDE.md (1)
101-123: Consider noting that paths are examples.The testing commands use hardcoded paths like
~/Dev/superpowers. Since contributors may have different setups, consider adding a note that these paths should be adjusted to their local installation, or use relative paths where possible (e.g.,cd tests/claude-code).skills/meta-learning-review/lib/learning-analyzer.js (1)
49-55: Prefer fs traversal over shelling out tofind.
The currentexecSync('find …')approach is POSIX-specific and less idiomatic for Node CLIs. Consider a fs-based implementation for portability.♻️ Suggested refactor
function findLearnings() { try { - const result = execSync( - `find ${LEARNINGS_DIR} -maxdepth 1 -name "*.md" -type f 2>/dev/null`, - { encoding: 'utf8' } - ); - return result.trim().split('\n').filter(Boolean); + return fs.readdirSync(LEARNINGS_DIR, { withFileTypes: true }) + .filter(d => d.isFile() && d.name.endsWith('.md')) + .map(d => path.join(LEARNINGS_DIR, d.name)); } catch { return []; } }tests/claude-code/run-skill-tests.sh (1)
25-53: Code duplication with test-helpers.sh.This
run_with_timeout()function is identical to the one intests/claude-code/test-helpers.sh(lines 5-31). Consider sourcingtest-helpers.shhere instead of duplicating the implementation.♻️ Proposed refactor to eliminate duplication
-# Portable timeout function -# Works on Linux (timeout), macOS with coreutils (gtimeout), or falls back to basic implementation -run_with_timeout() { - local timeout_duration=$1 - shift - - if command -v timeout &> /dev/null; then - timeout "$timeout_duration" "$@" - elif command -v gtimeout &> /dev/null; then - gtimeout "$timeout_duration" "$@" - else - # Basic timeout fallback for macOS without coreutils - # Run command in background and kill if it exceeds timeout - "$@" & - local pid=$! - local count=0 - while kill -0 $pid 2>/dev/null && [ $count -lt $timeout_duration ]; do - sleep 1 - count=$((count + 1)) - done - if kill -0 $pid 2>/dev/null; then - kill -TERM $pid 2>/dev/null - wait $pid 2>/dev/null - return 124 # timeout exit code - fi - wait $pid - return $? - fi -} +# Source shared test helpers (includes run_with_timeout) +source "$SCRIPT_DIR/test-helpers.sh"docs/learnings/implemented/2026-01-14-ai-self-reflection-requires-following-documented-workflow.md (1)
46-53: Add language specifier to fenced code block.The code block showing the suggested CLAUDE.md addition should have a language specifier for consistency and proper rendering.
📝 Proposed fix
-``` +```markdown ## Skill Execution Discipline When using any skill via Skill tool: 1. Read the entire SKILL.md first 2. Follow documented steps exactly (don't improvise) 3. Check "Success Criteria" section to verify completion 4. For rigid skills (workflows), every step is mandatory</details> </blockquote></details> <details> <summary>tests/claude-code/test-ai-self-reflection.sh (1)</summary><blockquote> `1-3`: **Minor: Inconsistent shebang.** Other test scripts use `#!/usr/bin/env bash` (e.g., `test-subagent-driven-development.sh` line 1), but this file uses `#!/bin/bash`. Consider using `#!/usr/bin/env bash` for consistency and better portability. <details> <summary>📝 Proposed fix</summary> ```diff -#!/bin/bash +#!/usr/bin/env bashdocs/plans/completed/2026-01-14-ai-self-reflection.md (1)
24-27: Optional: Add language specifiers to code blocks.Static analysis flagged code blocks without language specifiers (e.g., lines 26, 53). While this is documentation, adding
bashormarkdownspecifiers would improve rendering consistency.skills/finishing-a-development-branch/SKILL.md (1)
30-42: Optional: Add language specifiers to prompt/output code blocks.Several code blocks showing user prompts/outputs lack language specifiers. For consistency, consider using
textor leaving a brief comment. This is a low-priority nitpick for skill documentation.Also applies to: 167-179
docs/plans/completed/2026-01-11-finishing-workflow-enhancements.md (2)
22-28: Prefer headings over bold “Step” labels.markdownlint flags MD036 here; converting to headings improves structure and avoids lint failures. Apply consistently across the file.
♻️ Example adjustment
-**Step 1: Read the current skill content** +#### Step 1: Read the current skill content
30-72: Add language identifiers to fenced blocks.markdownlint flags MD040 on the unlabeled blocks (e.g., the prompt text). Use
text,bash, ormarkdownas appropriate, and apply consistently across the doc.♻️ Example adjustment
-``` +```text ⚠️ You have uncommitted changes: [Show git status output] What would you like to do? ... Which option? -``` +```
Comment on lines
+34
to
+37
| aws lambda invoke \ | ||
| --function-name calendar-prep-schedule-manager \ | ||
| --payload '{"action":"GET","userId":"[email protected]"}' | ||
|
|
There was a problem hiding this comment.
Redact personal email from the example payload.
The command embeds a real email address, which is PII and shouldn’t live in shared docs. Replace with a placeholder value.
🛠️ Proposed fix
- --payload '{"action":"GET","userId":"[email protected]"}'
+ --payload '{"action":"GET","userId":"[email protected]"}'📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| aws lambda invoke \ | |
| --function-name calendar-prep-schedule-manager \ | |
| --payload '{"action":"GET","userId":"pieter.portauw@gmail.com"}' | |
| aws lambda invoke \ | |
| --function-name calendar-prep-schedule-manager \ | |
| --payload '{"action":"GET","userId":"user@example.com"}' |
🤖 Prompt for AI Agents
In
`@docs/learnings/2026-01-23-running-actual-aws-cli-commands-to-verify-infrastructure-state-provides-concrete-evidence-that-assumptions-and-documentation-cannot.md`
around lines 34 - 37, The example AWS CLI invocation embeds a real email in the
JSON payload; replace the PII in the payload (the "userId" value used with the
function name calendar-prep-schedule-manager) with a non-sensitive placeholder
(e.g., "[email protected]" or "<USER_EMAIL>") so the command still demonstrates
usage but contains no personal data; update only the payload string in the shown
aws lambda invoke example.
Comment on lines
+30
to
+68
| if [ -f ~/Dev/superpowers/skills/ai-self-reflection/SKILL.md ]; then | ||
| echo " [PASS] Skill file exists" | ||
| else | ||
| echo " [FAIL] Skill file not found" | ||
| exit 1 | ||
| fi | ||
|
|
||
| if grep -q "^name: ai-self-reflection" ~/Dev/superpowers/skills/ai-self-reflection/SKILL.md; then | ||
| echo " [PASS] Has correct name in frontmatter" | ||
| else | ||
| echo " [FAIL] Missing or incorrect name in frontmatter" | ||
| exit 1 | ||
| fi | ||
|
|
||
| if grep -q "user-correction\|backtracking\|repeated-error" ~/Dev/superpowers/skills/ai-self-reflection/SKILL.md; then | ||
| echo " [PASS] Contains mistake type definitions" | ||
| else | ||
| echo " [FAIL] Missing mistake type definitions" | ||
| exit 1 | ||
| fi | ||
|
|
||
| echo "" | ||
|
|
||
| # Test 3: Verify command file exists | ||
| echo "Test 3: Command file..." | ||
|
|
||
| if [ -f ~/Dev/superpowers/commands/ai-self-reflection.md ]; then | ||
| echo " [PASS] Command file exists" | ||
| else | ||
| echo " [FAIL] Command file not found" | ||
| exit 1 | ||
| fi | ||
|
|
||
| if grep -q "REQUIRED SUB-SKILL.*ai-self-reflection" ~/Dev/superpowers/commands/ai-self-reflection.md; then | ||
| echo " [PASS] Command references skill correctly" | ||
| else | ||
| echo " [FAIL] Command missing skill reference" | ||
| exit 1 | ||
| fi |
There was a problem hiding this comment.
Hardcoded paths break portability.
The paths ~/Dev/superpowers/ are hardcoded throughout Tests 2 and 3. This will fail for contributors who clone the repository to a different location.
Use the repository root relative to SCRIPT_DIR instead:
🐛 Proposed fix - use relative paths
+# Derive repo root from script location
+REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
+
# Test 2: Verify skill file exists and has correct structure
echo "Test 2: Skill file structure..."
-if [ -f ~/Dev/superpowers/skills/ai-self-reflection/SKILL.md ]; then
+if [ -f "$REPO_ROOT/skills/ai-self-reflection/SKILL.md" ]; then
echo " [PASS] Skill file exists"
else
echo " [FAIL] Skill file not found"
exit 1
fi
-if grep -q "^name: ai-self-reflection" ~/Dev/superpowers/skills/ai-self-reflection/SKILL.md; then
+if grep -q "^name: ai-self-reflection" "$REPO_ROOT/skills/ai-self-reflection/SKILL.md"; then
echo " [PASS] Has correct name in frontmatter"
else
echo " [FAIL] Missing or incorrect name in frontmatter"
exit 1
fi
-if grep -q "user-correction\|backtracking\|repeated-error" ~/Dev/superpowers/skills/ai-self-reflection/SKILL.md; then
+if grep -q "user-correction\|backtracking\|repeated-error" "$REPO_ROOT/skills/ai-self-reflection/SKILL.md"; then
echo " [PASS] Contains mistake type definitions"
# ... and similar for remaining paths🤖 Prompt for AI Agents
In `@tests/claude-code/test-ai-self-reflection.sh` around lines 30 - 68, Tests use
hardcoded paths like ~/Dev/superpowers/ which breaks portability; update the
script to compute project-root-relative paths once (e.g., set a SKILL_DIR and
COMMAND_DIR based on SCRIPT_DIR or repo root) and replace all occurrences of
"~/Dev/superpowers/skills/ai-self-reflection/SKILL.md" and
"~/Dev/superpowers/commands/ai-self-reflection.md" in the file-existence and
grep checks with those variables so Test 2 and Test 3 use repository-relative
paths; ensure the grep patterns (e.g., "name: ai-self-reflection",
"user-correction\|backtracking\|repeated-error", and "REQUIRED
SUB-SKILL.*ai-self-reflection") still reference the same filenames/variables.
Comment on lines
+4
to
+31
| # Portable timeout function | ||
| # Works on Linux (timeout), macOS with coreutils (gtimeout), or falls back to basic implementation | ||
| run_with_timeout() { | ||
| local timeout_duration=$1 | ||
| shift | ||
|
|
||
| if command -v timeout &> /dev/null; then | ||
| timeout "$timeout_duration" "$@" | ||
| elif command -v gtimeout &> /dev/null; then | ||
| gtimeout "$timeout_duration" "$@" | ||
| else | ||
| # Basic timeout fallback for macOS without coreutils | ||
| # Run command in background and kill if it exceeds timeout | ||
| "$@" & | ||
| local pid=$! | ||
| local count=0 | ||
| while kill -0 $pid 2>/dev/null && [ $count -lt $timeout_duration ]; do | ||
| sleep 1 | ||
| count=$((count + 1)) | ||
| done | ||
| if kill -0 $pid 2>/dev/null; then | ||
| kill -TERM $pid 2>/dev/null | ||
| wait $pid 2>/dev/null | ||
| return 124 # timeout exit code | ||
| fi | ||
| wait $pid | ||
| return $? | ||
| fi |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
# Check if the file exists and show the function
fd test-helpers.sh -type f | head -5Repository: obra/superpowers
Length of output: 230
🏁 Script executed:
# Find all calls to run_with_timeout with various patterns
rg -n "run_with_timeout" --type sh -A 1 -B 1Repository: obra/superpowers
Length of output: 1396
🏁 Script executed:
# Specifically look for calls with timeout suffixes (s, m, h)
rg -n "run_with_timeout\s+" --type sh -A 1 | head -30Repository: obra/superpowers
Length of output: 615
🏁 Script executed:
# Check where TIMEOUT variable is defined in run-skill-tests.sh
rg -n "TIMEOUT\s*=" tests/claude-code/run-skill-tests.sh -B 2 -A 2Repository: obra/superpowers
Length of output: 289
🏁 Script executed:
# Check where timeout variable is defined in test-helpers.sh around line 49
rg -n "timeout=" tests/claude-code/test-helpers.sh -B 5 -A 2Repository: obra/superpowers
Length of output: 334
🏁 Script executed:
# Show the run-skill-tests.sh script to find TIMEOUT assignment
cat tests/claude-code/run-skill-tests.sh | head -100Repository: obra/superpowers
Length of output: 3120
Standardize timeout format support across all code paths.
The run_with_timeout function delegates to timeout or gtimeout, both of which accept suffixes like 30s or 1m. However, the fallback path assumes a pure integer and will error on -lt if a suffix is passed. Although current call sites only use integers (e.g., TIMEOUT=300, timeout=60), this creates an API inconsistency—callers passing timeout "30s" would work on Linux but fail on macOS without coreutils. Normalize the input to support or reject suffixes explicitly.
Suggested fix
else
+ # Normalize timeout for fallback (supports Ns/Nm/Nh like coreutils timeout)
+ local timeout_seconds="$timeout_duration"
+ if [[ "$timeout_seconds" =~ ^([0-9]+)s$ ]]; then
+ timeout_seconds="${BASH_REMATCH[1]}"
+ elif [[ "$timeout_seconds" =~ ^([0-9]+)m$ ]]; then
+ timeout_seconds=$((BASH_REMATCH[1] * 60))
+ elif [[ "$timeout_seconds" =~ ^([0-9]+)h$ ]]; then
+ timeout_seconds=$((BASH_REMATCH[1] * 3600))
+ elif [[ ! "$timeout_seconds" =~ ^[0-9]+$ ]]; then
+ echo "Unsupported timeout format: $timeout_duration" >&2
+ return 2
+ fi
# Basic timeout fallback for macOS without coreutils
# Run command in background and kill if it exceeds timeout
"$@" &
local pid=$!
local count=0
- while kill -0 $pid 2>/dev/null && [ $count -lt $timeout_duration ]; do
+ while kill -0 $pid 2>/dev/null && [ $count -lt $timeout_seconds ]; do
sleep 1
count=$((count + 1))
done📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| # Portable timeout function | |
| # Works on Linux (timeout), macOS with coreutils (gtimeout), or falls back to basic implementation | |
| run_with_timeout() { | |
| local timeout_duration=$1 | |
| shift | |
| if command -v timeout &> /dev/null; then | |
| timeout "$timeout_duration" "$@" | |
| elif command -v gtimeout &> /dev/null; then | |
| gtimeout "$timeout_duration" "$@" | |
| else | |
| # Basic timeout fallback for macOS without coreutils | |
| # Run command in background and kill if it exceeds timeout | |
| "$@" & | |
| local pid=$! | |
| local count=0 | |
| while kill -0 $pid 2>/dev/null && [ $count -lt $timeout_duration ]; do | |
| sleep 1 | |
| count=$((count + 1)) | |
| done | |
| if kill -0 $pid 2>/dev/null; then | |
| kill -TERM $pid 2>/dev/null | |
| wait $pid 2>/dev/null | |
| return 124 # timeout exit code | |
| fi | |
| wait $pid | |
| return $? | |
| fi | |
| # Portable timeout function | |
| # Works on Linux (timeout), macOS with coreutils (gtimeout), or falls back to basic implementation | |
| run_with_timeout() { | |
| local timeout_duration=$1 | |
| shift | |
| if command -v timeout &> /dev/null; then | |
| timeout "$timeout_duration" "$@" | |
| elif command -v gtimeout &> /dev/null; then | |
| gtimeout "$timeout_duration" "$@" | |
| else | |
| # Normalize timeout for fallback (supports Ns/Nm/Nh like coreutils timeout) | |
| local timeout_seconds="$timeout_duration" | |
| if [[ "$timeout_seconds" =~ ^([0-9]+)s$ ]]; then | |
| timeout_seconds="${BASH_REMATCH[1]}" | |
| elif [[ "$timeout_seconds" =~ ^([0-9]+)m$ ]]; then | |
| timeout_seconds=$((BASH_REMATCH[1] * 60)) | |
| elif [[ "$timeout_seconds" =~ ^([0-9]+)h$ ]]; then | |
| timeout_seconds=$((BASH_REMATCH[1] * 3600)) | |
| elif [[ ! "$timeout_seconds" =~ ^[0-9]+$ ]]; then | |
| echo "Unsupported timeout format: $timeout_duration" >&2 | |
| return 2 | |
| fi | |
| # Basic timeout fallback for macOS without coreutils | |
| # Run command in background and kill if it exceeds timeout | |
| "$@" & | |
| local pid=$! | |
| local count=0 | |
| while kill -0 $pid 2>/dev/null && [ $count -lt $timeout_seconds ]; do | |
| sleep 1 | |
| count=$((count + 1)) | |
| done | |
| if kill -0 $pid 2>/dev/null; then | |
| kill -TERM $pid 2>/dev/null | |
| wait $pid 2>/dev/null | |
| return 124 # timeout exit code | |
| fi | |
| wait $pid | |
| return $? | |
| fi | |
| } |
🤖 Prompt for AI Agents
In `@tests/claude-code/test-helpers.sh` around lines 4 - 31, The fallback in
run_with_timeout treats timeout_duration as an integer but timeout/gtimeout
accept suffixed values (e.g., "30s", "1m"), causing inconsistent behavior;
update run_with_timeout to normalize timeout_duration up front: parse the input
string (timeout_duration) to convert suffixes s/m/h to an integer seconds value
(store in a new timeout_seconds variable) and reject unsupported formats with a
clear error, then use timeout_seconds in the fallback loop and comparisons (keep
passing the original string to timeout/gtimeout branches so their suffixes still
work); reference run_with_timeout, timeout_duration, and timeout_seconds when
applying the change.
Comment on lines
+3
to
+109
| source "$(dirname "$0")/test-helpers.sh" | ||
|
|
||
| echo "=== Test: meta-learning integration ===" | ||
| echo "" | ||
|
|
||
| # Test 1: Verify learning directory can be created | ||
| echo "Test 1: Create learning directory..." | ||
|
|
||
| mkdir -p ~/Dev/superpowers/docs/learnings | ||
|
|
||
| # Create 5 YAML learnings (pattern threshold = 3) | ||
| for i in {1..5}; do | ||
| cat > ~/Dev/superpowers/docs/learnings/2026-01-0${i}-yaml-${i}.md << EOF | ||
| --- | ||
| date: 2026-01-0${i} | ||
| tags: [yaml, debugging] | ||
| workflow: systematic-debugging | ||
| --- | ||
|
|
||
| # YAML Issue ${i} | ||
|
|
||
| Sample learning content for YAML debugging. | ||
| EOF | ||
| done | ||
|
|
||
| echo " [PASS] Learning directory created with 5 learnings" | ||
| echo "" | ||
|
|
||
| # Test 2: Verify pattern detection | ||
| echo "Test 2: Pattern detection in analyzer..." | ||
|
|
||
| output=$(cd ~/Dev/superpowers && node skills/meta-learning-review/lib/learning-analyzer.js analyze 2>&1) | ||
|
|
||
| if assert_contains "$output" "yaml" "Analyzer detects yaml tag"; then | ||
| : # pass | ||
| else | ||
| rm -rf ~/Dev/superpowers/docs/learnings | ||
| exit 1 | ||
| fi | ||
|
|
||
| if assert_contains "$output" '"count": 5' "Analyzer counts 5 learnings"; then | ||
| : # pass | ||
| else | ||
| rm -rf ~/Dev/superpowers/docs/learnings | ||
| exit 1 | ||
| fi | ||
|
|
||
| echo "" | ||
|
|
||
| # Test 3: Verify meta-learning-review skill identifies patterns in learnings | ||
| echo "Test 3: Meta-learning-review skill analysis..." | ||
|
|
||
| # Instead of asking Claude to use the skill, directly test the analyzer | ||
| output=$(cd ~/Dev/superpowers && node skills/meta-learning-review/lib/learning-analyzer.js patterns 2>&1) | ||
|
|
||
| # Verify the analyzer detects the yaml pattern with 5 learnings | ||
| if assert_contains "$output" "yaml" "Analyzer detects yaml pattern"; then | ||
| : # pass | ||
| else | ||
| rm -rf ~/Dev/superpowers/docs/learnings | ||
| exit 1 | ||
| fi | ||
|
|
||
| # Verify the count is exactly 5 | ||
| if assert_contains "$output" '"count": 5' "Analyzer reports 5 yaml learnings"; then | ||
| : # pass | ||
| else | ||
| rm -rf ~/Dev/superpowers/docs/learnings | ||
| exit 1 | ||
| fi | ||
|
|
||
| echo "" | ||
|
|
||
| # Test 4: Verify compound-learning skill is discoverable with accurate description | ||
| echo "Test 4: Compound-learning skill discovery..." | ||
|
|
||
| output=$(run_claude "What is the compound-learning skill? Describe its purpose briefly." 30) | ||
|
|
||
| # Verify the skill's actual purpose: capturing/knowledge and learnings | ||
| if assert_contains "$output" "knowledge.*capture\|capture.*knowledge\|learning" "Skill purpose is accurately described"; then | ||
| : # pass | ||
| else | ||
| rm -rf ~/Dev/superpowers/docs/learnings | ||
| exit 1 | ||
| fi | ||
|
|
||
| echo "" | ||
|
|
||
| # Test 5: Verify verification-before-completion skill integrates learning capture | ||
| echo "Test 5: Verification-before-completion learning integration..." | ||
|
|
||
| # Directly verify the skill content mentions compound-learning | ||
| output=$(cat ~/Dev/superpowers/skills/verification-before-completion/SKILL.md 2>&1) | ||
|
|
||
| # Verify it mentions the compound-learning skill as the mechanism for capturing | ||
| if assert_contains "$output" "compound-learning" "Mentions compound-learning for capturing"; then | ||
| : # pass | ||
| else | ||
| rm -rf ~/Dev/superpowers/docs/learnings | ||
| exit 1 | ||
| fi | ||
|
|
||
| echo "" | ||
| echo "=== All integration tests passed ===" | ||
|
|
||
| # Cleanup | ||
| rm -rf ~/Dev/superpowers/docs/learnings |
There was a problem hiding this comment.
Replace hard-coded paths and destructive cleanup.
This test assumes ~/Dev/superpowers and deletes docs/learnings on failure. That’s brittle and can remove real data. Use repo-root detection and clean only the files created by this test.
🔧 Suggested fix
source "$(dirname "$0")/test-helpers.sh"
+ROOT_DIR="$(cd "$(dirname "$0")/../.."; pwd)"
+LEARNINGS_DIR="$ROOT_DIR/docs/learnings"
+TEST_FILES=()
+cleanup() { rm -f "${TEST_FILES[@]}"; }
+trap cleanup EXIT
...
-mkdir -p ~/Dev/superpowers/docs/learnings
+mkdir -p "$LEARNINGS_DIR"
for i in {1..5}; do
- cat > ~/Dev/superpowers/docs/learnings/2026-01-0${i}-yaml-${i}.md << EOF
+ file="$LEARNINGS_DIR/2026-01-0${i}-yaml-${i}.md"
+ TEST_FILES+=("$file")
+ cat > "$file" << EOF
...
done
-output=$(cd ~/Dev/superpowers && node skills/meta-learning-review/lib/learning-analyzer.js analyze 2>&1)
+output=$(cd "$ROOT_DIR" && node skills/meta-learning-review/lib/learning-analyzer.js analyze 2>&1)
...
- rm -rf ~/Dev/superpowers/docs/learnings
exit 1
...
-output=$(cd ~/Dev/superpowers && node skills/meta-learning-review/lib/learning-analyzer.js patterns 2>&1)
+output=$(cd "$ROOT_DIR" && node skills/meta-learning-review/lib/learning-analyzer.js patterns 2>&1)
...
- rm -rf ~/Dev/superpowers/docs/learnings
exit 1
...
-output=$(cat ~/Dev/superpowers/skills/verification-before-completion/SKILL.md 2>&1)
+output=$(cat "$ROOT_DIR/skills/verification-before-completion/SKILL.md" 2>&1)
...
-# Cleanup
-rm -rf ~/Dev/superpowers/docs/learnings
+# Cleanup handled by trap🤖 Prompt for AI Agents
In `@tests/claude-code/test-meta-learning-integration.sh` around lines 3 - 109,
The test script uses hard-coded ~/Dev/superpowers paths and performs destructive
rm -rf on docs/learnings; change it to discover the repo root (e.g.,
REPO_ROOT="$(git -C "$(dirname "$0")/.." rev-parse --show-toplevel" or
REPO_ROOT="$(cd "$(dirname "$0")/.."; pwd)") and create a dedicated temp test
folder under the repo (e.g., TEST_LEARNINGS="$REPO_ROOT/test-temp-learnings"),
update all occurrences of ~/Dev/superpowers/docs/learnings to use
$TEST_LEARNINGS, and update calls that cd into the project (cd
~/Dev/superpowers) to use $REPO_ROOT; add a trap cleanup function that only
removes $TEST_LEARNINGS on exit/failure (and remove any unconditional rm -rf of
~/Dev/superpowers/docs/learnings), and ensure the test uses TEST_LEARNINGS when
invoking learning-analyzer.js and when checking SKILL.md so you only delete the
files this test created.
Comment on lines
+3
to
+90
| source "$(dirname "$0")/test-helpers.sh" | ||
|
|
||
| echo "=== Test: meta-learning-review skill ===" | ||
| echo "" | ||
|
|
||
| # Test 1: Verify skill can be loaded | ||
| echo "Test 1: Skill loading..." | ||
|
|
||
| output=$(run_claude "What is the meta-learning-review skill? Describe its key steps briefly." 30) | ||
|
|
||
| if assert_contains "$output" "meta-learning-review" "Skill is recognized"; then | ||
| : # pass | ||
| else | ||
| exit 1 | ||
| fi | ||
|
|
||
| if assert_contains "$output" "pattern\|analyze\|learning" "Mentions key concepts"; then | ||
| : # pass | ||
| else | ||
| exit 1 | ||
| fi | ||
|
|
||
| echo "" | ||
|
|
||
| # Test 2: Verify skill describes stale learning handling | ||
| echo "Test 2: Stale learning handling..." | ||
|
|
||
| output=$(run_claude "In the meta-learning-review skill, how are stale learnings handled? What is the time threshold?" 30) | ||
|
|
||
| if assert_contains "$output" "6.*month\|stale\|archive" "Mentions 6 month threshold"; then | ||
| : # pass | ||
| else | ||
| exit 1 | ||
| fi | ||
|
|
||
| echo "" | ||
|
|
||
| # Test 3: Verify pattern detection threshold is mentioned | ||
| echo "Test 3: Pattern detection threshold..." | ||
|
|
||
| output=$(run_claude "What is the threshold for detecting patterns in the meta-learning-review skill?" 30) | ||
|
|
||
| if assert_contains "$output" "3.*learning\|three\|threshold" "Mentions 3+ learnings threshold"; then | ||
| : # pass | ||
| else | ||
| exit 1 | ||
| fi | ||
|
|
||
| echo "" | ||
|
|
||
| # Test 4: Verify learning analyzer script works | ||
| echo "Test 4: Learning analyzer execution..." | ||
|
|
||
| mkdir -p ~/Dev/superpowers/docs/learnings | ||
|
|
||
| for i in 1 2 3; do | ||
| cat > ~/Dev/superpowers/docs/learnings/2026-01-0${i}-yaml-issue.md << MDEOF | ||
| --- | ||
| date: 2026-01-0${i} | ||
| tags: [yaml, debugging] | ||
| workflow: systematic-debugging | ||
| --- | ||
|
|
||
| # YAML Issue $i | ||
|
|
||
| Sample learning content. | ||
| MDEOF | ||
| done | ||
|
|
||
| output=$(cd ~/Dev/superpowers && node skills/meta-learning-review/lib/learning-analyzer.js analyze 2>&1) | ||
|
|
||
| if assert_contains "$output" "yaml" "Analyzer detects yaml tag"; then | ||
| : # pass | ||
| else | ||
| exit 1 | ||
| fi | ||
|
|
||
| if assert_contains "$output" '"count": 3' "Analyzer counts 3 learnings"; then | ||
| : # pass | ||
| else | ||
| exit 1 | ||
| fi | ||
|
|
||
| echo "" | ||
| echo "=== All tests passed ===" | ||
|
|
||
| # Cleanup | ||
| rm -rf ~/Dev/superpowers/docs/learnings |
There was a problem hiding this comment.
Remove hard-coded repo path and avoid deleting the whole learnings directory.
The script assumes ~/Dev/superpowers and rm -rf nukes docs/learnings, which can break CI and wipe real data. Use the script’s repo root and clean only test files.
🔧 Suggested fix
source "$(dirname "$0")/test-helpers.sh"
+ROOT_DIR="$(cd "$(dirname "$0")/../.."; pwd)"
+LEARNINGS_DIR="$ROOT_DIR/docs/learnings"
+TEST_FILES=()
+cleanup() { rm -f "${TEST_FILES[@]}"; }
+trap cleanup EXIT
...
-mkdir -p ~/Dev/superpowers/docs/learnings
+mkdir -p "$LEARNINGS_DIR"
for i in 1 2 3; do
- cat > ~/Dev/superpowers/docs/learnings/2026-01-0${i}-yaml-issue.md << MDEOF
+ file="$LEARNINGS_DIR/2026-01-0${i}-yaml-issue.md"
+ TEST_FILES+=("$file")
+ cat > "$file" << MDEOF
...
done
-output=$(cd ~/Dev/superpowers && node skills/meta-learning-review/lib/learning-analyzer.js analyze 2>&1)
+output=$(cd "$ROOT_DIR" && node skills/meta-learning-review/lib/learning-analyzer.js analyze 2>&1)
...
-# Cleanup
-rm -rf ~/Dev/superpowers/docs/learnings
+# Cleanup handled by trap📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| source "$(dirname "$0")/test-helpers.sh" | |
| echo "=== Test: meta-learning-review skill ===" | |
| echo "" | |
| # Test 1: Verify skill can be loaded | |
| echo "Test 1: Skill loading..." | |
| output=$(run_claude "What is the meta-learning-review skill? Describe its key steps briefly." 30) | |
| if assert_contains "$output" "meta-learning-review" "Skill is recognized"; then | |
| : # pass | |
| else | |
| exit 1 | |
| fi | |
| if assert_contains "$output" "pattern\|analyze\|learning" "Mentions key concepts"; then | |
| : # pass | |
| else | |
| exit 1 | |
| fi | |
| echo "" | |
| # Test 2: Verify skill describes stale learning handling | |
| echo "Test 2: Stale learning handling..." | |
| output=$(run_claude "In the meta-learning-review skill, how are stale learnings handled? What is the time threshold?" 30) | |
| if assert_contains "$output" "6.*month\|stale\|archive" "Mentions 6 month threshold"; then | |
| : # pass | |
| else | |
| exit 1 | |
| fi | |
| echo "" | |
| # Test 3: Verify pattern detection threshold is mentioned | |
| echo "Test 3: Pattern detection threshold..." | |
| output=$(run_claude "What is the threshold for detecting patterns in the meta-learning-review skill?" 30) | |
| if assert_contains "$output" "3.*learning\|three\|threshold" "Mentions 3+ learnings threshold"; then | |
| : # pass | |
| else | |
| exit 1 | |
| fi | |
| echo "" | |
| # Test 4: Verify learning analyzer script works | |
| echo "Test 4: Learning analyzer execution..." | |
| mkdir -p ~/Dev/superpowers/docs/learnings | |
| for i in 1 2 3; do | |
| cat > ~/Dev/superpowers/docs/learnings/2026-01-0${i}-yaml-issue.md << MDEOF | |
| --- | |
| date: 2026-01-0${i} | |
| tags: [yaml, debugging] | |
| workflow: systematic-debugging | |
| --- | |
| # YAML Issue $i | |
| Sample learning content. | |
| MDEOF | |
| done | |
| output=$(cd ~/Dev/superpowers && node skills/meta-learning-review/lib/learning-analyzer.js analyze 2>&1) | |
| if assert_contains "$output" "yaml" "Analyzer detects yaml tag"; then | |
| : # pass | |
| else | |
| exit 1 | |
| fi | |
| if assert_contains "$output" '"count": 3' "Analyzer counts 3 learnings"; then | |
| : # pass | |
| else | |
| exit 1 | |
| fi | |
| echo "" | |
| echo "=== All tests passed ===" | |
| # Cleanup | |
| rm -rf ~/Dev/superpowers/docs/learnings | |
| source "$(dirname "$0")/test-helpers.sh" | |
| ROOT_DIR="$(cd "$(dirname "$0")/../.."; pwd)" | |
| LEARNINGS_DIR="$ROOT_DIR/docs/learnings" | |
| TEST_FILES=() | |
| cleanup() { rm -f "${TEST_FILES[@]}"; } | |
| trap cleanup EXIT | |
| echo "=== Test: meta-learning-review skill ===" | |
| echo "" | |
| # Test 1: Verify skill can be loaded | |
| echo "Test 1: Skill loading..." | |
| output=$(run_claude "What is the meta-learning-review skill? Describe its key steps briefly." 30) | |
| if assert_contains "$output" "meta-learning-review" "Skill is recognized"; then | |
| : # pass | |
| else | |
| exit 1 | |
| fi | |
| if assert_contains "$output" "pattern\|analyze\|learning" "Mentions key concepts"; then | |
| : # pass | |
| else | |
| exit 1 | |
| fi | |
| echo "" | |
| # Test 2: Verify skill describes stale learning handling | |
| echo "Test 2: Stale learning handling..." | |
| output=$(run_claude "In the meta-learning-review skill, how are stale learnings handled? What is the time threshold?" 30) | |
| if assert_contains "$output" "6.*month\|stale\|archive" "Mentions 6 month threshold"; then | |
| : # pass | |
| else | |
| exit 1 | |
| fi | |
| echo "" | |
| # Test 3: Verify pattern detection threshold is mentioned | |
| echo "Test 3: Pattern detection threshold..." | |
| output=$(run_claude "What is the threshold for detecting patterns in the meta-learning-review skill?" 30) | |
| if assert_contains "$output" "3.*learning\|three\|threshold" "Mentions 3+ learnings threshold"; then | |
| : # pass | |
| else | |
| exit 1 | |
| fi | |
| echo "" | |
| # Test 4: Verify learning analyzer script works | |
| echo "Test 4: Learning analyzer execution..." | |
| mkdir -p "$LEARNINGS_DIR" | |
| for i in 1 2 3; do | |
| file="$LEARNINGS_DIR/2026-01-0${i}-yaml-issue.md" | |
| TEST_FILES+=("$file") | |
| cat > "$file" << MDEOF | |
| --- | |
| date: 2026-01-0${i} | |
| tags: [yaml, debugging] | |
| workflow: systematic-debugging | |
| --- | |
| # YAML Issue $i | |
| Sample learning content. | |
| MDEOF | |
| done | |
| output=$(cd "$ROOT_DIR" && node skills/meta-learning-review/lib/learning-analyzer.js analyze 2>&1) | |
| if assert_contains "$output" "yaml" "Analyzer detects yaml tag"; then | |
| : # pass | |
| else | |
| exit 1 | |
| fi | |
| if assert_contains "$output" '"count": 3' "Analyzer counts 3 learnings"; then | |
| : # pass | |
| else | |
| exit 1 | |
| fi | |
| echo "" | |
| echo "=== All tests passed ===" | |
| # Cleanup handled by trap |
🤖 Prompt for AI Agents
In `@tests/claude-code/test-meta-learning-review.sh` around lines 3 - 90, The
script currently hard-codes ~/Dev/superpowers and uses rm -rf to delete
docs/learnings; change it to create a temporary test learnings directory under
the repo root (use the variable provided by test-helpers.sh, e.g., $REPO_ROOT or
$SCRIPT_DIR) instead of ~/Dev/superpowers, update the analyzer invocation to cd
"$REPO_ROOT" && node skills/meta-learning-review/lib/learning-analyzer.js
analyze, and replace the global rm -rf ~/Dev/superpowers/docs/learnings with a
safe cleanup that only removes the temp test files (e.g., trap cleanup;
cleanup() { rm -rf "$REPO_ROOT/tests/tmp_learnings"; } ) so only test artifacts
are deleted.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
Consolidated 19 overlapping learnings into 10 comprehensive files (47% reduction), then implemented all patterns into 5 skills.
📊 Learning Consolidation
Before: 19 active learnings with significant overlap
After: 10 active learnings
5 New Consolidated Files:
workflow-discipline-follow-chains-suggest-proactively-never-skip-steps.md(from 3)evidence-before-assertions-always-verify-with-concrete-commands.md(from 3)thorough-upfront-analysis-mental-models-interactions-scope-impact.md(from 3)validation-architecture-add-immediately-validate-before-persistence.md(from 2)proactive-cleanup-scan-for-redundant-artifacts-after-changes.md(from 2)14 Files Archived: Moved to
docs/learnings/implemented/🎯 Skills Enhanced
1. ai-self-reflection - Categorization system
categoryfield to learning files2. using-superpowers - Workflow discipline
3. verification-before-completion - Evidence-based verification
4. brainstorming - Upfront analysis
5. requesting-code-review - Self-review checklist
Test Plan
Files Changed
🤖 Generated with Claude Code
Summary by CodeRabbit
New Features
/simplifycommand for improving code readability/ai-self-reflectioncommand for session analysis/review-learnings,/retrospective, and/compoundcommandsImprovements
Documentation
✏️ Tip: You can customize this high-level summary in your review settings.