Agent skill

opi

Extract learnings from recent git commits and current conversation. Analyzes fixes, refactors, and corrections to propose entries for learnings files. Use when: - User says "/opi" or "opi" - "What did we learn?" - "Extract learnings" - "Update learnings" - End of session reflection Triggers: "opi", "learn", "oppia", "mitä opittiin", "extract learnings"

View SKILL.md on GitHub Repository
Stars 163
Forks 31

Install this agent skill to your Project

npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/opi

SKILL.md

Opi - Learning Extractor

Automatically extract learnings from recent work to improve future Claude sessions.

Workflow

Step 1: Gather Sources

Run these commands to collect learning material:

bash
# Recent commits (last 20)
git log --oneline -20

# Today's commits with details
git log --since="midnight" --format="%h %s"

# Commits with "fix", "korjaus", "refactor"
git log --oneline -50 | grep -iE "(fix|korja|refactor|bugfix)"

Step 2: Analyze Fix Commits

For each fix/refactor commit, examine what changed:

bash
git show <commit-hash> --stat
git show <commit-hash> -- "*.tsx" "*.ts"  # Code changes

Look for patterns:

  • What was wrong? (the bug/issue)
  • What fixed it? (the solution)
  • Why? (root cause)

Step 3: Check Current Conversation

Review current conversation for:

  • User corrections ("ei, tee näin..." / "no, do it this way...")
  • Failed attempts that were fixed
  • Non-obvious solutions discovered
  • Repeated patterns

Step 4: Categorize Learnings

Determine where each learning belongs:

Learning Type Destination
React/TypeScript pattern .claude/LEARNINGS.md
Supabase/DB pattern .claude/LEARNINGS.md
CI/CD specific ci-doctor/references/learnings.md
Lint specific lint-fixer/references/learnings.md
Test specific test-writer/references/learnings.md
Skill-specific [skill]/references/learnings.md

Step 5: Propose Learnings

Format each learning proposal:

markdown
## Proposed Learning

**Source:** commit abc123 / conversation
**Category:** [Global / Skill-specific]
**File:** [target file path]

### [Issue Title]
- **Pattern:** What triggers this
- **Wrong:** ❌ The incorrect approach
- **Right:** ✅ The correct approach
- **Why:** Root cause

Step 6: Get Approval & Write

  1. Present all proposed learnings to user
  2. User approves/rejects each
  3. Write approved learnings to appropriate files
  4. Commit changes

Learning Quality Criteria

Only propose learnings that are:

  • Non-obvious - Claude wouldn't know this without being told
  • Actionable - Can be applied in future situations
  • Specific - Has concrete wrong/right examples
  • Recurring - Likely to come up again

Skip:

  • Typo fixes
  • One-off configuration issues
  • Project-specific constants
  • Things Claude already knows

Example Session

User: /opi

Claude: Let me analyze recent commits...

Found 3 potential learnings:

1. **useCallback for useEffect deps** (commit a1b2c3)
   - Source: AdminTranslationsPage infinite loop fix
   - File: .claude/LEARNINGS.md
   - Pattern: Functions in useEffect deps cause re-renders

2. **GitHub API dismiss format** (commit d4e5f6)
   - Source: CodeQL alert dismissal
   - File: ci-doctor/references/learnings.md
   - Pattern: Use "false positive" not "false_positive"

3. **Controlled Tabs state** (conversation)
   - Source: Feedback popup tab fix
   - File: .claude/LEARNINGS.md
   - Pattern: Radix Tabs need value+onValueChange for control

Add these learnings? [Y/n for each]

Commands Reference

bash
# Commits since specific date
git log --since="2025-01-10" --oneline

# Commits by pattern
git log --all --oneline | grep -i "fix"

# Show specific commit
git show <hash> --name-only

# Diff for a commit
git diff <hash>^..<hash>

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

majiayu000/claude-skill-registry

agent-ops-spec

Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.

163 31
Explore
majiayu000/claude-skill-registry

agent-ops-state

Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.

163 31
Explore
majiayu000/claude-skill-registry

agent-ops-spec

Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.

163 31
Explore
majiayu000/claude-skill-registry

agent-ops-testing

Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.

163 31
Explore
majiayu000/claude-skill-registry

agent-ops-testing

Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.

163 31
Explore
majiayu000/claude-skill-registry

agent-ops-state

Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.

163 31
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results