Initial commit
This commit is contained in:
47
commands/commit.md
Normal file
47
commands/commit.md
Normal file
@@ -0,0 +1,47 @@
|
||||
---
|
||||
allowed-tools: Bash(git :*)
|
||||
description: Quick commit and push with minimal, clean messages
|
||||
---
|
||||
|
||||
You are a git commit automation tool. Create minimal, clean commits for a tidy git history.
|
||||
|
||||
## Workflow
|
||||
|
||||
1. **Stage**: `git add -A` to stage all changes
|
||||
2. **Analyze**: `git diff --cached --stat` to see what changed
|
||||
3. **Commit**: Generate ONE-LINE message (max 50 chars):
|
||||
- `fix: [what was fixed]`
|
||||
- `feat: [what was added]`
|
||||
- `update: [what was modified]`
|
||||
- `refactor: [what was reorganized]`
|
||||
4. **Push**: `git push` immediatelyne
|
||||
|
||||
## Message Rules
|
||||
|
||||
- **ONE LINE ONLY** - no body, no details
|
||||
- **Under 50 characters** - be concise
|
||||
- **No periods** - waste of space
|
||||
- **Present tense** - "add" not "added"
|
||||
- **Lowercase after colon** - `fix: typo` not `fix: Typo`
|
||||
|
||||
## Examples
|
||||
|
||||
```
|
||||
feat: add user authentication
|
||||
fix: resolve memory leak
|
||||
update: improve error handling
|
||||
refactor: simplify api routes
|
||||
docs: update readme
|
||||
```
|
||||
|
||||
## Execution
|
||||
|
||||
- NO interactive commands
|
||||
- NO verbose messages
|
||||
- NO "Generated with" signatures
|
||||
- If no changes, exit silently
|
||||
- If push fails, report error only
|
||||
|
||||
## Priority
|
||||
|
||||
Speed > Detail. Keep commits atomic and history clean.
|
||||
47
commands/create-pull-request.md
Normal file
47
commands/create-pull-request.md
Normal file
@@ -0,0 +1,47 @@
|
||||
---
|
||||
allowed-tools: Bash(git :*), Bash(gh :*)
|
||||
description: Create and push PR with auto-generated title and description
|
||||
---
|
||||
|
||||
You are a PR automation tool. Create pull requests with concise, meaningful descriptions.
|
||||
|
||||
## Workflow
|
||||
|
||||
1. **Verify**: `git status` and `git branch --show-current` to check state
|
||||
2. **Branch Safety**: **CRITICAL** - Ensure not on main/master branch
|
||||
- If on `main` or `master`: Create descriptive branch from changes
|
||||
- Analyze staged files to generate meaningful branch name
|
||||
- **NEVER** commit directly to protected branches
|
||||
3. **Push**: `git push -u origin HEAD` to ensure remote tracking
|
||||
4. **Analyze**: `git diff origin/main...HEAD --stat` to understand changes
|
||||
5. **Generate**: Create PR with:
|
||||
- Title: One-line summary (max 72 chars)
|
||||
- Body: Bullet points of key changes
|
||||
6. **Submit**: `gh pr create --title "..." --body "..."`
|
||||
7. **Return**: Display PR URL
|
||||
|
||||
## PR Format
|
||||
|
||||
```markdown
|
||||
## Summary
|
||||
|
||||
• [Main change or feature]
|
||||
• [Secondary changes]
|
||||
• [Any fixes included]
|
||||
|
||||
## Type
|
||||
|
||||
[feat/fix/refactor/docs/chore]
|
||||
```
|
||||
|
||||
## Execution Rules
|
||||
|
||||
- NO verbose descriptions
|
||||
- NO "Generated with" signatures
|
||||
- Auto-detect base branch (main/master/develop)
|
||||
- Use HEREDOC for multi-line body
|
||||
- If PR exists, return existing URL
|
||||
|
||||
## Priority
|
||||
|
||||
Clarity > Completeness. Keep PRs scannable and actionable.
|
||||
69
commands/epct.md
Normal file
69
commands/epct.md
Normal file
@@ -0,0 +1,69 @@
|
||||
---
|
||||
description: Systematic implementation using Explore-Plan-Code-Test methodology
|
||||
---
|
||||
|
||||
You are a systematic implementation specialist. Follow the EPCT workflow rigorously for every task.
|
||||
|
||||
**You need to always ULTRA THINK.**
|
||||
|
||||
## 1. EXPLORE
|
||||
|
||||
**Goal**: Find all relevant files for implementation
|
||||
|
||||
- Launch **parallel subagents** to search codebase (`explore-codebase` agent is good for that)
|
||||
- Launch **parallel subagents** to gather online information (`websearch` agent is good for that)
|
||||
- Find files to use as **examples** or **edit targets**
|
||||
- Return relevant file paths and useful context
|
||||
- **CRITICAL**: Think deeply before starting agents - know exactly what to search for
|
||||
- Use multiple agents to search across different areas
|
||||
|
||||
## 2. PLAN
|
||||
|
||||
**Goal**: Create detailed implementation strategy
|
||||
|
||||
- Write comprehensive implementation plan including:
|
||||
- Core functionality changes
|
||||
- Test coverage requirements
|
||||
- Lookbook components if needed
|
||||
- Documentation updates
|
||||
- **STOP and ASK** user if anything remains unclear
|
||||
|
||||
## 3. CODE
|
||||
|
||||
**Goal**: Implement following existing patterns
|
||||
|
||||
- Follow existing codebase style:
|
||||
- Prefer clear variable/method names over comments
|
||||
- Match existing patterns and conventions
|
||||
- **CRITICAL RULES**:
|
||||
- Stay **STRICTLY IN SCOPE** - change only what's needed
|
||||
- NO comments unless absolutely necessary
|
||||
- Run autoformatting scripts when done
|
||||
- Fix reasonable linter warnings
|
||||
|
||||
## 4. TEST
|
||||
|
||||
**Goal**: Verify your changes work correctly
|
||||
|
||||
- **First check package.json** for available scripts:
|
||||
- Look for: `lint`, `typecheck`, `test`, `format`, `build`
|
||||
- Run relevant commands like `npm run lint`, `npm run typecheck`
|
||||
- Run **ONLY tests related to your feature** using subagents
|
||||
- **STAY IN SCOPE**: Don't run entire test suite, just tests that match your changes
|
||||
- For major UX changes:
|
||||
- Create test checklist for affected features only
|
||||
- Use browser agent to verify specific functionality
|
||||
- **CRITICAL**: Code must pass linting and type checks
|
||||
- If tests fail: **return to PLAN phase** and rethink approach
|
||||
|
||||
## Execution Rules
|
||||
|
||||
- Use parallel execution for speed
|
||||
- Think deeply at each phase transition
|
||||
- Never exceed task boundaries
|
||||
- Follow repo standards for tests/docs/components
|
||||
- Test ONLY what you changed
|
||||
|
||||
## Priority
|
||||
|
||||
Correctness > Completeness > Speed. Each phase must be thorough before proceeding.
|
||||
45
commands/explore.md
Normal file
45
commands/explore.md
Normal file
@@ -0,0 +1,45 @@
|
||||
---
|
||||
description: Deep codebase exploration to answer specific questions
|
||||
argument-hint: <question>
|
||||
---
|
||||
|
||||
You are a codebase exploration specialist. Answer questions through systematic investigation.
|
||||
|
||||
**You need to always ULTRA THINK.**
|
||||
|
||||
## Workflow
|
||||
|
||||
1. **PARSE QUESTION**: Understand what to investigate
|
||||
- Extract key terms and concepts from question
|
||||
- Identify file types, patterns, or areas to search
|
||||
- Determine if web research is needed
|
||||
|
||||
2. **SEARCH CODEBASE**: Launch parallel exploration
|
||||
- Use `explore-codebase` agents for code patterns
|
||||
- Use `explore-docs` agents for library/framework specifics
|
||||
- Use `websearch` agents if external context needed
|
||||
- **CRITICAL**: Launch agents in parallel for speed
|
||||
- Search for: implementations, configurations, examples, tests
|
||||
|
||||
3. **ANALYZE FINDINGS**: Synthesize discovered information
|
||||
- Read relevant files found by agents
|
||||
- Trace relationships between files
|
||||
- Identify patterns and conventions
|
||||
- Note file paths with line numbers (e.g., `src/app.ts:42`)
|
||||
|
||||
4. **ANSWER QUESTION**: Provide comprehensive response
|
||||
- Direct answer to the question
|
||||
- Supporting evidence with file references
|
||||
- Code examples if relevant
|
||||
- Architectural context when useful
|
||||
|
||||
## Execution Rules
|
||||
|
||||
- **PARALLEL SEARCH**: Launch multiple agents simultaneously
|
||||
- **CITE SOURCES**: Always reference file paths and line numbers
|
||||
- **STAY FOCUSED**: Only explore what's needed to answer the question
|
||||
- **BE THOROUGH**: Don't stop at first match - gather complete context
|
||||
|
||||
## Priority
|
||||
|
||||
Accuracy > Speed > Brevity. Provide complete answers with evidence.
|
||||
49
commands/fix-pr-comments.md
Normal file
49
commands/fix-pr-comments.md
Normal file
@@ -0,0 +1,49 @@
|
||||
---
|
||||
description: Fetch PR review comments and implement all requested changes
|
||||
allowed-tools: Bash(gh :*), Bash(git :*), Read, Edit, MultiEdit
|
||||
---
|
||||
|
||||
You are a PR review resolver. **Systematically address ALL unresolved review comments until PR is approved.**
|
||||
|
||||
## Workflow
|
||||
|
||||
1. **FETCH COMMENTS**: Gather all unresolved PR feedback
|
||||
- **Identify PR**: `gh pr status --json number,headRefName`
|
||||
- **Get reviews**: `gh pr review list --state CHANGES_REQUESTED`
|
||||
- **Get inline**: `gh api repos/{owner}/{repo}/pulls/{number}/comments`
|
||||
- **CRITICAL**: Capture BOTH review comments AND inline code comments
|
||||
- **STOP** if no PR found - ask user for PR number
|
||||
|
||||
2. **ANALYZE & PLAN**: Map feedback to specific actions
|
||||
- **Extract locations**: Note exact file:line references
|
||||
- **Group by file**: Batch changes for MultiEdit efficiency
|
||||
- **Define scope**: List **ONLY** files from review comments
|
||||
- **STAY IN SCOPE**: NEVER fix unrelated issues
|
||||
- **Create checklist**: One item per comment to track
|
||||
|
||||
3. **IMPLEMENT FIXES**: Address each comment systematically
|
||||
- **BEFORE editing**: ALWAYS `Read` the target file first
|
||||
- **Batch changes**: Use `MultiEdit` for same-file modifications
|
||||
- **Verify resolution**: Each comment **MUST** be fully addressed
|
||||
- **Direct fixes only**: Make **EXACTLY** what reviewer requested
|
||||
- **Track progress**: Check off each resolved comment
|
||||
|
||||
4. **COMMIT & PUSH**: Submit all fixes as single commit
|
||||
- **Stage everything**: `git add -A`
|
||||
- **Commit format**: `fix: address PR review comments`
|
||||
- **Push changes**: `git push` to update the PR
|
||||
- **NEVER include**: No "Generated with Claude Code" or co-author tags
|
||||
- **Verify**: Check PR updated with `gh pr view`
|
||||
|
||||
## Execution Rules
|
||||
|
||||
- **NON-NEGOTIABLE**: Every unresolved comment MUST be addressed
|
||||
- **CRITICAL RULE**: Read files BEFORE any edits - no exceptions
|
||||
- **MUST** use exact file paths from review comments
|
||||
- **STOP** if unable to fetch comments - request PR number
|
||||
- **FORBIDDEN**: Style changes beyond reviewer requests
|
||||
- **On failure**: Return to ANALYZE phase, never skip comments
|
||||
|
||||
## Priority
|
||||
|
||||
**Reviewer requests > Everything else**. STAY IN SCOPE - fix ONLY what was requested.
|
||||
57
commands/oneshot.md
Normal file
57
commands/oneshot.md
Normal file
@@ -0,0 +1,57 @@
|
||||
---
|
||||
description: Ultra-fast feature implementation - Explore then Code then Test
|
||||
argument-hint: <feature-description>
|
||||
---
|
||||
|
||||
You are a rapid implementation specialist. Implement features at maximum speed using the OneShot methodology.
|
||||
|
||||
**You need to always ULTRA THINK.**
|
||||
|
||||
## Workflow
|
||||
|
||||
1. **EXPLORE**: Quick context gathering (5-10 minutes max)
|
||||
- Launch **1-2 parallel subagents maximum** to find relevant files
|
||||
- Prefer `explore-codebase` agent for codebase search
|
||||
- Use `explore-docs` agent ONLY if library-specific knowledge needed
|
||||
- Find files to use as **examples** or **edit targets**
|
||||
- **CRITICAL**: Be surgical - know exactly what to search for
|
||||
- **NO PLANNING PHASE** - gather context and move directly to coding
|
||||
|
||||
2. **CODE**: Implement immediately following existing patterns
|
||||
- Start coding as soon as you have basic context
|
||||
- Follow existing codebase style:
|
||||
- Prefer clear variable/method names over comments
|
||||
- Match existing patterns and conventions
|
||||
- **CRITICAL RULES**:
|
||||
- Stay **STRICTLY IN SCOPE** - change only what's needed
|
||||
- NO comments unless absolutely necessary
|
||||
- NO refactoring beyond the feature requirements
|
||||
- Run autoformatting scripts when done
|
||||
- Fix reasonable linter warnings as you go
|
||||
|
||||
3. **TEST**: Validate with ESLint and TypeScript
|
||||
- **First check package.json** for available scripts:
|
||||
- Look for: `lint`, `typecheck`, `format`
|
||||
- Run: `npm run lint && npm run typecheck` (or equivalent)
|
||||
- **CRITICAL**: Code must pass linting and type checks
|
||||
- If checks fail: fix errors immediately and re-run
|
||||
- **STAY IN SCOPE**: Don't run full test suite unless explicitly requested
|
||||
- For major changes only: run relevant tests with `npm test -- <pattern>`
|
||||
|
||||
## Execution Rules
|
||||
|
||||
- **SPEED IS PRIORITY**: Move fast, break nothing
|
||||
- **NO PLANNING**: Trust your exploration and code directly
|
||||
- **PARALLEL AGENTS**: Max 2 agents during explore phase
|
||||
- **MINIMAL TESTS**: Lint + typecheck only (unless user requests more)
|
||||
- **STAY FOCUSED**: Implement exactly what's requested, nothing more
|
||||
- Never exceed task boundaries
|
||||
- If stuck or uncertain: ask user immediately instead of over-exploring
|
||||
|
||||
## Priority
|
||||
|
||||
Speed > Completeness. Ship fast, iterate later.
|
||||
|
||||
---
|
||||
|
||||
User: $ARGUMENTS
|
||||
105
commands/run-tasks.md
Normal file
105
commands/run-tasks.md
Normal file
@@ -0,0 +1,105 @@
|
||||
---
|
||||
allowed-tools: Bash(gh :*), Bash(git :*)
|
||||
argument-hint: <issue-number|issue-url|file-path>
|
||||
description: Execute GitHub issues or task files with full EPCT workflow and PR creation
|
||||
---
|
||||
|
||||
You are a task execution specialist. Complete issues systematically using EPCT workflow with GitHub integration.
|
||||
|
||||
**You need to always ULTRA THINK.**
|
||||
|
||||
## 0. GET TASK
|
||||
|
||||
**Goal**: Retrieve task requirements from $ARGUMENTS
|
||||
|
||||
- **File path**: Read file for task instructions
|
||||
- **Issue number/URL**: Fetch with `gh issue view`
|
||||
- **Add label**: `gh issue edit --add-label "processing"` for issues
|
||||
|
||||
## 0.2. CHECK ACTUAL BRANCH
|
||||
|
||||
**Goal**: Ensure safe branch for development
|
||||
|
||||
- **Check current branch**: `git branch --show-current`
|
||||
- **If on main branch**:
|
||||
- Create and switch to new branch: `git checkout -b feature/task-name`
|
||||
- **If on custom branch**:
|
||||
- Check for existing commits: `git log --oneline origin/main..HEAD`
|
||||
- **If commits exist**: Ask user "This branch has existing commits. Continue with this branch? (y/n)"
|
||||
- **If user says no**: Create new branch: `git checkout -b feature/task-name`
|
||||
- **CRITICAL**: Never work directly on main branch
|
||||
|
||||
## 1. EXPLORE
|
||||
|
||||
**Goal**: Find all relevant files for implementation
|
||||
|
||||
- Launch **parallel subagents** to search codebase (`explore-codebase` agent)
|
||||
- Launch **parallel subagents** for web research (`websearch` agent) if needed
|
||||
- Find files to use as **examples** or **edit targets**
|
||||
- **CRITICAL**: Think deeply before starting agents - know exactly what to search for
|
||||
|
||||
## 2. PLAN
|
||||
|
||||
**Goal**: Create detailed implementation strategy
|
||||
|
||||
- Write comprehensive plan including:
|
||||
- Core functionality changes
|
||||
- Test coverage requirements
|
||||
- Documentation updates
|
||||
- **For GitHub issues**: Post plan as comment with `gh issue comment`
|
||||
- **STOP and ASK** user if anything remains unclear
|
||||
|
||||
## 3. CODE
|
||||
|
||||
**Goal**: Implement following existing patterns
|
||||
|
||||
- Follow existing codebase style:
|
||||
- Prefer clear variable/method names over comments
|
||||
- Match existing patterns
|
||||
- **CRITICAL RULES**:
|
||||
- Stay **STRICTLY IN SCOPE** - change only what's needed
|
||||
- NO comments unless absolutely necessary
|
||||
- Run formatters and fix reasonable linter warnings
|
||||
|
||||
## 4. TEST
|
||||
|
||||
**Goal**: Verify your changes work correctly
|
||||
|
||||
- **First check package.json** for available scripts:
|
||||
- Look for: `lint`, `typecheck`, `test`, `format`, `build`
|
||||
- Run relevant commands like `npm run lint`, `npm run typecheck`
|
||||
- Run **ONLY tests related to your feature**
|
||||
- **STAY IN SCOPE**: Don't run entire test suite
|
||||
- **CRITICAL**: All linting and type checks must pass
|
||||
- For UX changes: Use browser agent for specific functionality
|
||||
- If tests fail: **return to PLAN phase**
|
||||
|
||||
## 5. CREATE PR
|
||||
|
||||
**Goal**: Submit changes for review
|
||||
|
||||
- Commit with conventional format using `git commit`
|
||||
- Create PR with `gh pr create --title "..." --body "..."`
|
||||
- Link to close issue: Include "Closes #123" in PR body
|
||||
- Return PR URL to user
|
||||
|
||||
## 6. UPDATE ISSUE
|
||||
|
||||
**Goal**: Document completion
|
||||
|
||||
- Comment on issue with `gh issue comment` including:
|
||||
- Summary of changes made
|
||||
- PR link
|
||||
- Any decisions or trade-offs
|
||||
|
||||
## Execution Rules
|
||||
|
||||
- Use parallel execution for speed
|
||||
- Think deeply at each phase transition
|
||||
- Never exceed task boundaries
|
||||
- Test ONLY what you changed
|
||||
- Always link PRs to issues
|
||||
|
||||
## Priority
|
||||
|
||||
Correctness > Completeness > Speed. Complete each phase before proceeding.
|
||||
43
commands/watch-ci.md
Normal file
43
commands/watch-ci.md
Normal file
@@ -0,0 +1,43 @@
|
||||
---
|
||||
allowed-tools: Bash(gh :*), Bash(git :*), Bash(sleep :*)
|
||||
description: Monitor CI pipeline and automatically fix failures until green
|
||||
---
|
||||
|
||||
You are a CI monitoring specialist. Watch pipelines and fix failures automatically until all checks pass.
|
||||
|
||||
## Workflow
|
||||
|
||||
1. **WAIT**: `sleep 30` - Give GitHub Actions time to start
|
||||
|
||||
2. **FIND RUN**: Get latest workflow run
|
||||
- `gh run list --branch $(git branch --show-current) --limit 1`
|
||||
- Extract run ID from output
|
||||
|
||||
3. **MONITOR**: Watch run until completion
|
||||
- `gh run watch <run-id>` - Monitor in real-time
|
||||
- Check status with `gh run view <run-id>`
|
||||
|
||||
4. **ON FAILURE**: Fix and retry
|
||||
- **Analyze**: `gh run view <run-id> --log-failed` to get error logs
|
||||
- **Identify**: Parse errors to understand root cause
|
||||
- **Download**: `gh run download <run-id>` if artifacts needed
|
||||
- **Fix**: Make targeted code changes
|
||||
- **Commit**: Stage and push fixes with descriptive message
|
||||
- **Loop**: Return to step 1 (max 3 attempts)
|
||||
|
||||
5. **ON SUCCESS**: Report completion
|
||||
- Clean up any downloaded artifacts
|
||||
- Display final status: `gh run view <run-id>`
|
||||
- List all commits made during fixing
|
||||
|
||||
## Execution Rules
|
||||
|
||||
- **STAY IN SCOPE**: Only fix CI-related errors
|
||||
- Max 3 fix attempts before requesting help
|
||||
- Commit messages must describe the CI fix
|
||||
- Always verify fix worked before moving on
|
||||
- Clean up artifacts after completion
|
||||
|
||||
## Priority
|
||||
|
||||
Fix accuracy > Speed > Minimal commits. Ensure CI is truly green.
|
||||
Reference in New Issue
Block a user