xiaohongshu
xiaohongshu
Systematic development workflow: Analyze → Plan → Execute → eLicit → eXamine. Use for ANY development task: features, bug fixes, refactoring, hotfixes. Triggers: "implement", "create", "build", "fix", "add feature", "refactor", "develop". Auto-detects project type (Laravel, Next.js, React, Swift)...
Full skill instructions
Current Task: $ARGUMENTS
Analyze → Plan → Execute → eLicit → eXamine
Complete development workflow for features, fixes, and refactoring.
BEFORE anything else, run this command to initialize APEX tracking:
mkdir -p .claude/apex/docs && cat > .claude/apex/task.json << 'INITEOF'
{
"current_task": "1",
"created_at": "'"$(date -u +"%Y-%m-%dT%H:%M:%SZ")"'",
"tasks": {
"1": {
"status": "in_progress",
"started_at": "'"$(date -u +"%Y-%m-%dT%H:%M:%SZ")"'",
"doc_consulted": {}
}
}
}
INITEOF
echo "✅ APEX tracking initialized in $(pwd)/.claude/apex/"
This creates:
.claude/apex/task.json - Tracks documentation consultation status.claude/apex/docs/ - Stores consulted documentation summariesThe PreToolUse hooks will BLOCK Write/Edit until documentation is consulted.
┌─────────────────────────────────────────────────────────────────┐
│ APEX WORKFLOW │
├─────────────────────────────────────────────────────────────────┤
│ 00-init-branch → Create feature branch │
│ 01-analyze-code → Understand codebase (A) │
│ 02-features-plan → Plan implementation (P) │
│ 03-execution → Write code (E) │
│ 03.5-elicit → Expert self-review (L) ← NEW │
│ 04-validation → Verify quality (X) │
│ 05-review → Self-review │
│ 06-fix-issue → Handle issues │
│ 07-add-test → Write tests │
│ 08-check-test → Run tests │
│ 09-create-pr → Create Pull Request │
└─────────────────────────────────────────────────────────────────┘
| Phase | File | Purpose |
|---|---|---|
| 00 | references/00-init-branch.md | Create feature branch |
| 01 | references/01-analyze-code.md | Explore + Research (APEX A) |
| 02 | references/02-features-plan.md | TodoWrite planning (APEX P) |
| 03 | references/03-execution.md | Implementation (APEX E) |
| 03.5 | references/03.5-elicit.md | Expert self-review (APEX L) ← NEW |
| 04 | references/04-validation.md | sniper validation (APEX X) |
| 05 | references/05-review.md | Self-review checklist |
| 06 | references/06-fix-issue.md | Fix validation/review issues |
| 07 | references/07-add-test.md | Write unit/integration tests |
| 08 | references/08-check-test.md | Run and verify tests |
| 09 | references/09-create-pr.md | Create and merge PR |
1. 00-init-branch → git checkout -b feature/xxx
2. 01-analyze-code → explore-codebase + research-expert
3. 02-features-plan → TodoWrite task breakdown
4. 03-execution → Implement (files <100 lines)
5. 03.5-elicit → Expert self-review (75 techniques) ← NEW
6. 04-validation → sniper agent
7. 07-add-test → Write tests
8. 08-check-test → Run tests
9. 05-review → Self-review
10. 09-create-pr → gh pr create
1. 00-init-branch → git checkout -b fix/xxx
2. 01-analyze-code → Understand bug context
3. 07-add-test → Write failing test FIRST
4. 03-execution → Fix the bug
5. 08-check-test → Verify test passes
6. 04-validation → sniper agent
7. 09-create-pr → gh pr create
1. 00-init-branch → git checkout -b hotfix/xxx
2. 03-execution → Minimal fix only
3. 04-validation → sniper agent
4. 08-check-test → Run tests
5. 09-create-pr → Urgent merge
🚨 STOP at 90 lines → Split immediately
❌ NEVER exceed 100 lines
📊 Target: 50-80 lines per file
✅ src/interfaces/ (global)
✅ src/types/ (type definitions)
✅ Contracts/ (PHP/Laravel)
❌ NEVER in component files
01-analyze: explore-codebase + research-expert (PARALLEL)
04-validate: sniper (MANDATORY after ANY change)
ALWAYS run 2 agents in parallel:
1. explore-codebase
→ Map project structure
→ Find existing patterns
→ Identify change locations
2. research-expert
→ Verify official documentation
→ Confirm API methods
→ Check best practices
ALWAYS use TodoWrite:
1. Break down into tasks
2. Each task <100 lines
3. Plan file splits FIRST
4. Map dependencies
FOLLOW plan strictly:
1. Create interfaces FIRST
2. Monitor file sizes
3. Write JSDoc/comments
4. Atomic commits
ALWAYS run sniper:
6-phase validation:
1. explore-codebase
2. research-expert
3. grep usages
4. run linters
5. apply fixes
6. ZERO errors
feature/ISSUE-123-short-description
fix/ISSUE-456-bug-name
hotfix/ISSUE-789-urgent-fix
refactor/ISSUE-321-cleanup
docs/ISSUE-654-readme
test/ISSUE-987-coverage
✅ Short-lived branches (1-3 days)
✅ Small, focused changes
✅ Sync frequently with main
✅ Squash and merge
<type>(<scope>): <description>
Types: feat, fix, refactor, docs, test, chore
Scope: component/feature name
Description: imperative mood, <50 chars
feat(auth): add JWT authentication
fix(cart): resolve quantity validation
refactor(api): extract fetch utilities
test(auth): add login component tests
□ sniper passes (ZERO errors)
□ All tests pass
□ Build succeeds
□ Self-review complete
□ No console.logs
□ No TODO unaddressed
□ Files <100 lines
□ Interfaces in correct location
□ JSDoc on all exports
□ No any types
□ Error handling complete
feat(auth): add social login with Google
fix(cart): resolve quantity update bug
refactor(api): extract fetch utilities
□ Summary (1-3 bullets)
□ Changes (added/modified/removed)
□ Related issues (Closes #xxx)
□ Test plan (checkboxes)
□ Screenshots (if UI changes)
START
│
▼
┌───────────────┐
│ 00-init-branch│
└───────┬───────┘
│
▼
┌───────────────┐
│ 01-analyze │ ← explore + research
└───────┬───────┘
│
▼
┌───────────────┐
│ 02-plan │ ← TodoWrite
└───────┬───────┘
│
▼
┌───────────────┐
│ 03-execute │ ← Write code
└───────┬───────┘
│
▼
┌───────────────┐
│ 04-validate │ ← sniper
└───────┬───────┘
│
┌───────┴───────┐
│ │
▼ ▼
┌──────────┐ ┌──────────┐
│ 06-fix │ │ 07-test │
└────┬─────┘ └────┬─────┘
│ │
└──────┬───────┘
│
▼
┌───────────────┐
│ 08-check-test │
└───────┬───────┘
│
▼
┌───────────────┐
│ 05-review │
└───────┬───────┘
│
▼
┌───────────────┐
│ 09-create-pr │
└───────┬───────┘
│
▼
DONE
❌ Skip explore-codebase or research-expert
❌ Assume API syntax without verification
❌ Create files >100 lines
❌ Put interfaces in component files
❌ Skip sniper after changes
❌ Merge without tests
❌ Large PRs (>400 lines)
All detailed guides in references/ directory:
references/
├── 00-init-branch.md # Branch creation
├── 01-analyze-code.md # Code analysis
├── 02-features-plan.md # Planning
├── 03-execution.md # Implementation
├── 04-validation.md # Validation
├── 05-review.md # Self-review
├── 06-fix-issue.md # Issue fixes
├── 07-add-test.md # Test writing
├── 08-check-test.md # Test running
└── 09-create-pr.md # PR creation
Framework-specific APEX methodology guides:
| Framework | Directory | Tools |
|---|---|---|
| Laravel | references/laravel/ | Pest, Larastan, Pint |
| Next.js | references/nextjs/ | Vitest, Playwright, ESLint |
| React | references/react/ | Vitest, Testing Library, Biome |
| Swift | references/swift/ | XCTest, SwiftLint, swift-format |
Project Type → References Used
─────────────────────────────────────
composer.json → references/laravel/
next.config.* → references/nextjs/
vite.config.* → references/react/
Package.swift → references/swift/
Default → references/ (generic)
references/[framework]/
├── 00-init-branch.md # Framework-specific branching
├── 01-analyze-code.md # Framework exploration tools
├── 02-features-plan.md # Planning patterns
├── 03-execution.md # SOLID implementation
├── 04-validation.md # Linters and formatters
├── 05-review.md # Framework checklist
├── 06-fix-issue.md # Common fixes
├── 07-add-test.md # Testing patterns
├── 08-check-test.md # Test commands
└── 09-create-pr.md # PR template
xiaohongshu
technical spec
product ux expert
database patterns
Conduct multi-agent task orchestration and workflow coordination.
Initialize project with Conductor artifacts (product definition,
Expert in web animations, transitions, and motion design using Framer Motion and CSS
Creates Mermaid and ASCII diagrams for flowcharts, architecture, ERDs, state machines, mindmaps, and more. Use when user mentions diagram, flowchart, mermaid, ASCII diagram, text diagram, terminal diagram, visualize, C4, mindmap, architecture diagram, sequence diagram, ERD, or needs visual docume...
PostgreSQL bindings for H3 hexagonal grid system. Use when working with H3 cells in Postgres, including spatial indexing, geometry/geography integration, and raster analysis.
Context-Driven Development skill for projects using Conductor. Use this skill when you detect a `conductor/` directory in the project, when working on tasks defined in a `plan.md` file, or when the user asks about tracks, specs, or plans. Automatically applies TDD workflow, tracks task completion...
Display project status, active tracks, and next actions
Official Stakpak application containerization standard operating procedure, a step-by-step guidline to properly dockerize applications. This is a rule book curated by the Stakpak Team.
Generate, edit, and beat-sync AI video with leading models in one workspace.
The world's fastest calendar for remote work
Transform Your Design with AI Designer by ImgCreator.ai
Revolutionizing Video Production with AI-Powered Creativity
Extend an image past the frame and let AI fill the new aspect ratio.
Discover your celebrity doppelgänger with StarByFace!
ChainClarity explains 700+ crypto whitepapers in plain English, with layered summaries, comparisons, research tools, alerts, and a $4.99 Pro plan.
Opus.ai: Revolutionize Your Web Experience