test-first
Test-Driven Development (TDD Red-Green-Refactor)
git clone --depth 1 https://github.com/claude-world/director-mode-lite /tmp/test-first && cp -r /tmp/test-first/skills/test-first ~/.claude/skills/test-firstSKILL.md
# Test-Driven Development
Implement TDD for: $ARGUMENTS
## Quick Steps
1. Write a failing test
2. Run test, confirm failure
3. Write minimal code to pass
4. Refactor while keeping tests green
5. Repeat
---
## Red Phase - Write Failing Test
### Test Design Principles
- **Test one specific behavior**
- **Test name describes expected result**
- **Test should fail (feature doesn't exist yet)**
### Must Test
- [ ] Normal case
- [ ] Edge cases
- [ ] Error cases
- [ ] Invalid input
### Example
```typescript
// auth/login.test.ts
it('should return JWT token for valid credentials', async () => {
const res = await request(app)
.post('/auth/login')
.send({ email: 'test@example.com', password: 'password123' })
expect(res.status).toBe(200)
expect(res.body.token).toBeDefined()
})
```
---
## Green Phase - Minimal Implementation
### Implementation Principles
- **Write ONLY enough code to pass the test**
- **Don't optimize yet**
- **Don't worry about elegance**
- **Just make it work**
---
## Refactor Phase - Clean Up
### Refactoring Checklist
- [ ] Is there code duplication?
- [ ] Are variable names clear?
- [ ] Are functions too long?
- [ ] Is the logic too complex?
### Refactoring Rules
- **Keep tests passing**
- **Change one thing at a time**
- **Run tests frequently**
---
## Test Quality Checklist
- [ ] Unit tests cover core logic
- [ ] Integration tests cover interactions
- [ ] Test names clearly describe intent
- [ ] Tests are independent and repeatable
- [ ] Tests run fast (unit tests < 100ms)
- [ ] Edge cases are covered
---
Follow TDD strictly. No shortcuts.Track development session events in a daily markdown changelog, including file changes, test results, and key decisions.
Expert on creating and configuring custom Claude Code agents. Helps design specialized agents for project-specific tasks.
Expert on CLAUDE.md design patterns, best practices, and project configuration. Essential for project initialization and customization.
Code review specialist for quality, security, and best practices
Decision-making agent for Self-Evolving Loop. Evaluates validation results and decides next action (continue, evolve, or ship).
Debugging specialist for root cause analysis and problem resolution
Documentation specialist for README, API docs, and code comments
Lightweight orchestrator for Self-Evolving Loop with Meta-Engineering integration. Coordinates phases, manages memory, and handles lifecycle. Only returns brief summaries.