Red-Green-Refactor workflow. Write tests before implementation, maintain 80%+ coverage. Use when implementing logic, fixing bugs, or changing behavior.
npx claudepluginhub v1truv1us/ai-eng-system --plugin ai-eng-learningThis skill uses the workspace's default tool permissions.
Write a failing test first, then implement the minimum code to pass, then refactor. Tests are proof that the system behaves as intended. This is the canonical Build-phase testing skill.
Creates isolated Git worktrees for feature branches with prioritized directory selection, gitignore safety checks, auto project setup for Node/Python/Rust/Go, and baseline verification.
Executes implementation plans in current session by dispatching fresh subagents per independent task, with two-stage reviews: spec compliance then code quality.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
Write a failing test first, then implement the minimum code to pass, then refactor. Tests are proof that the system behaves as intended. This is the canonical Build-phase testing skill.
Tests should be Descriptive And Meaningful Phrases. Prefer readability over test-code abstraction. Duplication in test setup is acceptable when it makes the test self-contained.
If you liked it, you should have put a test on it. If behavior matters, a test should verify it.
it('should return 404 when user does not exist')it('works')Before writing tests, define the public interface:
| Rationalization | Reality |
|---|---|
| "I will add tests later" | Later never comes. Untested code is unverifiable code. |
| "TDD slows me down" | TDD slows down typing but speeds up delivery by reducing debugging time. |
| "This is too simple to test" | Simple code can have simple bugs. Simple tests are cheap to write. |
| "I need to implement first to know what to test" | Defining expected behavior first is exactly the point. |