What problem does it solve? Writing tests after implementation often produces brittle tests coupled to internal structure that break on every refactor. This Skill enforces a disciplined red-green TDD loop so tests verify observable behavior through public interfaces and survive code changes. ## Core Features & Use Cases - Red-Green Loop Rules: Write the failing test first, then only enough code to pass it, one vertical slice at a time. - Seam Identification: Agree on public interface boundaries with the user before writing any test, focusing effort on critical paths. - Anti-Pattern Detection: Avoid implementation-coupled, tautological, and horizontally-sliced tests using concrete good/bad examples in tests.md and mocking guidance in mocking.md. - Use Case: When adding a checkout feature, ask the AI to drive it test-first: it will confirm the seams with you, write one failing behavior test, implement the minimal code to pass, and repeat per slice. ## Quick Start Use the tdd skill to build the new shopping cart checkout feature test-first, one red-green cycle at a time.
