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 the red-green-refactor discipline 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: Define and confirm public test boundaries with the user before writing any test, keeping effort on critical paths. - Anti-Pattern Detection: Avoid implementation-coupled, tautological, and horizontally-sliced tests with concrete good/bad examples. - Mocking Guidelines: Mock only at system boundaries like external APIs, time, and randomness, never internal collaborators. - Use Case: When adding a checkout feature, ask the assistant to build it test-first; it will agree on seams with you, write a failing behavior test, implement the minimal code to pass, and repeat per slice. ## Quick Start Ask the assistant to implement a new feature or bug fix using test-driven development with the red-green-refactor loop.