What problem does it solve? Writing tests after implementation often produces brittle, implementation-coupled tests that break on refactors and fail to verify real behavior. This Skill enforces a disciplined red-green TDD loop so every test verifies observable behavior through public interfaces. ## Core Features & Use Cases - Red-Green Loop Rules: Enforces writing a failing test first, then only enough code to pass it, one vertical slice at a time. - Seam Identification: Requires agreeing on public test boundaries (seams) with the user before any test is written, focusing effort on critical paths. - Anti-Pattern Detection: Flags implementation-coupled, tautological, and horizontally-sliced tests with concrete good/bad examples in tests.md and mocking guidance in mocking.md. - Use Case: When adding a checkout feature, ask the assistant to build it test-first; it will confirm the seams, write one failing behavior test, implement the minimal code to pass, and repeat per slice. ## Quick Start Ask the assistant to build the next feature or fix the bug using test-driven development with the red-green loop.