What problem does it solve? Developers often write production code first and add tests afterward, which produces biased tests that pass immediately and prove nothing. This Skill enforces strict test-driven development so every feature, bug fix, and refactor starts with a failing test that verifies real behavior. ## Core Features & Use Cases - RED-GREEN-REFACTOR Enforcement: Guides the agent through writing one failing test, verifying the failure, writing minimal passing code, and refactoring safely. - Rationalization Detection: Lists common excuses ("too simple to test", "I'll test after") and red flags that signal TDD is being skipped, with instructions to delete code and restart. - Subagent Integration: Provides templates for delegating implementation tasks with TDD requirements embedded, and pairs with systematic debugging so every bug fix starts with a reproducing test. - Use Case: When asked to add a retry mechanism to an API client, the agent first writes a failing test asserting three retry attempts, watches it fail, implements the minimal retry logic, confirms the full suite passes, then refactors. ## Quick Start Ask the agent to implement a new feature or fix a bug using strict test-driven development with a failing test written first.
