What it does
A skill that makes the agent write a test first, watch it fail, and only then write the minimum code to make it pass. It applies to new features, bug fixes, refactoring and behavior changes, and treats code written before its test as something to redo.
Use cases
- 01Add a feature with a failing test written first
- 02Fix a bug with a test that reproduces it
- 03Refactor code while the tests stay green