lootlog/monorepo / .agents/skills/tdd
tdd
VerifiedDevelop a feature or fix a defect test-first when the user requests TDD or when a cheap, focused regression path already exists. Use for red-green-refactor, failing tests, regression coverage, and bugs with a practical Vitest, component, integration, or end-to-end seam.
Test-driven development
Make the intended behavior executable before changing production code.
Workflow
- Identify the intended behavior, current behavior, affected public seam, and smallest observable reproduction.
- Choose the narrowest existing test layer that can express the behavior. Prefer Vitest unit, component, or integration patterns already used by that workspace.
- Add one focused failing test. Assert behavior, not private implementation.
- Run it and confirm that it fails for the intended reason.
- Make the smallest production change that passes the test.
- Run the focused test again, then relevant adjacent tests, typecheck, and lint in proportion to the change.
- Refactor only while the tests remain green.
When a failing test is impractical
Do not build a large harness, mock most of the system, or introduce brittle timing merely to claim TDD. State why a focused failing test is not practical and use the closest executable check: a targeted script, an existing integration path, browser automation against the running app, a response assertion, or generated-output comparison.
Guardrails
- Do not change assertions to bless incorrect behavior.
- Do not test private functions when a public seam exists.
- Mock only boundaries that cannot run locally.
- Keep regression coverage specific to the defect.
- For flaky behavior, first make the signal deterministic or measure its reproduction rate.
Report
Name the failing-before evidence, the passing-after evidence, and every adjacent check performed. If no red test was practical, report the substitute evidence explicitly.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |