Hyperwork tdd
Skill samrom3/claude-hyper-plugs/hyperloop/skills/hyperwork-tdd
Language-agnostic TDD discipline — red/green/refactor cycle. Fallback for unknown stack. Compose with language skills (hyperwork-python, hyperwork-typescript) for tooling specifics.From its SKILL.md
npx -y skills add samrom3/claude-hyper-plugs --skill hyperwork-tddAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
- runs commandsInstructs the agent to run 3 commands, including `pre-commit run --all-files` and 2 more.
SKILL.md
1.3 KB, 258 tokens by cl100k_base, as published. Nobody here has run it
TDD
Use: Any impl task. Compose with language skill for tooling. Standalone = fallback.
Cycle
- Write failing test first — defines expected behaviour.
- Implement minimum code → test passes.
- Refactor → still passes.
- Repeat per behaviour slice.
Adapting to Unknown Stack
- Read
CLAUDE.md+package.json/pyproject.toml/Makefile/Cargo.toml→ find test command. - Run existing tests first — confirm baseline green before touching anything.
- Match existing test file naming and structure exactly.
- No test framework present → note gap in PR description; write closest supported equivalent.
Verification Before Commit
Run project lint+test command (pre-commit run --all-files, make test, npm test, etc.). Must be green. No exceptions.
Do / Don't
- DO: test behaviour, not implementation details.
- DO: search existing tests before writing any — understand conventions first.
- DON'T: commit with failing tests.
- DON'T: invent new testing framework — use what's in the repo.
- DON'T: skip verification because stack is unfamiliar — investigate until green.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.