Tdd
Use when writing any implementation code - enforces Red-Green-Refactor cycle with no production code without a failing test firstFrom its SKILL.md
npx -y skills add mizzy/my-skills --skill 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
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 5 stars5 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.
SKILL.md
2.6 KB, as published. Nobody here has run it
TDD (Test-Driven Development)
Overview
Enforces Red-Green-Refactor. No production code without a failing test first.
Iron Law: NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST.
If you wrote code before a test, delete it and start over. No exceptions.
When to Use
- Called from pick-issue / codex to govern how implementation code is written
- Any time implementation code is being written
Opus does not hand-write implementation code — it delegates the writing to Codex (see the codex skill). Opus owns intent and review; Codex owns thorough execution. This skill is the Red-Green- Refactor discipline that the delegated code must follow. The Iron Law applies regardless of who types it: a failing test must precede the production code.
The Cycle
RED: Write a Failing Test
- Write one minimal test for the next behavior
- Run it and confirm it fails
- The failure message should clearly describe what's missing
GREEN: Write Minimal Code
- Write the simplest code that makes the test pass
- No extra features, no "while I'm here" improvements
- Run the test and confirm it passes
REFACTOR: Clean Up
- Remove duplication, improve names, extract helpers
- Run tests after every change — must stay green
- Stop when the code is clean enough, not perfect
Repeat
Move to the next behavior. One cycle at a time.
Language-Specific Setup
| Language | Test Command | Watch Mode |
|---|---|---|
| Rust | cargo test | cargo watch -x test |
| Go | go test ./... | - |
| Ruby | bundle exec rspec / bundle exec rake test | bundle exec guard |
| TypeScript | npx vitest run / npx jest | npx vitest |
Detect the project's actual test setup and use the appropriate command.
Forbidden Rationalizations
These are not valid reasons to skip the cycle:
| Excuse | Reality |
|---|---|
| "I'll write tests after" | A test that passes immediately proves nothing |
| "It's just a small change" | Small changes cause big bugs |
| "I already tested manually" | Manual testing is not reproducible |
| "This is too simple to test" | Then the test is trivial to write |
| "I need to see the code first" | The test IS the spec for the code |
Red Flags
If any of these happen, stop and restart the cycle:
- Production code exists without a preceding failing test
- Test was written after the implementation
- "Let me just get this working first"
- Multiple behaviors tested in one cycle