agentleFS
kapadiaskapadias/nonna/.claude/skills/tdd/SKILL.md

tdd

Skill0 starsChanged 47 days agoMITView on GitHub

Run the test-driven cycle — RED (failing test) → GREEN (minimal code) → REFACTOR — for a unit of behavior. The default way to build anything in Nonna.

194 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use capture-learning-tools, design-frontend-dev and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 187 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No production logic without a test that would have failed before it.

    line 24
  2. Distinctive:

    Do not weaken or delete a test to get to green.

    line 25
  3. Distinctive:

    Keep the working tree green at each step.

    line 26

“Common” is measured: kept by at least 6 in 10 of the 187 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Build, test-first: $ARGUMENTS

The cycle

  1. RED — pin the behavior. Have test-engineer write the smallest test that fails for the right reason and captures the desired behavior. Confirm it fails before writing any production code — a test that passes immediately proves nothing. For core/critical logic, include a golden test (exact oracle value) and a property test (invariant over generated inputs). See .claude/rules/testing.md.
  2. GREEN — make it pass. Have implementer write the minimal code that passes the test. No speculative generality, no extra features. Run the test; see it pass.
  3. REFACTOR — clean up. With tests green as the safety net, improve names, remove duplication, and make the change match the surrounding code. Re-run the suite after each refactor.

Rules

  • No production logic without a test that would have failed before it.
  • Do not weaken or delete a test to get to green. If a test is wrong, fix it deliberately and say why.
  • Keep the working tree green at each step. Run lint + type-check + tests before handing off.

Output

The new/changed tests, the implementation, and a one-line note that the full suite is green. Hand off to /review when the behavior is complete.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.