agentleFS
Sign inStart free
stevemarksavastevemarksava/superteam/skills/test-driven-development/SKILL.md

test-driven-development

Skill1 starsChanged 2 months agoMITView on GitHub

RED / GREEN / REFACTOR loop — write the failing test first, minimum code to green, then clean up. Adapted from obra/superpowers.

190 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use chinese-code-review, chinese-commit-conventions 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.
  • Leodorareluctant259Skill

    chinese-code-review

    中文代码审查规范——在保持专业严谨的同时，用符合国内团队文化的方式给出有效反馈

    Also in 8 projects that use this

  • Leodorareluctant259Skill

    chinese-commit-conventions

    中文 Git 提交规范 — 适配国内团队的 commit message 规范和 changelog 自动化

    Also in 8 projects that use this

  • obraSkill

    diagnosing-superpowers

    Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.

    Also in 19 projects that use this

  • LLl0k0laDSkill

    using-agent-skills

    Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.

    Also in 39 projects that use this

  • LLl0k0laDSkill

    git-workflow-and-versioning

    Use when making any code change. Use when committing, branching, resolving conflicts, or when you need to organize work across multiple parallel streams.

    Also in 47 projects that use this

  • MrCipherSmithSkill

    constraint-driven-development

    Use when a project needs a persistent, measurable quality bar — starting a project without documented standards, 'set up constraints', or when coverage/perf/a11y thresholds get re-debated per-PR. Produces CONSTRAINTS.md with enforceable numbers, ratchets, and a guard against silent weakening. NOT for throwaway prototypes or a one-off CI setup.

    Also in 15 projects that use this

  • +3 more from Leodorareluctant259
  • +3 more from LLl0k0laD

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 178 edited versions we read keep these.

  • 6

    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:

    GREEN — write minimum code to pass: Do the simplest thing that could possibly work.

    line 19
  2. Distinctive:

    Test file(s) committed alongside implementation

    line 26
  3. Distinctive:

    Every commit either RED→GREEN, GREEN→GREEN (refactor), or new RED

    line 27
  4. Distinctive:

    Never write production code without a failing test first

    line 31
  5. Distinctive:

    Never refactor with red tests

    line 32
  6. Distinctive:

    Never commit a test that has never been red — you have not verified the assertion

    line 33

“Common” is measured: kept by at least 6 in 10 of the 178 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

/test-driven-development — RED · GREEN · REFACTOR

TDD is a discipline, not a preference. Write the test before the code. Let the failing test drive the design. Refactor only when green. This produces code that is testable by construction and impossible to ship without coverage.

When to invoke

  • Building a new feature with a clear behavioural contract (input → output)
  • Fixing a bug — the reproducer test is written first (see /systematic-debugging)
  • Refactoring an untested area — write characterisation tests first, then refactor under green
  • Vera pushes back on coverage — this skill produces coverage as a side effect

Steps

  1. RED — write the failing test. Pick the smallest slice of behaviour. Write a test that expresses the intended behaviour. Run it. Confirm it fails for the right reason (assertion failure, not import error).
  2. GREEN — write minimum code to pass. Do the simplest thing that could possibly work. Hardcode if that gets you green. The goal is a working suite, not clever code. Run the test — confirm it passes.
  3. REFACTOR — clean up under green. With a green suite as your safety net, improve the code: rename, extract, deduplicate, tighten types. Run the tests after every meaningful change. If red, undo and try a smaller step.
  4. Repeat. Next behavioural slice — go back to RED. Iterate until the feature is complete.
  5. Coverage check. Confirm the test suite exercises the happy path, at least one error path, and any edge cases the spec calls out. Add missing cases as new RED cycles.
  6. Hand to Vera. Deliver with: test file paths, coverage summary, list of behaviours covered.

Deliverable format

  • Test file(s) committed alongside implementation
  • Every commit either RED→GREEN, GREEN→GREEN (refactor), or new RED
  • Coverage summary (percentage or explicit list of covered behaviours)

Non-negotiables

  • Never write production code without a failing test first
  • Never refactor with red tests
  • Never commit a test that has never been red — you have not verified the assertion
  • One behaviour per RED cycle — resist the urge to test two things at once

References

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.

Check your setup, free