agentleFS
Sign inStart free
ovargasovargas/virtual-team/skills/test-driven-development/SKILL.md

test-driven-development

Skill14 starsChanged 8 months agoMITView on GitHub

Use when implementing any feature or bugfix, before writing implementation code — enforces red-green-refactor cycle with configurable strictness

190 other projects use a version of this, 1 of them edited.

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, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 178 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read stack.md and check the tdd: field.

    line 10
  2. Distinctive:

    Run the test. Confirm it fails for the expected reason (feature missing, not typo/error)

    line 42
  3. Distinctive:

    Write the simplest code to make the test pass.

    line 46
  4. Distinctive:

    Run the test. Confirm it passes.

    line 66
  5. Distinctive:

    Only after green: remove duplication, improve names, extract helpers.

    line 70
  6. Distinctive:

    Before marking any implementation step complete:

    line 88

“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

Mode Selection

Read stack.md and check the tdd: field. If the field is missing, default to recommended.

tdd: valueBehavior
strictIron law — no production code without a failing test. Delete and restart on violations.
recommendedTDD is the expected workflow. Warn when skipped, log the skip, but proceed.
offNo TDD enforcement. Tests are encouraged but not gated. Skip the rest of this skill.

If tdd: off — stop reading. Do not enforce any TDD discipline.

Anti-Pattern: Horizontal Slicing

<Bad> Horizontal slicing — write all tests first, then all implementation: test1, test2, test3, test4, test5 → impl1, impl2, impl3, impl4, impl5 Tests describe imagined behavior. Discovery comes too late. </Bad><Good> Vertical slicing (tracer bullets) — one test, one impl, repeat: test1 → impl1 → test2 → impl2 → test3 → impl3 Each test responds to what the previous cycle taught you. </Good>

The rule: ONE test, ONE implementation, then the next test. Never batch. Each RED-GREEN cycle is a learning step — the next test is informed by what you just discovered.

The Cycle

RED — Write one failing test

  • One behavior per test, clear name (e.g., 'rejects empty email with validation error')
  • Real code preferred over mocks (mocks only if unavoidable)
  • Run the test. Confirm it fails for the expected reason (feature missing, not typo/error)

GREEN — Write minimal code to pass

Write the simplest code to make the test pass. Nothing more.

<Good> // Just enough to pass async function retryOperation(fn, maxRetries = 3) { for (let i = 0; i < maxRetries; i++) { try { return await fn(); } catch (e) { if (i === maxRetries - 1) throw e; } } } </Good><Bad> // YAGNI — over-engineered beyond what the test requires async function retryOperation(fn, options?: { maxRetries?: number; backoff?: 'linear' | 'exponential'; onRetry?: (attempt: number) => void; timeout?: number; }) { ... } </Bad>

Run the test. Confirm it passes. Confirm all other tests still pass.

REFACTOR — Then repeat

Only after green: remove duplication, improve names, extract helpers. Keep tests green. Don't add behavior. Then write the next failing test for the next behavior.

When TDD Is Skipped (recommended mode only)

In recommended mode, if you write production code before a test:

  1. Log the skip — note which function/method was written without test-first
  2. Write the test immediately after — cover the code before moving on
  3. Flag it in phase verification as a TDD skip with a brief reason

In strict mode, skips are not allowed. Delete the code and start over.

Reference Material

  • Test quality: See skills/test-driven-development/references/test-quality.md — load when reviewing test quality
  • Rationalization prevention: See skills/test-driven-development/references/rationalizations.md — load in strict mode when tempted to skip TDD

Verification Checklist

Before marking any implementation step complete:

  • All tests pass, output clean (no errors, warnings)
  • Tests use real code (mocks only if unavoidable)
  • Edge cases and error paths covered
  • Every new function/method has a test (strict + recommended)
  • Tests written before implementation, or skip logged (recommended) / code deleted (strict)
  • Each test failed for the expected reason before implementation (strict)

Debugging Integration

Bug found? Write a failing test reproducing it first. In recommended mode, strongly encouraged. In strict mode, mandatory.

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