agentleFS
Sign inStart free
ntaffziintaffzii/Skill-Agents/skills/engineering/tdd/SKILL.md

tdd

Skill4 starsChanged 2 months agoMITView on GitHub

Test-driven development workflow for implementing features or fixing bugs through red-green-refactor. Use when the user asks to build, change, or fix behavior and the codebase has a practical automated test surface.

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-Vibe-CompanySkill

    capture-learning-tools

    Turn technical conversations, bugs, CI failures, review comments,

    Also in 5 projects that use this

  • The-Vibe-CompanySkill

    design-frontend-dev

    Clean Impeccable frontend design skill. Use when the user wants to

    Also in 5 projects that use this

  • tristanphvnSkill

    ketchup-video

    Catch the user up like /keel:ketchup, with a short silent video of slides for what happened and the waiting calls as text under it. Use for /keel:ketchup-video.

    Also in 14 projects that use this

  • jaydubya818Skill

    figure-it-out

    Use when novel or multi-phase work needs an auditable workflow and no narrower playbook fits.

    Also in 54 projects that use this

  • jaydubya818Skill

    principle-laziness-protocol

    Apply when a refactor is adding wrappers or abstractions instead of simplifying.

    Also in 45 projects that use this

  • +2 more from The-Vibe-Company
  • +5 more from jaydubya818

The file

Show its rules and text

We split this skill into the rules it gives an agent

15 rules. 0 are common, 15 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 186 edited versions we read keep these.

  • 15

    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:

    Use this skill to make behavior changes with a tight feedback loop.

    line 8
  2. Distinctive:

    If the request is ambiguous, make a conservative assumption and state it.

    line 15
  3. Distinctive:

    Prefer the seam closest to real behavior: integration, API, component, e2e, then unit.

    line 18
  4. Distinctive:

    Avoid tests that only assert implementation details.

    line 19
  5. Distinctive:

    If no useful seam exists, note that as design pressure and choose the best available signal.

    line 20
  6. Distinctive:

    Write one failing test for the next slice.

    line 23
  7. Distinctive:

    Run only the narrowest relevant test command first.

    line 24
  8. Distinctive:

    Keep changes scoped to the behavior under test.

    line 29
  9. Distinctive:

    Do not refactor unrelated code during green.

    line 30
  10. Distinctive:

    Remove duplication only when it is real and local.

    line 35
  11. Distinctive:

    Add edge cases only after the core path works.

    line 38
  12. Distinctive:

    Test names should describe behavior, not implementation.

    line 45
  13. Distinctive:

    Do not mock the thing being tested.

    line 46
  14. Distinctive:

    Prefer fixtures over hand-built objects when local patterns already use fixtures.

    line 47
  15. Distinctive:

    Keep assertions specific enough to catch the bug or behavior contract.

    line 48

“Common” is measured: kept by at least 6 in 10 of the 186 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

TDD

Use this skill to make behavior changes with a tight feedback loop.

Workflow

  1. Clarify behavior
    • Identify the user-visible behavior, input, output, and edge cases.
    • Find the smallest vertical slice that proves the behavior.
    • If the request is ambiguous, make a conservative assumption and state it.
  2. Find the test seam
    • Prefer the seam closest to real behavior: integration, API, component, e2e, then unit.
    • Avoid tests that only assert implementation details.
    • If no useful seam exists, note that as design pressure and choose the best available signal.
  3. Red
    • Write one failing test for the next slice.
    • Run only the narrowest relevant test command first.
    • Confirm the failure is for the expected reason.
  4. Green
    • Implement the smallest change that passes the test.
    • Keep changes scoped to the behavior under test.
    • Do not refactor unrelated code during green.
  5. Refactor
    • Improve clarity only after the test passes.
    • Preserve behavior and rerun the relevant tests.
    • Remove duplication only when it is real and local.
  6. Expand
    • Add edge cases only after the core path works.
    • Repeat red-green-refactor for each slice.
    • Finish by running the broader relevant suite.

Test Quality Rules

  • A good test fails before the fix and passes after it.
  • Test names should describe behavior, not implementation.
  • Do not mock the thing being tested.
  • Prefer fixtures over hand-built objects when local patterns already use fixtures.
  • Keep assertions specific enough to catch the bug or behavior contract.

Verification

  • The new or changed test fails before the implementation when practical.
  • The focused test command passes after the implementation.
  • A broader relevant suite passes when the change touches shared behavior.
  • Untested risk is named when broader validation is not practical.

Completion Report

End with:

  • Behavior implemented
  • Tests added or changed
  • Commands run
  • Any untested risk

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