agentleFS
rayketcham-labrayketcham-lab/qn-claude-web/.claude/skills/tdd/SKILL.md

tdd

Skill2 starsChanged 8 months agoApache-2.0View on GitHub

Test-Driven Development — Red/Green/Refactor cycle. Writes failing tests first from a spec, implements minimum code to pass, refactors, then verifies.

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 subtitled 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

18 rules. 0 are common, 18 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 186 edited versions we read keep these.

  • 18

    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:

    Run a full test-driven development cycle for a feature or requirement.

    line 12
  2. Distinctive:

    Write test cases that define the expected behavior.

    line 25
  3. Distinctive:

    Test one behavior per test

    line 27
  4. Distinctive:

    Run the tests. All must fail.

    line 29
  5. Distinctive:

    If any test passes → something is wrong.

    line 30
  6. Distinctive:

    Read the failing tests carefully.

    line 41
  7. Distinctive:

    Write the minimum code to make all tests pass.

    line 42
  8. Distinctive:

    No gold-plating — if the tests don't require it, don't build it

    line 43
  9. Distinctive:

    No extra features, no premature abstractions

    line 44
  10. Distinctive:

    Run the tests. All must pass.

    line 46
  11. Distinctive:

    If any test still fails → fix the implementation, not the test

    line 47
  12. Distinctive:

    If a test reveals an implementation design issue → fix the design, keep the test

    line 48
  13. Distinctive:

    Run lint/check for the language:

    line 49
  14. Distinctive:

    If no refactoring is needed, say so — don't force changes.

    line 68
  15. Distinctive:

    Run the full test suite (not just the new tests)

    line 78
  16. Distinctive:

    Run lint and build checks

    line 79
  17. Distinctive:

    Check for regressions — did any previously passing test break?

    line 80
  18. Distinctive:

    When you want tighter, more focused tests than test-after produces

    line 113

“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 — Red / Green / Refactor

Run a full test-driven development cycle for a feature or requirement. Tests are written before implementation, ensuring the design is driven by the specification rather than the code.

Input: A feature description, requirement, or user story passed as the skill argument.

Phase 1 — RED (Write Failing Tests)

Agent perspective: Tester

  1. Analyze the feature spec. Identify the behaviors, inputs, outputs, and edge cases it implies.
  2. Determine the appropriate test framework and file location based on the project:
    • Rust: #[cfg(test)] module or tests/ directory, cargo test
    • Python: pytest in tests/ or test_*.py, pytest -v
    • Shell: BATS or inline assertion scripts
  3. Write test cases that define the expected behavior. Each test should:
    • Have a descriptive name reflecting the requirement
    • Test one behavior per test
    • Cover happy path, edge cases, and error conditions
  4. Run the tests. All must fail.
    • If any test passes → something is wrong. Either the feature already exists or the test is not actually testing the new behavior. Stop and report.
  5. Record which tests were written and what specs they cover.
RED checkpoint: N tests written, all failing. Specs covered: [list]

Phase 2 — GREEN (Implement Minimum Code)

Agent perspective: Builder

  1. Read the failing tests carefully. They are your specification.
  2. Write the minimum code to make all tests pass. Rules:
    • No gold-plating — if the tests don't require it, don't build it
    • No extra features, no premature abstractions
    • Favor the simplest correct implementation
  3. Run the tests. All must pass.
    • If any test still fails → fix the implementation, not the test
    • If a test reveals an implementation design issue → fix the design, keep the test
  4. Run lint/check for the language:
    • Rust: cargo clippy -- -D warnings
    • Python: ruff check
    • Shell: shellcheck
GREEN checkpoint: N/N tests passing. Files modified: [list]

Phase 3 — REFACTOR (Simplify Without Changing Behavior)

Agent perspective: Simplifier

  1. Review the implementation from Phase 2 for:
    • Duplicated code that can be extracted
    • Overly complex conditionals
    • Poor naming or unclear structure
    • Unnecessary allocations or inefficiencies
  2. Refactor while keeping all tests green. Run tests after each change.
  3. If no refactoring is needed, say so — don't force changes.
REFACTOR checkpoint: [changes made or "none needed"]. Tests still passing: YES/NO

Phase 4 — VERIFY (Final Gate)

Agent perspective: Verifier

  1. Run the full test suite (not just the new tests)
  2. Run lint and build checks
  3. Check for regressions — did any previously passing test break?
  4. Behavioral diff: compare the change against the base state
  5. Produce the final verdict

Output Format

## TDD Report: [Feature]

**Cycle**: RED -> GREEN -> REFACTOR -> VERIFIED

### Red Phase
- Tests written: [N] in [file(s)]
- All failing: YES/NO
- Specs covered: [list]

### Green Phase
- Files modified: [list]
- Tests passing: [X/Y]
- Implementation approach: [brief]

### Refactor Phase
- Changes made: [list or "none needed"]
- Tests still passing: YES/NO

### Verdict: PROVEN / FAILED

When to Use

  • Starting a new feature where the requirements are clear enough to test
  • Implementing a bug fix where you can write the regression test first
  • Working on specification-driven code (protocol handlers, validators, parsers)
  • When you want tighter, more focused tests than test-after produces
  • Any time the user invokes /tdd with a feature description

When NOT to Use

  • Exploratory/prototyping work where requirements are still forming
  • Pure refactors with no behavioral change (use Simplifier + Verifier instead)
  • Configuration changes, documentation, or CI/CD work

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.