Skip to content
Agentmart
Submit a tool

tdd

Use when the user requests test-first development or a red-green-refactor workflow.

Skill by jason-wjs

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/jason-wjs-tdd

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when the user requests test-first development or a red-green-refactor workflow.

Use cases: testing, productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/tdd

What's inside

Skill name
tdd
Description
Use when the user requests test-first development or a red-green-refactor workflow.
License
MIT
Instructions
39 lines in SKILL.md · view on GitHub

Files (4)

  • SKILL.md
  • openai.yaml · agents/
  • mocking.md
  • tests.md

SKILL.md (first lines)

# Test-Driven Development

Work in small behavior slices: write a test, observe its relevant failure,
implement enough to pass, then refactor while preserving behavior.

Derive tests from agreed requirements, existing contracts, and real failure
scenarios. Prioritize observable behavior at useful interfaces. Do not invent
unsupported inputs or recovery requirements merely to add edge-case tests;
a test the agent just wrote is not independent evidence of a requirement.
Expected values should come from a spec, known-good example, or independent
calculation; do not repeat the implementation in the assertion.

Resolve consequential interface or behavior ambiguity with the user. Reuse
existing decisions and authorization; routine test selection and implementation
do not need a new approval gate.

## Loop

- Choose the next meaningful behavior rather than prewriting a speculative
  suite. Existing seams are preferred when they exercise the actual behavior.
- Confirm the test fails for the intended reason, not a broken fixture/import.
- Implement the behavior without speculative abstractions or fallbacks.
- Run affected tests. Refactor when there is a concrete clarity or duplication
  benefit; testing is not an instruction to redesign surrounding code.
- Complete the relevant project checks after a coherent change. Repeat checks
  when new edits or failures justify it, not as a ritual after every edit.

Validate external input at its boundary. Rely on established internal contracts;
retain error handling for reachable I/O failures, cleanup, and security checks.

## References

Read only what the task needs:
- [tests.md](tests.md): behavior-oriented test examples.
- [mocking.md](mocking.md): choosing real dependencies and test doubles.
- [Codebase design](../codebase-design/SKILL.md): when an interface or dependency
  boundary prevents meaningful testing.

From jason-wjs/wujs-curated-skills, MIT.

More from jason-wjs/wujs-curated-skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 15, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from jason-wjs

Cite this page

tdd skill. Agent Mart. https://agentmart.dev/skills/jason-wjs-tdd (last updated 2026-10-24)