Skip to content
Agentmart
Submit a tool

tdd

Build or fix behavior test-first when TDD is requested, using red-green cycles at agreed public interfaces.

Skill by kewvydev

IndexedMIT★ 2
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/kewvydev-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

Build or fix behavior test-first when TDD is requested, using red-green cycles at agreed public interfaces.

Use cases: testing

Reviews

Write a review

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
Build or fix behavior test-first when TDD is requested, using red-green cycles at agreed public interfaces.
License
MIT
Instructions
19 lines in SKILL.md · view on GitHub

Files (9)

  • LICENSE
  • SKILL.md
  • openai.yaml · agents/
  • DEEPENING.md · references/design/
  • DESIGN-IT-TWICE.md · references/design/
  • vocabulary.md · references/design/
  • mocking.md · references/
  • tests.md · references/
  • upstream.md · references/

SKILL.md (first lines)

# Test-Driven Development

Use TDD for the requested scope, not as a mandate for every project change.
Read existing test commands, domain vocabulary and relevant decisions. Agree the
observable interfaces and behaviors to test with the user; reuse agreement already
present in the request or project criteria. Do not write tests at unconfirmed seams.

Work one behavior at a time: write a test, run it and observe the intended failure,
make the smallest implementation pass, then repeat. Diagnose setup failures before
calling a test red. Tests must observe public behavior and survive internal refactors;
avoid private-method tests, tautological assertions and batches of speculative tests.
Keep refactoring separately scoped. Report checks actually run and remaining gaps.

Read [test examples](references/tests.md) and [mocking guidance](references/mocking.md)
before choosing test doubles. If interface placement is unclear, consult the
[design vocabulary](references/design/vocabulary.md); this is a reference, not an
extra installed skill or approval for architectural changes.

From kewvydev/kewvy-ai-stack, MIT.

More from kewvydev/kewvy-ai-stack

Signals

Stars
2
Forks
0
Open issues
0
Last commit (this folder)
Oct 20, 2026 (8 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/kewvydev/kewvy-ai-stack
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from kewvydev

Cite this page

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