Skip to content
Agentmart
Submit a tool

test-driven-development

Use when implementing a high-risk behavior change, reproduced regression, or costly contract.

Skill by tsergeytovarov

IndexedMIT★ 15
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/tsergeytovarov-test-driven-development

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 implementing a high-risk behavior change, reproduced regression, or costly contract. Do NOT use by default for docs, styling, config, or low-risk wiring.

Use cases: documents, testing

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 and code. Checked Oct 26, 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/test-driven-development

What's inside

Skill name
test-driven-development
Description
Use when implementing a high-risk behavior change, reproduced regression, or costly contract. Do NOT use by default for docs, styling, config, or low-risk wiring.
License
MIT
Instructions
44 lines in SKILL.md · view on GitHub

Files (3)

  • CHANGELOG.md
  • SKILL.md
  • writing-good-tests.md

SKILL.md (first lines)

# Risk-Based Test-Driven Development

TDD protects critical behavior. It is not a requirement to create a test for
every changed function.

Read `../using-superpowers/references/risk-policy.md` and classify the change.

## Decision

| Risk | New test |
|---|---|
| Low | None by default; use a focused check or smoke path |
| Medium | Only for a key outcome, non-obvious branch, or hard-to-notice regression |
| High | One minimal regression or contract test first when practical |

Do not test private helpers, trivial branches, static rendering details, or
behavior already covered through a public seam.

## Critical TDD Cycle

For a warranted test:

1. Write the smallest test that describes the critical observable behavior.
2. Run it and confirm it fails for the expected missing behavior.
3. Implement the smallest production change.
4. Run the focused test and the affected suite once.
5. Refactor only if needed, then rerun the closest affected target.

Mocks are limited to external boundaries. Prefer real in-process behavior.

## Existing Code or Impractical Automation

Do not delete completed code merely because the test was not written first.
Add a focused regression test when it materially protects the outcome. If
automation is disproportionately expensive or impossible, record and run a
reproducible smoke check instead.

## Completion

- Every check that was run must pass.
- A passing focused test does not justify running unrelated suites.
- State what was verified and what was intentionally not tested.

From tsergeytovarov/ai-settings, MIT.

More from tsergeytovarov/ai-settings

Signals

Stars
15
Forks
4
Open issues
2
Last commit (this folder)
Jul 31, 2026 (3 months ago)
Last release
Oct 12, 2026 (17 days ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from tsergeytovarov

Cite this page

test-driven-development skill. Agent Mart. https://agentmart.dev/skills/tsergeytovarov-test-driven-development (last updated 2026-10-24)