Skill

fix-and-test

This skill should be used when the user asks to 'fix the tests', 'make tests pass', 'tests are failing', 'fix and test', 'green the tests', or wants to iteratively fix failing tests until they pass.

npx claudepluginhub 45ck/prompt-language --plugin prompt-language

Tool Access

This skill is limited to using the following tools:

ReadWriteEditBashGrepGlob

Preview

Run a fix-test loop: identify failing tests, fix them, re-run tests, repeat until green.

Supporting Assets

examples/multi-ecosystem.md

SKILL.md

Similar Skills

cache-components

139.2k

Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.

cache-components

mcp-builder

124.2k

Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).

9 files

anthropics-skills-13

canvas-design

124.2k

Generates original PNG/PDF visual art via design philosophy manifestos for posters, graphics, and static designs on user request.

20 files

anthropics-skills-13

Stats

Stars3

Forks0

Last CommitApr 10, 2026

Actions

View Source View Plugin View on GitHub View README

Fix and Test

Run a fix-test loop: identify failing tests, fix them, re-run tests, repeat until green.

Use this when the codebase is already in a failing state and the goal is recovery. Do not use this for greenfield feature delivery (use tdd) or structural cleanup of already-green code (use refactor).

What to do

If the user provided an argument, use it as the test command (for example npm test -- auth). Otherwise use npm test.

Run the command and triage existing failures.

Fix production code first; only edit tests when they are demonstrably wrong.

Re-run the same command and iterate until green (max 5 passes).

Once scoped tests are green, run full npm test before declaring done.

Flow

flow: retry max 5 run: npm test if command_failed prompt: Analyze the test failures above and fix the underlying code. Do not modify tests unless they are genuinely wrong. end end done when: tests_pass

Rules

Focus on fixing the source code, not the tests, unless the tests themselves are incorrect.

During active triage you may run a scoped test command, but finish with the full suite.

If you cannot fix a test after 5 attempts, explain what you tried and why it's failing.

Examples

For ecosystem-specific command patterns, see examples/multi-ecosystem.md.

Fix and Test

Run a fix-test loop: identify failing tests, fix them, re-run tests, repeat until green.

What to do

If the user provided an argument, use it as the test command (for example npm test -- auth). Otherwise use npm test.
Run the command and triage existing failures.
Fix production code first; only edit tests when they are demonstrably wrong.
Re-run the same command and iterate until green (max 5 passes).
Once scoped tests are green, run full npm test before declaring done.

Flow

flow:
  retry max 5
    run: npm test
    if command_failed
      prompt: Analyze the test failures above and fix the underlying code. Do not modify tests unless they are genuinely wrong.
    end
  end

done when:
  tests_pass

Rules

Focus on fixing the source code, not the tests, unless the tests themselves are incorrect.
During active triage you may run a scoped test command, but finish with the full suite.
If you cannot fix a test after 5 attempts, explain what you tried and why it's failing.

Examples

For ecosystem-specific command patterns, see examples/multi-ecosystem.md.