fix-tests — Claude Code skill: what it does, how to install
This skill tracks down failing tests after logic changes or refactoring and guides fixes until the suite passes.
npx skills add NeoLabHQ/context-engineering-kit --skill fix-tests -a claude-codeWhat fix-tests does
The skill reads README.md and the project configuration, finds test and coverage commands, then runs the full suite. It parses the failures, groups them by file, and checks how to run one test file in isolation. Developer agents then inspect each failing file, the project documentation, and the failure cause before making a fix.
Its main rule is to change tests while preserving what they are meant to verify. Assertions, setup, or mocks may be updated; business logic should change only when it is clearly broken. With two or more changed files, or with complex logic in one file, the skill orchestrates agents instead of writing tests itself. A single simple file change can be handled directly. After each pass, it runs the full suite again and returns to the remaining failures. That makes the business-logic boundary worth checking before you accept a fix.
What it helps with
- locate every failing test file
- find a reliable command for one test file
- update assertions after a refactor
- repair broken test setup or mocks
- rerun the full suite after fixes
Example prompts for the agent
- Use
fix-teststo find and repair every failing test after a business logic change. - Run
fix-testsfor the tests insrc/orders, verify the single-file command, then run the full suite. - Apply
fix-testsafter a dependency update; preserve test intent and change business logic only if it is clearly broken.
How to install fix-tests
1Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill fix-tests -a claude-code2Manually: put the files in place
~/.claude/skills/fix-tests/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/fix-tests/
1Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill fix-tests -a codex2Manually: put the files in place
.agents/skills/fix-tests/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill fix-tests -a cursor2Manually: put the files in place
.cursor/skills/fix-tests/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install NeoLabHQ/context-engineering-kit fix-tests2Manually: put the files in place
.github/skills/fix-tests/SKILL.md1Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill fix-tests -a gemini-cli2Platform CLI
gemini skills install https://github.com/NeoLabHQ/context-engineering-kit --path skills/fix-testsManually: put the files in place
.devin/skills/fix-tests/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill fix-tests -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about fix-tests
How do I install fix-tests in Claude Code?
Run npx skills add NeoLabHQ/context-engineering-kit --skill fix-tests -a claude-code, then run npx skills add NeoLabHQ/context-engineering-kit --skill fix-tests -a claude-code again. The skill file is at ~/.claude/skills/fix-tests/SKILL.md.
What does fix-tests do?
It runs the full test suite, groups failing files, and assigns fixes to developer agents. It then reruns the suite and works through any failures that remain.
Does fix-tests change business logic?
It focuses on fixing tests while preserving their intent. Business logic changes are reserved for clear bugs, and complex changes are handled through agent orchestration.