Menu
Use this skill to run tests, identify failures, and fix them. Triggered by "run tests", "fix failing tests", "make tests pass", or "/test".
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use this skill when the user wants to create a git commit, stage files, write a commit message, or finalize their work with a git commit. Also invoked by phrases like "commit my changes", "save to git", "git commit".
Use this skill to help deploy code to an environment. Triggered by "deploy", "deploy to staging", "deploy to production", "ship it".
Use this skill to generate, update, or improve documentation. Triggered by "write docs", "generate documentation", "update README", "document this code".
Use this skill when the user wants to review a pull request, check a PR for issues, or get feedback on a GitHub PR. Triggered by "review PR", "check PR", "review pull request", or "/review-pr <number>".
Use this skill to perform a security audit, scan for vulnerabilities, check OWASP Top 10 issues, or review code for security problems. Triggered by "security audit", "check security", "find vulnerabilities".
| name | test |
| description | Use this skill to run tests, identify failures, and fix them. Triggered by "run tests", "fix failing tests", "make tests pass", or "/test". |
| argument-hint | [file or pattern] |
| allowed-tools | Bash, Read, Edit, Grep, Glob |
Run the test suite and automatically fix any failures.
!npm test -- --passWithNoTests 2>&1 | tail -30
Run the tests (filtered to $ARGUMENTS if provided):
npm test $ARGUMENTS
# or: pytest $ARGUMENTS
# or: go test ./...
# or: cargo test
For each failing test: a. Read the test file to understand what's being tested b. Read the source file being tested c. Identify the root cause (test wrong? source wrong? missing mock?) d. Fix the root cause — prefer fixing source bugs over changing tests e. Only update a test if it's clearly wrong or testing the wrong thing
Re-run tests to confirm they pass
If tests still fail after 2 attempts at fixing, report:
$ARGUMENTS