Menu
Run tests. Use when the user says "test", "run tests", or before commits.
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
Pick a bug from Linear, fix it test-first, verify, and update. Use when the user says "fix issue", "fix bug", "work on known issue", or "pick a bug".
Create a new ticket for task tracking. Use when the user says "create ticket", "new ticket", or "track this".
Diagnose an integration/E2E test log, classify failures by severity, and batch-create issues. Use when the user says "smoke test", "diagnose log", "triage test log", or provides a test log.
Pull Linear issues and generate a local snapshot for quick reference. Use when the user says "sync linear", "pull linear issues", "update from linear", or "show my issues".
Triage, prioritize, and groom Linear issues. Use when the user says "triage linear", "review inbox", "prioritize issues", "groom backlog", or "clean up issues".
Investigate a bug using structured differential diagnosis. Use when the user says "diagnose", "investigate this", "what's causing this", or "figure out why".
| name | test |
| description | Run tests. Use when the user says "test", "run tests", or before commits. |
| argument-hint | [test-name or module] |
| user-invocable | true |
| allowed-tools | Bash, Read, Grep |
| model | haiku |
Run the test suite and report results.
If $ARGUMENTS is provided, run the specific test:
[YOUR SPECIFIC TEST COMMAND] $ARGUMENTS
If no arguments, run the full test suite:
[YOUR FULL TEST COMMAND HERE]
Parse the output and report in this format:
TESTS: [PASS/FAIL]
Passed: [count]
Failed: [count]
Skipped: [count]
[If failures:]
FAILED: [test name] — [error summary]
FAILED: [test name] — [error summary]
If tests fail, identify which test failed and the likely cause. Do NOT attempt to fix — just report.