Menu
Verify that implementation work is correct before reporting done.
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
Help with Claude/LLM API usage, models, and integration patterns.
Scaffold or plan LilBot-style local plugins.
Break a large request into a tracked batch of smaller tasks.
Coordinate browser-assisted work when a Chrome/browser connector is available.
Investigate a bug or failing behavior and isolate the likely cause.
Use subagents to split exploration, implementation, review, and verification work.
| name | verify |
| description | Verify that implementation work is correct before reporting done. |
| allowed-tools | read_file, list_dir, grep_files, git_status, git_diff, run_tests, agent_open, agent_eval |
| when_to_use | Use after non-trivial implementation, backend/API changes, infrastructure changes, or before claiming completion. |
| context | fork |
| agent | verifier |
Verify the work described by the user or by these arguments:
{{args}}
Produce a compact verdict:
STATUS: PASS, FAIL, or PARTIAL. EVIDENCE: commands run, files inspected, and exact outcomes. RISKS: unresolved edge cases or missing coverage. NEXT: smallest next action if not PASS.
Prefer concrete validation over reassurance. If tests cannot be run, explain why and substitute targeted code inspection with file references.
