メニュー
Verify that implementation work is correct before reporting done.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
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.
