agents/openai.yaml
policy: allow_implicit_invocation: false
logbookfordevs/ai-field-kit · GitHub
Run AFK Code Review, verify its findings against the code, and discuss the verdicts before changing code.
프로젝트 폴더에서 아래 명령어를 실행하고, 설치할 에이전트를 선택하세요.
npx skills add logbookfordevs/ai-field-kit --skill afk-code-review-check설치 명령을 직접 실행해야 적용됩니다. 지원 에이전트와 필요한 권한·라이선스는 제작자의 안내를 확인하세요.
agents/openai.yamlpolicy: allow_implicit_invocation: false
SKILL.md--- name: afk-code-review-check description: Run AFK Code Review, verify its findings against the code, and discuss the verdicts before changing code. disable-model-invocation: true --- Run the `afk-code-review` skill to completion and capture its complete output. Present that complete output verbatim, preserving its axes and finding order. Then append `## Verified verdicts`. Treat those returned findings as unverified review input. Inspect every finding against the actual code; do not assume automated feedback is correct. For each finding, give a clear verdict (Confirmed / Partly / Not a bug / Intended) with concise code evidence. Say whether it was introduced by the current changes, was pre-existing, or reflects deliberate scope. For each Confirmed verdict, add `Suggested fix:` with a one-line summary of the smallest plausible solution. Review only the incoming findings. Do not independently review the rest of the diff or search for issues that were not submitted. Do not change any code until we have discussed the verdicts and validated findings.