Skill
adversarial-review-loop
重要成果物 (レビュー・設計・修正) の完了報告前に独立・敵対的検証を挟む手順。バイアスフリーの独立 subagent × レンズ分割 → 実データ裏取り → 反映 → Critical ゼロまで反復。手動起動。
Claim this listing
Connect your GitHub to prove you own or maintain this listing. We verify repo access automatically — most publishers are confirmed in seconds.
1Connect GitHub
2Submit your claim
3Auto-verified, or reviewed within 48h