メニュー
Iterative code review — fix all P1/P2/P3 findings until clean
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
| name | review-loop |
| description | Iterative code review — fix all P1/P2/P3 findings until clean |
| version | 1.0 |
| requires | {"bins":[],"env":[],"os":[],"providers":[]} |
| tags | ["review","quality","code"] |
| config | {"max_iterations":10,"timeout_minutes":20} |
Perform an iterative code review. Classify findings as:
After each round, fix ALL findings (P1, P2, and P3), then re-review. Continue until no findings remain. Max 20 iterations.
Multi-persona Round-Table mit domain-aware Personas (LLM wählt 4–6 themenspezifische Rollen); iterative Cross-Pollination bis TF-IDF-Konvergenz; Synthesizer ranked Top-N mit Pro/Contra
Research → Execute → Dual-Review Loop (Code Quality + Issue Resolution) bis beide Reviews bestanden
Multi-agent deep security audit — 6 expert personas (pentester, architect, code auditor, supply chain, data privacy, forensics) + CISO synthesis + optional fix implementation
Radical-honesty architectural review — questions code, methodology, design, and operational fitness
Security audit + fix — scans for hardcoded secrets, injection vectors, path traversal, input validation gaps, then implements all fixes
Cross-Domain Know-How-Transfer — findet kreative Anwendungen von Vault-Expertise in anderen Branchen
