Loading...
Loading...
Found 7 Skills
Drive the Codex review cycle on an open PR. Polls Codex comments, classifies severity (P0/P1 blocking, P2/nit ignored), applies fixes via subagent or escalates to a different worker on round 3, labels needs-human and stops on round 4. Auto-merges when all merge gates are green.
Fandhe-AI 組織標準の CI ガード一式(codex-review 導入 / AGENTS.md レビュー観点集 / 必須チェック集約ジョブ / branch protection ruleset・追加ガード)を対象リポジトリへ導入する。「リポジトリガード入れて」「CI ガード導入して」 「branch protection セットアップ」「codex-review 導入して」「AGENTS.md 整備して」などで使用。 複数リポジトリへの一括適用にも対応。.claude/ 体系の初期セットアップは init-claude、既存体系の充実は update-claude を参照。
Add one optional external Codex critique after the existing council has produced a decision draft. Use when an ambiguous, high-consequence decision would benefit from a separate model invocation's attempt to break the synthesis. Requires explicit consent before sending the compact draft and disagreement to OpenAI, labels same-provider reviews honestly, and marks the review absent when the adapter is unavailable.
Use when wanting independent review from external models before merging, committing, or finalizing architecture or plan decisions, or when the user asks for a second opinion, codex review, or gemini review
Use when doing dev-stage self-review on the current branch before pushing or opening a PR — runs an auto-loop of codex review (cross-model, OpenAI) + per-finding fix + re-review until findings converge or stop conditions fire. Codex follows pr-review's multi-role methodology (security / staff-engineer / sdet / spec-auditor). Triggers — 'self review', 'self-review', '自己 review', '自我 review', 'cross-model review', 'pre-push review', 'review and fix my branch'. NOT for live PR review with sticky/inline comments (use pr-review), NOT for managed PR babysitting (use pr-babysit), NOT for first-time review without intent to fix (use mode=review-only opt-in).
Automated code review loop with progressive reasoning levels. Runs n parallel Codex reviews (configurable via -n), Claude addresses issues, climbs from low→xhigh reasoning until fixed point (all n clean). Human approval at each iteration.
Explicitly launch the automated Ralph-Lisa plan-implement-review workflow. Use only when the current request directly asks to start or run Ralph-Lisa; a mention or discussion of the skill is not an invocation. Never infer it from ordinary planning, building, implementation, or review requests.