菜单
Use before presenting implementation plans and after non-trivial commits that require review. Runs codex exec in read-only review mode, handles resume, MCP transport errors, and review timeout semantics.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use by any agent before writing specs, editing code, or changing workflow files when the change could add compatibility behavior, aliases, silent fallbacks, or default-value fallbacks.
Use before presenting implementation plans and after non-trivial commits when the review should run through Claude Code with the configured Fable model. Runs claude -p in streaming review mode, derives the Fable model from claude/settings.json, constrains tools for read-only review plus currentness checks, handles resume, and defines review timeout semantics.
Use when committing, pushing, or preparing PRs. Defines the user's commit workflow, message style discovery, review handoff, and branch/worktree push requirements.
Linearのissueを整理し、会話しながら新規issueに落とすスキル。2つのモードを持つ: (1) 既存issue整理: Backlogの全issueをINVEST原則で診断し、分割・統合・再分類を提案・実行 (2) 会話→issue化: ユーザーとの対話から要件を引き出し、適切な粒度のissueに落とす 両モード完了後、整理された実行計画を自動生成する。 トリガー: 「issueを整理して」「Backlog整理」「issue棚卸し」「やること整理」「実行計画を作って」 「issueの粒度を揃えて」「issueに落として」「要件をissueにして」
Use for code implementation, bug fixes, refactors, and test additions. Enforces the user's development style: YAGNI, TDD, clear contracts, separation of concerns, no unsolicited fallback or backward-compatibility helpers, and maintainable code structure.
Use when writing or editing tests. Tests should be ordered by near-normal, normal, then abnormal cases where applicable, and test names must be Japanese behavior descriptions from a reviewer/user perspective.
| name | codex-exec-review |
| description | Use before presenting implementation plans and after non-trivial commits that require review. Runs codex exec in read-only review mode, handles resume, MCP transport errors, and review timeout semantics. |
codex exec to review the plan.codex exec to review the committed change.--sandbox read-only.-c model_reasoning_effort=medium only for review runs.-c service_tier=fast and -c features.fast_mode=true when appropriate.--skip-git-repo-check only when the review must run outside a Git repository.codex exec or external review command.codex exec \
--sandbox read-only \
--model gpt-5.4 \
-c model_reasoning_effort=medium \
-c service_tier=fast \
-c features.fast_mode=true \
"このプランをレビューして。read-only sandboxなのでテスト・build・format・install・生成コマンドは実行せず、差分・設定・既存ログの読取だけで判断して。不足する実行結果があれば質問して。別の codex exec や外部レビューコマンドは絶対に起動しないで。瑣末な点へのクソリプはしないで。致命的な点だけ指摘して。回答内容が現時点で out of date / deprecated になっていないかにも気をつけて: {plan_full_path} (ref: {CLAUDE_md_full_path})"
Use the same session for updated plan reviews:
codex exec resume <SESSION_ID> \
"前回の指摘を反映してプランを更新した。もう一度レビューして。read-only sandboxなのでテスト・build・format・install・生成コマンドは実行せず、差分・設定・既存ログの読取だけで判断して。不足する実行結果があれば質問して。別の codex exec や外部レビューコマンドは絶対に起動しないで。瑣末な点へのクソリプはしないで。致命的な点だけ指摘して。新しく追加された問題がなければ、その旨を明示して: {plan_full_path} (ref: {CLAUDE_md_full_path})"
codex exec may print MCP transport errors such as http://127.0.0.1:8000/mcp connection failures at startup.codex exec failure.codex response is returned after the error, consider the run successful but degraded.codex exec exits without a final codex answer or without the requested review result.codex exec failure.review started but final result not yet returned is not review complete.codex exec resume <SESSION_ID> or rerun.review incomplete and ask the user how to proceed.