メニュー
Review an exact PR head in isolation using trusted-base instructions and execution evidence
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。
Clade goal-driven autonomous improvement loop (Blueprint architecture — deterministic pre/post phases + LLM supervisor/worker nodes, converges when goal met or max-iter hit). NOT the Claude Code built-in /loop (which polls a prompt on an interval like `/loop 5m /foo`) — if the user wants interval polling, route to the built-in.
Adaptive, resumable Git delivery across repositories and agent runtimes — probe policy, checkpoint coherent work, publish, review, integrate, and verify cleanup
Adaptive, resumable Git delivery across repositories and agent runtimes — probe policy, checkpoint coherent work, publish, review, integrate, and verify cleanup
Inspect or select a Clade execution connection while keeping agent runtime, inference provider, wire protocol, and model distinct. Use for Claude/Codex runtime selection, Anthropic/OpenAI/MiniMax/Kimi/custom gateways, model routing, or connection troubleshooting.
Inspect or select a Clade execution connection while keeping agent runtime, inference provider, wire protocol, and model distinct. Use for Claude/Codex runtime selection, Anthropic/OpenAI/MiniMax/Kimi/custom gateways, model routing, or connection troubleshooting.
Equipment manager for Claude Code projects — inventory local skills/agents/scripts, audit external upstream repos (red-flag + prompt-injection screening), and sync selectively after user approval. Absorbs container-layout skill repos AND single-skill-at-root repos (e.g. a company design-system repo). Project-agnostic.
SOC 職業分類に基づく
| name | review-pr |
| description | Review an exact PR head in isolation using trusted-base instructions and execution evidence |
| when_to_use | review PR, code review pull request, PR feedback, validate candidate |
| argument-hint | [PR_NUMBER_OR_URL] |
| user_invocable | true |
Review one exact pull-request candidate in an isolated checkout. Resolve trusted base instructions before executing head code, run repository-required evidence, bind findings to base/head SHAs, and never count the author's own review as an independent approval.
