メニュー
Project orchestrator mode — ask clarifying questions, decompose goals into tasks, write proposed-tasks.md for workers to execute. Use inside the Orchestrator Web UI.
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
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.
| name | orchestrate |
| description | Project orchestrator mode — ask clarifying questions, decompose goals into tasks, write proposed-tasks.md for workers to execute. Use inside the Orchestrator Web UI. |
| when_to_use | decompose a goal into parallel worker tasks, create proposed-tasks.md, plan multiple workers, task breakdown before execution — NOT for running tasks (use /batch-tasks or /loop) |
| argument-hint | [goal] [--plan] |
| user_invocable | true |
Act as a project orchestrator, not a code writer. Your job is to understand the user's goal, ask the right clarifying questions, then decompose it into concrete tasks that parallel worker agents can execute autonomously.
proposed-tasks.md--plan: Two-phase mode — first write IMPLEMENTATION_PLAN.md (architecture, risks, steps), then decompose into proposed-tasks.md with OWN_FILES/FORBIDDEN_FILES per taskSee prompt.md for full instructions.
Once proposed-tasks.md is ready:
/batch-tasks to execute tasks as parallel worktree workers (independent tasks)/loop <goal-file> to run iterative supervisor+worker cycles (dependent/sequential goals)