本文へスキップ
TakoAPI
スキル一覧に戻る

agent-orchestrator

aatmaan1 作

AI & LLMs
9.1kダウンロード数はclawskills.shが公開している値です
24スター
1閲覧数
0件のいいねサインインするとこのスキルにいいねできます
—まだ評価がありません
あなたの評価

概要

Meta-agent skill for orchestrating complex tasks.

説明

このスキルでできること

A meta-agent skill that decomposes complex tasks into parallelizable subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, and consolidates their outputs. Agents communicate through a file-based inbox/outbox protocol, with status.json tracking each agent's state from pending to completed or failed.

Parallel sub-agent execution cuts total task time compared to sequential single-agent workflows, particularly when subtasks have no shared dependencies.

使いどころ

  • Running parallel research agents across multiple independent topics
  • Breaking a large codebase refactor into isolated agent-owned modules
  • Generating multi-section reports with dedicated collector, analyst, writer, and reviewer agents
  • Coordinating sequential data pipeline stages where one agent feeds the next
  • Delegating documentation tasks across specialized agents with automatic output consolidation

ワークフロー例

入力

User asks: Create a comprehensive market analysis report

エージェント
  1. 1

    Decompose the task into four subtasks: data collection, analysis, writing, and review, with an explicit dependency chain

  2. 2

    Generate a workspace and SKILL.md for each sub-agent using scripts/create_agent.py

  3. 3

    Write task instructions to each agent's inbox/ directory and set status.json to pending

  4. 4

    Spawn agents via the Task tool and poll status.json files until all report completed

  5. 5

    Collect outputs from each outbox/, merge sections, and run scripts/dissolve_agents.py to archive workspaces

出力

A consolidated market analysis report with a summary of each agent's deliverables and any issues encountered

インストール

clawhub install aatmaan1/agent-orchestrator

CLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。

リンク