agent-orchestrator
Coordinates complex tasks by assigning responsibilities to specific agents based on project definitions.
Install
mkdir -p .claude/skills/agent-orchestrator && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12523" && unzip -o skill.zip -d .claude/skills/agent-orchestrator && rm skill.zipInstalls to .claude/skills/agent-orchestrator
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
`.agent/agents/` のエージェント定義を入口に、タスクを調査・計画・実装・レビュー・検証へ分担するスキル。ユーザーが「エージェント」「マルチエージェント」「orchestrator」「役割分担」「複数担当」などを求めたとき、または大きな変更で担当境界を決める必要があるときに使う。Key capabilities
- →Divide tasks into investigation, planning, implementation, review, and verification stages
- →Select necessary agents based on `.agent/agents/` definitions
- →Determine work order and writing scope for agents
- →Refer to `AGENTS.md` and agent definitions for guidance
- →Execute commands like `/orchestrate` and `/agent-review-flow`
How it works
The skill orchestrates multi-agent workflows by referencing agent definitions to divide tasks into stages, select agents, and define their work order and scope.
Inputs & outputs
When to use agent-orchestrator
- →Planning large refactors
- →Assigning tasks to specialized agents
- →Managing multi-agent projects
About this skill
Agent Orchestrator
このファイルは Codex 実行用の入口とメタデータを管理する。
手順本文の正本は .claude/skills/agent-orchestrator/SKILL.md に置く。必ず正本を読み、そのすべてに従う。ここには手順を写さない。
Codex での差分
- 正本の参照順 5 の「関連する
.claude/skills/*/SKILL.md」は、対応する.codex/skills/*/SKILL.mdの「Codex での差分」もあわせて読む。 - 担当を分けると決めた場合も、
assets/docs/ai-runtime-governance.mdのとおり、Codex では 1 つのセッションで担当の順に行う。開始時の宣言では、選んだ担当と順序を示す。
When not to use it
- →When the task does not involve multi-agent collaboration
- →When the changes are small and do not require task division
- →When agent definitions are not available in `.agent/agents/`
Limitations
- →It relies on agent definitions in `.agent/agents/`
- →It requires `AGENTS.md` for reference
- →Detailed execution rules are located in a separate file
How it compares
This skill provides a structured approach to multi-agent task orchestration by explicitly defining agent responsibilities and work boundaries based on agent definitions, unlike a single-agent workflow.
Compared to similar skills
agent-orchestrator side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| agent-orchestrator (this skill) | 0 | 6mo | No flags | Intermediate |
| planning-with-files | 233 | 10mo | Review | Intermediate |
| ralph-plan | 14 | 10mo | No flags | Beginner |
| agent-planner | 3 | 9mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
planning-with-files
davila7
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
ralph-plan
mastra-ai
Interactive planning assistant that helps create focused, well-structured ralph-loop commands through collaborative conversation
agent-planner
ruvnet
Agent skill for planner - invoke with $agent-planner
llm-council
am-will
Orchestrate a configurable, multi-member CLI planning council (Codex, Claude Code, Gemini, OpenCode, or custom) to produce independent implementation plans, anonymize and randomize them, then judge and merge into one final plan. Use when you need a robust, bias-resistant planning workflow, structured JSON outputs, retries, and failure handling across multiple CLI agents.
agent-queen-coordinator
ruvnet
Agent skill for queen-coordinator - invoke with $agent-queen-coordinator
swarm-planner
am-will
[EXPLICIT INVOCATION ONLY] Creates dependency-aware implementation plans optimized for parallel multi-agent execution.