multi-agent-orchestration

# Multi-Agent Orchestration Skill > Decompose complex problems into agent-appropriate subtasks, delegate effectively, and synthesize results. ## ⚠️ Rapid Evolution Domain Multi-agent patterns are evolving rapidly. This skill captures stable patterns while acknowledging the field is in flux. **Refresh triggers:** - New orchestration frameworks (LangGraph, AutoGen, CrewAI releases) - Claude/GPT native multi-agent features - VS Code Copilot agent architecture changes **Last validated:** February 2026 --- ## Core Concepts ### When to Use Multi-Agent | Scenario | Single Agent | Multi-Agent | |----------|--------------|-------------| | Simple code edit | ✅ | ❌ Overkill | | Multi-file refactor | ✅ (if capable model) | ⚠️ Consider | | Research + implement | ⚠️ Long context | ✅ Decompose | | Cross-domain task | ❌ Context overload | ✅ Specialists | | Parallel independent work | ❌ Sequential | ✅ Parallel agents | ### Agent Roles | Role | Responsibility | Example | |------|---------------|---------| | **Orchestrator** | Decompose, delegate, synthesize | Main chat session | | **Specialist** | Deep expertise in one domain | Security reviewer agent | | **Worker** | Execute well-defined subtask | "Find all usages of X" | | **Critic** | Validate, review, improve | Code review agent | --- ## Decomposition Patterns ### 1. **Horizontal Decomposition** (Parallel) Split task into independent subtasks that can run simultaneously. ``` ┌─────────────────┐ │ Orchestrator │ └──────...