How does it handle agent routing?

It guides you through selecting the best strategy—Keyword, LLM-based, Semantic, or Rule-based—based on your specific complexity requirements and latency needs.

What orchestration patterns can I implement?

You can choose from five primary patterns: Delegation (task routing), Sequential (pipelines), Parallel (concurrent execution), Hierarchical (manager-worker), and Mesh (peer-to-peer collaboration).

Which AI frameworks are compatible with this skill?

This skill provides specific implementation patterns and RAG queries for Google ADK, LangGraph, CrewAI, and OpenAI's multi-agent handoff architecture.

Does this skill help with state management between agents?

Yes, it includes detailed patterns for shared dictionaries, message history passing, external persistence stores, and event-driven state sharing.

Multi-Agent Orchestration

Name: Multi-Agent Orchestration
Author: MattMagg

byMattMagg

•

Ciencia de Datos y ML

Architects complex multi-agent systems and workflows using standardized patterns across major AI frameworks.

Acerca de

The Multi-Agent Orchestration skill provides a comprehensive blueprint for building, managing, and optimizing multi-agent AI systems within Claude Code. It offers structured guidance on implementing various orchestration patterns—such as delegation, hierarchical management, and agent meshes—tailored specifically for frameworks like Google ADK, LangGraph, CrewAI, and OpenAI. By leveraging targeted RAG queries and best practices for routing, state sharing, and error handling, this skill helps developers avoid common pitfalls like infinite loops or context loss, ensuring the creation of resilient and efficient agentic workflows.

Características Principales

Support for major frameworks including LangGraph, CrewAI, and Google ADK
2 GitHub stars
Pre-configured RAG queries for framework-specific code implementation
Standardized orchestration patterns: Delegation, Sequential, Parallel, Hierarchical, and Mesh
Comprehensive state management patterns for synchronous and persistent workflows
Advanced routing strategies including LLM-based classification and semantic routing

Casos de Uso

Developing high-performance parallel execution workflows to reduce LLM latency
Creating a sequential research and content generation pipeline with automated handoffs
Building a hierarchical customer support system where a manager agent routes queries to specialists

Acerca de

Características Principales

Support for major frameworks including LangGraph, CrewAI, and Google ADK
2 GitHub stars
Pre-configured RAG queries for framework-specific code implementation
Standardized orchestration patterns: Delegation, Sequential, Parallel, Hierarchical, and Mesh
Comprehensive state management patterns for synchronous and persistent workflows
Advanced routing strategies including LLM-based classification and semantic routing

Casos de Uso

Developing high-performance parallel execution workflows to reduce LLM latency
Creating a sequential research and content generation pipeline with automated handoffs
Building a hierarchical customer support system where a manager agent routes queries to specialists