magnus919_agent-skills/langgraph/README.md

LangGraph — Stateful Multi-Agent Orchestration

Build multi-agent AI systems with LangGraph — the low-level orchestration framework for stateful, graph-based agent workflows. The foundation for agents in the LangChain ecosystem.

Why Install This Skill

When your agent loads this skill, it becomes a LangGraph architect who can:

• Design graph topologies — nodes, edges, state schemas, reducers
• Implement multi-agent patterns — supervisor, swarm, and hierarchical orchestration
• Add persistence — checkpointers and stores for long-running agents
• Handle production complexity — branching, cycles, parallel execution, human-in-the-loop
• Evaluate agent performance — systematic eval methodology
• Debug production failures — common failure modes and how to trace them

What You Get

Directory	Purpose
SKILL.md	Quick start, design principles, pattern selection guide
scripts/	Supervisor scaffold, swarm scaffold, eval generator
templates/	3 runnable template implementations
references/	8 reference files: architecture, each pattern in depth, evals, production failures, troubleshooting

Triggers

Load this when designing agent architectures that need cycles, conditional branching, parallel execution, or human-in-the-loop patterns.

Requirements

Python 3.8+ with langgraph, langchain, and langchain-openai packages.

Quick Start

Start with the setup and first workflow in SKILL.md, then use the linked resources for the specific task you need to complete.