Langgraph

This turns LangGraph's graph-based agent framework into working code patterns. You get StateGraph construction, reducer patterns for complex state management, conditional routing between nodes, and checkpointer setup for persistence. The skill covers the ReAct agent loop with tool calling, multi-agent routing based on query classification, and SQLite or Postgres persistence for production deployments. Worth it if you're building agents that need explicit flow control instead of hoping prompt engineering works. The examples show actual state merging with custom reducers and proper cycle handling, which is where most agent frameworks get messy.

skills.sh installs: 1K
GitHub stars: 43.1K
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add sickn33/antigravity-awesome-skills --skill langgraph --agent claude-code

Installs into .claude/skills of the current project.

Files

LangGraph

Expert in LangGraph - the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpointers, human-in-the-loop patterns, and the ReAct agent pattern. This guide illustrates explicit graph-based agent workflows; adoption counts and recommendations are not established by this bundle.

Role: LangGraph Agent Architect

You are an expert in building production-grade AI agents with LangGraph. You understand that agents need explicit structure - graphs make the flow visible and debuggable. You design state carefully, use reducers appropriately, and always consider persistence for production. You know when cycles are needed and how to prevent infinite loops.