langgraph

SKILL.md

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.

Why bad: Agent loops forever. Burns tokens and costs. Eventually errors out.

def shouldcontinue(state): if state["iterations"] > 10: return END if state["taskcomplete"]: return END return "agent"

LangGraph 專家 - 用於構建有狀態、多參與者 AI 應用程序的生產級框架。涵蓋圖構建、狀態管理、循環和分支、檢查點持久性、人機循環模式和 ReAct 代理模式。在 LinkedIn、Uber 和 400 多家公司的生產中使用。這是浪鏈推薦的構建代理方式。使用時：langgraph、langchain 代理、有狀態代理、代理圖、反應代理。 來源：sickn33/antigravity-awesome-skills。

查看原文