langgraph-orchestrationlisted

# LangGraph Orchestration Use this skill when the task is about building or fixing an orchestrated agent system on the LangGraph stack. This skill is written for the agent, not as user-facing docs. Favor shipped patterns and official APIs over improvised orchestration. ## First Move Classify the request before touching code: 1. **High-level agent harness**: prefer `deepagents.create_deep_agent(...)` 2. **General-purpose tool-calling agent**: prefer `langchain.agents.create_agent(...)` 3. **Custom workflow / graph topology**: prefer `langgraph.graph.StateGraph` 4. **MCP tool integration**: prefer `langchain_mcp_adapters` 5. **Human approval / resumability**: prefer `interrupt()` + checkpointer 6. **Specialist delegation**: prefer deep-agent subagents, or explicit subgraphs If more than one applies, choose the highest abstraction that still preserves the required control. Do not drop to raw `StateGraph` just because it is more familiar. ## Read Only What You Need - `references/decision-guide.md` for framework choice and migration choices - `references/langgraph-patterns.md` for `StateGraph`, `Command`, `Send`, reducers, routing, and durable execution - `references/deep-agents.md` for `create_deep_agent`, middleware, skills, filesystem, memory, and subagents - `references/mcp-bridging.md` for `langchain_mcp_adapters` patterns - `references/subagents-and-subgraphs.md` for delegation boundaries and isolation rules - `references/interrupts-hitl.md` for approval gates,