LangChain Skills

Covers building Deep Agents applications: create_deep_agent, harness architecture and configuration.

Covers creating LangChain agents with create_agent, defining tools and using middleware.

Covers LangChain middleware: human approval of risky tool calls, custom middleware and structured output.

Covers building RAG systems with LangChain: document loaders, text splitters, embeddings and vector stores.

Covers writing LangGraph code: StateGraph, state schemas, nodes, edges, streaming and error handling.

Covers human-in-the-loop patterns in LangGraph: interrupts, approval workflows and error handling.

Covers persistence in LangGraph: checkpointers, thread ids, time travel and the Store.