LangChain

Use this skill to build or refactor LangChain application logic with predictable tool use, structured outputs, and clean runtime boundaries.

Quick Triage

• Use this skill when the task is primarily chain/agent composition, tool calling, middleware, output schemas, or prompt wiring.
• Switch to $langgraph when the core problem is graph topology, node routing, checkpoints, interrupts, or multi-step state machines.
• Switch to $ag-ui when the core problem is event protocol compliance between backend and UI.
• Switch to $copilotkit when the core problem is frontend coagent UX, hooks, and runtime provider wiring.

Workflow

1. Confirm language/runtime surface first. Choose Python or TypeScript and identify existing package boundaries before code edits.
2. Define the contract before implementation. Lock input shape, output shape, tool schema, and failure behavior.
3. Choose abstraction level deliberately. Use simple LCEL chains when tools are not required; use create_agent when iterative tool use is needed.