graph-agents-cli-langgraph-code
This skill should be used when the user wants to "write agent code", "build an agent with LangGraph", "add a tool", "add a node to the graph", "use a checkpointer", "stream events", "add human-in-the-loop", "add a subgraph", "switch the model provider", "implement the auth policy", "call an external API from a tool", or needs LangGraph and LangChain patterns for a graph-agents-cli project. Covers create_agent and StateGraph, tools with the API_CALLS declaration, memory vs postgres checkpointers and thread_id, streaming, interrupts, subgraphs, init_chat_model provider switching, the fake provider for tests, the auth policy adapter, the API client and api-policy.yaml, and telemetry opt-in. Do NOT use for scaffolding (graph-agents-cli-scaffold), evaluation (graph-agents-cli-eval), or deployment (graph-agents-cli-deploy).
- Version
- 0.3.1
Pinned to revision 540e2a351795, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/graph-agents-cli-langgraph-code/SKILL.md
- skills/graph-agents-cli-langgraph-code/references/langchain-models.md
- skills/graph-agents-cli-langgraph-code/references/langgraph.md
- skills/graph-agents-cli-langgraph-code/references/template-contract.md
Every link opens the file at its source, pinned to the revision this page describes.