LangGraph workflow patterns for stateful multi-step LLM workflows. State schemas (TypedDict/Pydantic), conditional routing, parallel fan-out/fan-in, human-in-the-loop gates, checkpointing, and supervisor agents. Use when: building LangGraph workflows, adding approval steps, coordinating agents, or persisting state. Triggers on: LangGraph, workflow graph, conditional routing, human-in-loop, checkpointing, supervisor agent, state machine, fan-out
$npx -y skills add ariegoldkin/claude-forge --skill langgraphInstalls into the current project.
Run `npx skills use "https://github.com/ariegoldkin/claude-forge" --skill "ariegoldkin/claude-forge/langgraph"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/ariegoldkin/claude-forge" that are relevant to the current task. Run `npx skills add "https://github.com/ariegoldkin/claude-forge"` and select the relevant skills, then follow their instructions.