This is a reference guide for LangGraph 1.x workflow patterns covering state management, routing, parallel execution, and supervisor-worker architectures. It's organized as 37 discrete rules across 11 categories, each loaded on demand when you're building multi-agent systems or complex AI pipelines. The 1.2 release adds deferred nodes for end-of-run aggregation, node-level caching with SQLite or Redis backends, and model middleware hooks for compression or PII redaction without subclassing. Honestly, the real value is in the routing and state management sections since those are where most LangGraph workflows break in production. Good if you're past the hello-world phase and need patterns for fan-out/fan-in, retry loops, or checkpointing with PostgresSaver.
npx skills add https://github.com/yonatangross/orchestkit --skill langgraph