Agent skill · software engineering · yonatangross
langgraph
LangGraph 1.x (LTS) Python workflow patterns for state management, delta channels, resilience (node timeouts, error handlers, graceful drain), routing, parallel execution, supervisor-worker, tool calling, checkpointing, human-in-loop, streaming (v2 format), subgraphs, and functional API. Use when building LangGraph pipelines, multi-agent systems, or AI workflows.
Why this skill is useful
Adds comprehensive patterns and executable scripts for building resilient LangGraph workflows that enhance AI capabilities in multi-agent systems.
What it needs
Requires langgraph installed locally. About 8k tokens when loaded. Last updated 2026-08-06. 215 stars on the source repository.
What this skill does
LangGraph Workflow Patterns Comprehensive patterns for building production LangGraph workflows. LangGraph 1.x is LTS (Long Term Support) — the first stable major release, powering agents at Uber, LinkedIn, and Klarna. Each category has individual rule files in rules/ loaded on-demand. LangGraph 1.2 (shipped 2026-05-12) — the fault-tolerance release. Everything below is on StateGraph.addnode(...) unless noted: - Per-node timeouts — timeout= accepts float timedelta TimeoutPolicy. TimeoutPolicy(runtimeout=, idletimeout=, refreshon="auto" "heartbeat") separates a hard wall-clock cap from an idle cap that progress refreshes. On expiry LangGraph raises NodeTimeoutError (carrying kind="idle" "run" and elapsed), drops that attempt's writes, and defers to the retry policy. Cooperative: it rides asyncio cancellation, so a node blocking the GIL is not interrupted. See rules/resilience-node-timeouts.md. - Node error handlers — errorhandler= registers a recovery node that runs once the retry budget is exhausted. It receives failure context by declaring a parameter typed NodeError (fields node, error) and returns a Command to update state and reroute. See rules/resilience-error-handlers.md. - RunControl (langgraph.runtime) — cooperative graceful shutdown. requestdrain(reason) from any thread; nodes poll runtime.drainrequested and stop at a checkpoint boundary, leaving a resumable thread instead of a half-applied superstep. See rules/resilience-graceful-drain.md. - DeltaChannel (langgraph.channels.delta, beta) — checkpoints store only incremental writes and replay them through a batch reducer, with a snapshot every snapshotfrequency updates. Fixes checkpoint cost growing with thread length. Its reducer takes a batch and must be batching-invariant. See rules/state-delta-channel.md. - runtime.heartbeat() — explicit progress signal, the only one that refreshes an idle timeout under refreshon="heartbeat". …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills yonatangross/langgraph--5c1317