agentsclimarketplace
Sign in

Langgraph

Skill 264Gaurav/DeepAgents/deepagents/skills/langgraph

LangGraph expertise for building stateful, multi-step agent workflows. Use when the user asks about LangGraph, StateGraph, nodes, edges, conditional routing, checkpointers, persistence, memory, human-in-the-loop, subgraphs, streaming, or building agents with langgraph / langchain. Provides architecture patterns, API workflows, and runnable examples.From its SKILL.md

Install
npx -y skills add 264Gaurav/DeepAgents --skill langgraph

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.2 KB, 404 tokens by cl100k_base, as published. Nobody here has run it

LangGraph Skill

You are acting as a LangGraph specialist. Use this skill whenever the user's query involves building, debugging, or understanding LangGraph applications — graphs, agents, state management, persistence, or streaming.

When to Use

  • User asks to build an agent or workflow with LangGraph
  • User mentions: StateGraph, nodes, edges, add_conditional_edges, MessagesState, checkpointer, MemorySaver, thread_id, interrupt, Command, subgraphs
  • User asks how to add memory / persistence / human-in-the-loop to an agent
  • User is debugging LangGraph state, routing, or streaming behavior

Supporting Files (read these for deeper context)

  • instructions.md — detailed build workflow, state design rules, and common pitfalls
  • examples.md — runnable graph examples (basic graph, conditional routing, memory, tools)

Core Workflow

  1. Read instructions.md in this skill folder for the full build methodology.
  2. Identify the graph shape: linear pipeline, router, agent loop, or multi-agent.
  3. Design the state schema FIRST (TypedDict / Pydantic with reducers).
  4. Define nodes as pure functions: state -> partial state update.
  5. Wire edges (static, then conditional), compile with a checkpointer if memory is needed.
  6. Show how to invoke with thread_id config and how to stream.
  7. Match the patterns in examples.md when one applies.

Quick Standards

  • Always show the state schema before the graph wiring
  • Nodes return partial updates, never mutate state in place
  • Use MessagesState / add_messages reducer for chat history
  • Checkpointer (MemorySaver for demos, SQLite/Postgres for prod) + thread_id = memory
  • Prefer create_react_agent / create_deep_agent prebuilts before hand-rolling loops

What ships with it: 2 files

7.3 KB alongside SKILL.md

Keep looking

Skills are one crate of 326,835. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.