langgraph-python
Design and build AI agents with LangGraph. Use when building ReAct agents, multi-agent systems, workflow orchestration, human-in-the-loop patterns, or state machine workflows.
npx skills add majiayu000/claude-skill-registry --skill langgraph-python --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# LangGraph Skill LangGraph: Framework for stateful, multi-actor AI applications. **For latest API syntax, use `context7` MCP.** --- ## Core Concepts ```python from langgraph.graph import StateGraph, MessagesState, START, END from langgraph.prebuilt import create_react_agent, ToolNode, tools_condition from langgraph.types import Command, interrupt, Send from langgraph.checkpoint.memory import InMemorySaver ``` | Concept | Description | |---------|-------------| | **StateGraph** | Graph managing state. Updates after each node | | **MessagesState** | Built-in state for chat (includes messages list) | | **Node** | Function: receives state → returns updates | | **Edge** | Transition: static (`add_edge`) or conditional | | **Checkpointer** | Persistence for conversation history, pause/resume | | **Command** | Dynamic routing + state update together | | **interrupt** | Pause for human-in-the-loop | | **Send** | Dynamically spawn parallel workers | --- ## Pattern Selection Guide ``` Need to use tools? ├─ Yes → ReAct Agent └─ No → Workflow patterns Sequential or parallel? ├─ Sequential → Prompt Chaining ├─ Parallel → Parallelization └─ Both → Orchestrator-Worker Different handling by input
- Core Concepts
- Pattern Selection Guide
- 1. ReAct Agent (Tool-Using)
- 2. Prompt Chaining (Sequential)
- 3. Parallelization
- 4. Routing
- 5. Orchestrator-Worker (Send)
- 6. Evaluator-Optimizer (Reflection)
- 7. Multi-Agent: Supervisor
- 8. Multi-Agent: Hierarchical
- 9. Human-in-the-Loop
- Persistence (Memory)
- State Definition
- Common Errors & Fixes
What does the langgraph-python skill do?
Design and build AI agents with LangGraph. Use when building ReAct agents, multi-agent systems, workflow orchestration, human-in-the-loop patterns, or state machine workflows.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill langgraph-python --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.