langgraph
LangGraph workflow patterns for agent orchestration
npx skills add majiayu000/claude-skill-registry --skill langgraph-skill --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 Patterns ## Graph Structure ```python from typing import TypedDict from langgraph.graph import StateGraph, END class GraphState(TypedDict): """State passed between nodes.""" input: str output: str | None error: str | None australian_context: dict | None # Locale info def create_graph() -> StateGraph: workflow = StateGraph(GraphState) # Add nodes workflow.add_node("process", process_node) workflow.add_node("validate", validate_node) workflow.add_node("respond", respond_node) # Set entry point workflow.set_entry_point("process") # Add edges workflow.add_edge("process", "validate") workflow.add_conditional_edges( "validate", check_validation, { "valid": "respond", "invalid": END, } ) workflow.add_edge("respond", END) return workflow.compile() ``` ## Node Implementation ```python async def process_node(state: GraphState) -> GraphState: """Process the input with Australian context.""" try: # Load Australian context if not present if not state.get("australian_context"): state["australian_context"] = { "locale": "en-AU", "currency": "AUD", "date_format": "DD/MM/YYYY", "timezone": "Australia/Brisbane" } result = await process_input(state["input"], state["australian_context"]) s
- Graph Structure
- Node Implementation
- State Management
- Checkpointing
- State Updates
- Conditional Routing
- Parallel Execution
- Multi-Agent Workflow Pattern
- Error Handling
- Australian Context in Workflows
- Testing Graphs
- Verification
- Integration with Agents
What does the langgraph skill do?
LangGraph workflow patterns for agent orchestration
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill langgraph-skill --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.