langgraph-functional
LangGraph Functional API with @entrypoint and @task decorators. Use when building workflows with the modern LangGraph pattern, enabling parallel execution, persistence, and human-in-the-loop.
npx skills add majiayu000/claude-skill-registry --skill langgraph-functional --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 Functional API Build workflows using decorators instead of explicit graph construction. ## Overview - Sequential workflows with conditional branching - Orchestrator-worker patterns with parallel execution - Workflows needing persistence and checkpointing - Human-in-the-loop approval flows - Simpler alternative to explicit StateGraph construction ## Core Concepts ### Graph API vs Functional API ``` Graph API (explicit): Functional API (implicit): StateGraph → add_node → @task functions + add_edge → compile @entrypoint orchestration ``` **When to Use Functional API**: - Sequential workflows with conditional logic - Orchestrator-worker patterns - Simpler debugging (regular Python functions) - Parallel task execution ## Quick Start ### Basic Pattern ```python from langgraph.func import entrypoint, task @task def step_one(data: str) -> str: """Task returns a future - call .result() to block""" return process(data) @task def step_two(result: str) -> str: return transform(result) @entrypoint() def my_workflow(input_data: str) -> str: # Tasks return futures - enables parallel execution result1 = step_one(input_data).result() result2 = step_two(result1).result() return result2 #
- Overview
- Core Concepts
- Graph API vs Functional API
- Quick Start
- Basic Pattern
- Key Rules
- Parallel Execution
- Fan-Out Pattern
- Map Over Collection
- Persistence & Checkpointing
- Enable Checkpointing
- Access Previous State
- Human-in-the-Loop
- Interrupt for Approval
What does the langgraph-functional skill do?
LangGraph Functional API with @entrypoint and @task decorators. Use when building workflows with the modern LangGraph pattern, enabling parallel execution, persistence, and human-in-the-loop.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill langgraph-functional --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.