Skills for Real Engineers. Straight from my .agents directory.
langgraph-human-in-the-loop
Agent skill fromlangchain-ai/langchain-skills
INVOKE THIS SKILL when implementing human-in-the-loop patterns, pausing for approval, or handling errors in LangGraph. Covers interrupt(), Command(resume=...), approval/validation workflows, and the 4-tier error handling strategy.
How to install langgraph-human-in-the-loop
npx skills add langchain-ai/langchain-skills# or add only this skill to Claude Code: copy the folder
config/skills/langgraph-human-in-the-loop/
# into
~/.claude/skills/langgraph-human-in-the-loop/ (all projects)
.claude/skills/langgraph-human-in-the-loop/ (one project)
1<overview>2LangGraph's human-in-the-loop patterns let you pause graph execution, surface data to users, and resume with their input:34- **`interrupt(value)`** — pauses execution, surfaces a value to the caller5- **`Command(resume=value)`** — resumes execution, providing the value back to `interrupt()`6- **Checkpointer** — required to save state while paused7- **Thread ID** — required to identify which paused execution to resume8</overview>910---1112## Requirements1314Three things are required for interrupts to work:15161. **Checkpointer** — compile with `checkpointer=InMemorySaver()` (dev) or `PostgresSaver` (prod)172. **Thread ID** — pass `{"configurable": {"thread_id": "..."}}` to every `invoke`/`stream` call183. **JSON-serializable payload** — the value passed to `interrupt()` must be JSON-serializable1920---2122## Basic Interrupt + Resume2324`interrupt(value)` pauses the graph. The value surfaces in the result under `__interrupt__`. `Command(resume=value)` resumes — the resume value becomes the return value of `interrupt()`.2526**Critical**: when the graph resumes, the node restarts from the **beginning** — all code before `interrupt()` re-runs.2728<ex-basic-interrupt-resume>29<python>30Pause execution for human review and resume with Command.3132```python33from langgraph.types import interrupt, Command34from langgraph.checkpoint.memory import InMemorySaver35from langgraph.graph import StateGraph, START, END36from typing_extensions import TypedDict3738class State(TypedDict):39 approved: bool40…
Excerpt shown under the repository's MIT license.
More skills in langchain-skills
Similar skill repositories
An agentic skills framework & software development methodology that works.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
