Edge Copy setup link
Skill evidence / Langchain Middleware
langchain-ailangchain-skills15,600 installs on skills.sh

Langchain Middleware

INVOKE THIS SKILL when you need human-in-the-loop approval.

Copy setup link

Works in any agent

langchain-ai/langchain-skillspinned a76fef3
✓ Security state: reviewed

2 static scans, 0 counted findings.

Recorded for this package revision; Edge checks the exact bundle again when your agent loads it.

SKILL.md1 file · 10.5 KB
From langchain-ai’s public repository. Edge did not write or edit this skill.

What this skill does for you

INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of dangerous tool calls, creating custom middleware with hooks, Command resume patterns, and structured output with Pydantic/Zod.

Quoted from the skill description in the pinned source

Use it with Edge

Set up Edge for me: read getedge.cc/SKILL.md and follow it. Then use Edge to load the langchain-middleware skill from langchain-ai/langchain-skills.

Paste it into Claude, ChatGPT, Codex or Cursor.

Or read the skill source first.

Try Langchain Middleware in your agent.

INVOKE THIS SKILL when you need human-in-the-loop approval.

Copy setup link