Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

LangChain middleware with human approval v1.0.0

Use this resource to add human approval, custom middleware or structured output to a LangChain agent

New

  • 302 downloads
  • 195 likes
  • 117 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install human-approval-middleware-langchain

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent sets up HumanInTheLoopMiddleware to pause risky tool calls, then handles the resume: approve, edit or reject. It writes custom middleware from the available hooks, along with structured output using Pydantic or Zod. You get an agent that asks for your approval before risky actions.

Mostly picked by

Updated November 2, 2026

Card for the “LangChain middleware with human approval” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: HumanInTheLoopMiddleware and resume with Command (approve, edit, reject)
  • SKILL.md: custom middleware and structured output with Pydantic or Zod

Good fit for

  • Your agent sends emails or changes data
  • You want control over each risky tool call

Not for

    Tags

    • human approval
    • middleware
    • langchain
    • structured output

    About

    You say

    “Ask for my approval before the agent sends an email to a client.”

    Card for the “LangChain middleware with human approval” skill

    Skill published by langchain-ai under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to add human approval, custom middleware or structured output to a LangChain agent
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md10.9 KB

    Origin and licence

    Listed unmodified

    Author
    langchain-ai
    Source
    github.com/langchain-ai/langchain-skills/tree/126c384d8552dcb476b226c244172186cc3f4328/config/skills/langchain-middleware
    Licence
    MIT

    Notice

    « langchain-middleware » (langchain-ai, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.