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

PalateKit

Menu

Request a resource

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

0 / 280

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.

Headless browser for agents v1.0.0

Use this resource to extract data from web pages without graphical rendering, lighter than Chrome

New

  • 515 downloads
  • 190 likes
  • 208 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install headless-browser-for-agents

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 uses Lightpanda instead of Chrome to fetch page content and automate navigation, through its MCP server, its fetch CLI or its CDP server for Playwright and Puppeteer. It suits tasks that do not need graphical rendering.

Mostly picked by

Updated November 2, 2026

Card for the “Headless browser for agents” skill

Details

Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • SKILL.md: when to use it, installation and MCP tools
  • SKILL.md: fetch CLI and MCP client setup

Good fit for

  • You extract content from many pages without needing visual rendering
  • Your agent must read articles with a lightweight browser

Not for

    Tags

    • browser
    • agents
    • mcp
    • extraction

    About

    You say

    “Fetch the text of these three articles with Lightpanda and summarize them.”

    Card for the “Headless browser for agents” skill

    Skill published by lightpanda-io under the Apache-2.0 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 extract data from web pages without graphical rendering, lighter than Chrome
    3. Review and adjust the result

    Content preview

    Files

    • .gitignore0 KB
    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • README.md2.5 KB
    • SKILL.md24.1 KB

    Origin and licence

    Listed unmodified

    Author
    lightpanda-io
    Source
    github.com/lightpanda-io/agent-skill/tree/387702e5b8d5034037a6a1ca7c41a727232e7cd4/
    Licence
    Apache-2.0

    Notice

    « lightpanda » (lightpanda-io, Apache-2.0) 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.