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.

Vision-driven browser automation v1.0.0

Use this resource to navigate, extract data or test a web interface through vision

New

  • 356 downloads
  • 223 likes
  • 243 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install vision-browser-automation

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 drives a headless browser from screenshots using natural language: it clicks, fills forms, uploads files and checks page state. You get the extracted results, screenshots and a test report.

Mostly picked by

Updated November 2, 2026

Card for the “Vision-driven browser automation” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: action commands (click, type, upload, verify)
  • SKILL.md: headless, CDP and Bridge modes to connect to an existing Chrome
  • SKILL.md: rules for running commands one at a time

Good fit for

  • You want to check that a form still works after a deployment
  • You need to extract data from a site that has no API

Not for

    Tags

    • browser
    • testing
    • extraction
    • automation

    About

    You say

    “Open the pricing page, check that the buy button works and take a screenshot.”

    Card for the “Vision-driven browser automation” skill

    Skill published by web-infra-dev 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 navigate, extract data or test a web interface through vision
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md24.2 KB

    Origin and licence

    Listed unmodified

    Author
    web-infra-dev
    Source
    github.com/web-infra-dev/midscene-skills/tree/dec1d1c55252ecb1a90c4ecbcfd0d2cb3ce0ac7b/skills/browser
    Licence
    MIT

    Notice

    « browser-automation » (web-infra-dev, 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.