Browse, capture, extract, and audit from one CLI.
What it does
Automates web navigation, page inspection, screenshots, form interaction, screencasts, JavaScript execution, and design audits.
When to use it
Use when an agent needs to browse pages, capture or extract their contents, interact with them, record them, or audit designs.
How to use it
Give it a browser task; it navigates or inspects pages, performs requested interactions, and returns the resulting information.
Latest review
What you need · 1
A Chrome or Chromium binary is required for the browser process.
Access · 7
This skill
website forms
Write
Submits values through website forms
web pages
Read
Reads and inspects web pages
JavaScript in page context
Execute
JavaScript inside web pages