What formats are supported for content extraction?

You can extract webpage content as Markdown, plain text, or raw HTML, making it easy to feed data back into Claude or other tools.

Does this skill require a manually started Chrome instance?

No, the skill automatically starts Chrome in headless mode if it is not already running, allowing for seamless automation.

Is it possible to automate logins or multi-step forms?

Yes, the 'form' and 'navigate' commands allow you to type into fields, select options, and click submit buttons while waiting for specific elements to load.

Can I capture specific parts of a webpage instead of the whole screen?

Yes, both the screenshot and extraction commands support CSS selectors, allowing you to target and capture specific elements on a page.

Browser Automation

Name: Browser Automation
Author: The-Focus-AI

byThe-Focus-AI

Browser Automation

Automates Google Chrome via the DevTools Protocol to perform web scraping, page captures, and form interactions directly from the terminal.

About

This skill provides a comprehensive toolkit for programmatic browser control, enabling Claude to interact with the web as a user would. It leverages the Chrome DevTools Protocol to facilitate headless browser operations including high-resolution full-page screenshots, PDF generation, and content extraction in Markdown or text formats. Whether you need to scrape data from JavaScript-heavy sites, automate complex form submissions, or record visual screencasts of web workflows, this skill offers a robust, zero-dependency solution for integrating real-time web data and interactions into your development process.

Key Features

Extract web content as Markdown, plain text, or HTML for easy processing.
Automate multi-step web interactions including clicking, typing, and navigation.
0 GitHub stars
Record browser sessions as frame-by-frame images for screencast generation.
Fill and submit complex web forms using CLI arguments or JSON data.
Capture full-page or element-specific screenshots and PDFs with custom scaling.

Use Cases

Generating automated visual documentation and PDF reports from live web applications.
Scraping structured content from modern, dynamic websites for data analysis or migration.
Performing end-to-end testing of user flows like authentication and registration.

About

Key Features

Extract web content as Markdown, plain text, or HTML for easy processing.
Automate multi-step web interactions including clicking, typing, and navigation.
0 GitHub stars
Record browser sessions as frame-by-frame images for screencast generation.
Fill and submit complex web forms using CLI arguments or JSON data.
Capture full-page or element-specific screenshots and PDFs with custom scaling.

Use Cases

Generating automated visual documentation and PDF reports from live web applications.
Scraping structured content from modern, dynamic websites for data analysis or migration.
Performing end-to-end testing of user flows like authentication and registration.