Can I extract content without raw HTML tags?

Yes, the extract command supports outputting content as cleaned Markdown or plain text, making it ideal for feeding data into other AI workflows.

What formats are supported for screenshots?

You can capture screenshots in PNG, JPEG, and WebP formats, with options for full-page captures or targeting specific elements via CSS selectors.

Does this skill require a running Chrome instance?

No, the skill scripts are designed to automatically start Chrome in headless mode if it is not already running.

Can I handle websites that require login?

Yes, you can use the navigate or form commands to log in, and the cookies command to save and load sessions for persistent authentication across browser restarts.

How does this handle very long web pages?

The skill includes an auto-scaling feature that ensures large screenshots fit within 8000px dimensions to satisfy standard API and system limits.

Chrome Browser Automation

Name: Chrome Browser Automation
Author: The-Focus-AI

byThe-Focus-AI

浏览器自动化

Automates Chrome browser interactions via the DevTools Protocol for web scraping, screenshots, and form filling.

关于

This skill provides a comprehensive suite of tools for programmatically controlling a Chrome browser directly from Claude Code. It enables users to capture full-page screenshots, generate high-quality PDFs from URLs, extract web content as Markdown or text, and automate complex workflows like multi-step form submissions and session management. By leveraging the Chrome DevTools Protocol, it offers a robust solution for developers needing to bridge the gap between AI-driven code generation and live web interaction without external dependencies.

主要功能

Content extraction from websites directly into Markdown, plain text, or HTML
High-fidelity PDF generation with customizable paper sizes, margins, and orientation
Full-page and element-specific screenshot capture in PNG, JPEG, and WebP formats
Automated form filling and multi-step web navigation with session persistence
Frame-by-frame screen recording for capturing web animations and visual processes
0 GitHub stars

使用场景

Automating competitive research by scraping data and capturing visual snapshots of competitor sites
Generating automated reports or documentation by converting live web dashboards into PDFs
Testing web application workflows by simulating user logins and complex form submissions

关于

主要功能

Content extraction from websites directly into Markdown, plain text, or HTML
High-fidelity PDF generation with customizable paper sizes, margins, and orientation
Full-page and element-specific screenshot capture in PNG, JPEG, and WebP formats
Automated form filling and multi-step web navigation with session persistence
Frame-by-frame screen recording for capturing web animations and visual processes
0 GitHub stars

使用场景

Automating competitive research by scraping data and capturing visual snapshots of competitor sites
Generating automated reports or documentation by converting live web dashboards into PDFs
Testing web application workflows by simulating user logins and complex form submissions