web-access

Control Chrome via CDP proxy for DOM extraction, clicks, scrolling, and file uploads.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/LillianLi110130/bu_agent_cli --skill web-access-lillianli110130
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: web-access
Source: https://github.com/LillianLi110130/bu_agent_cli/tree/main/skills/web-access-main
Command: npx skills add https://github.com/LillianLi110130/bu_agent_cli --skill web-access-lillianli110130

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ws, node, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the need for authentic browser sessions to perform dynamic page interactions, login, DOM manipulation, and file uploads that standard HTTP requests cannot handle.

Core Features & Use Cases

  • Real Browser Sessions: Open and control Chrome instances for accurate DOM rendering and interaction.
  • DOM Extraction: Retrieve page titles, URLs, and specific DOM elements' data.
  • Interaction Automation: Perform clicks, scrolls, fills, and file uploads within real browser contexts.
  • Use Case: Automate login and data extraction from dynamic web pages that rely on user interactions or JavaScript rendering.

Quick Start

Run node "<skill_root>/scripts/check-deps.mjs" to verify environment readiness before initiating browser operations.

Frequently Asked Questions about web-access

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate DOM extraction and clicking on dynamic web pages that require JavaScript rendering?

Automate DOM extraction and clicking on dynamic web pages by controlling Chrome via CDP proxy. This approach enables real browser rendering, supporting scripted interactions like scrolling and filling for accurate data retrieval.

What is the best way to handle authenticated sessions and file uploads during browser automation?

Handling authenticated sessions and file uploads requires a real browser session via CDP proxy. This allows precise UI manipulation to maintain login states and perform visually driven interactions like file uploads that standard HTTP requests cannot manage.

Do I need Node.js to run Chrome CDP browser automation scripts?

Yes, Node.js is required to run the browser automation scripts. Run the check-deps script first to verify environment readiness, ensuring Node.js and other dependencies are properly configured before initiating Chrome operations.

Can I use Chrome CDP for web automation instead of Selenium?

Chrome CDP facilitates scripted browser automation tasks by controlling Chrome instances directly. It is suited for workflows requiring dynamic content handling, precise UI manipulation, and real browser rendering, serving as an alternative to Selenium for specific automation needs.

Why does standard HTTP requests fail for dynamic web page interaction and login automation?

Standard HTTP requests fail because they cannot handle dynamic page interactions, login automation, and DOM manipulation. A real Chrome browser session controlled via CDP proxy is necessary to execute JavaScript rendering and perform visually driven interactions.

Does this Chrome CDP automation support web page scrolling and filling form fields?

Yes, the Chrome CDP automation supports interaction automation including scrolling, filling form fields, and clicking. It controls real Chrome instances to perform these tasks within authenticated sessions and dynamic content environments.