skills.rest
tianzecn
tianzecnCOMMUNITY
Explore all skills by this author →
GitHub

browsing

Automate browser tasks via Chrome DevTools Protocol with action-based APIs.

2|Updated Dec 25, 2025
One-click install
npx skills add https://github.com/tianzecn/myclaudecode --skill browsing-tianzecn
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browsing
Source: https://github.com/tianzecn/myclaudecode/tree/main/plugins/superpowers-chrome/skills/browsing
Command: npx skills add https://github.com/tianzecn/myclaudecode --skill browsing-tianzecn

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires chrome-ws, and includes references (resource) components.

What problem does it solve?

This Skill enables direct browser automation via Chrome DevTools Protocol for actions like navigation, element interaction, extraction, and screenshots.

Core Features & Use Cases

  • Navigation & Interaction: move through pages, fill forms, click elements.
  • Extraction & Capture: read text, attributes, and take screenshots.
  • Multi-Tab & Async: manage tabs and dynamic content.

Quick Start

Navigate to a page, wait for an element, then extract text from a heading.

Frequently Asked Questions about browsing

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

FAQPage Schema
How do I automate browser tasks with Chrome DevTools Protocol?▼

Chrome DevTools Protocol (CDP) enables direct browser automation through WebSocket connections. This Skill provides an action-based API to navigate pages, interact with elements, extract content, and capture screenshots by controlling Chrome instances locally or remotely, supporting headless and headed modes.

Can I use CDP to fill forms and click elements on a webpage?▼

Yes. This Skill offers form automation through type, select, and click actions, plus element waiting via await_element and await_text to handle dynamic content before interacting with forms or buttons.

How do I extract text and attributes from a webpage using CDP?▼

Extract text, attributes, and DOM data using the extract and attr actions to read element content, then use eval to run JavaScript for custom queries. Screenshots capture full page state for visual validation.

Does this work with multi-tab automation and tab management?▼

Yes. The Skill manages multiple tabs via list_tabs, new_tab, and close_tab actions, addressing tabs by index or WebSocket URL for coordinated workflows across sessions.

What environments support this Chrome DevTools Protocol automation?▼

This Skill requires Chrome or Chromium with CDP enabled, WebSocket access to the remote debugging port, and environments where the MCP use_browser tool is available or direct CLI/CDP access is configured with optional host/port override.

When should I use direct CDP instead of higher-level browser tools?▼

Use CDP when you need fine-grained control, real-time session management, multi-tab coordination, or when higher-level tools are unavailable. CDP offers lower latency and direct access to browser internals for complex automation scenarios.

Related Skills

adampetrovicadampetrovic
2

web-browser

Control Chrome/Chromium via the Chrome DevTools Protocol to navigate, execute JavaScript, and capture screenshots.

Community
Intermediate
ddarkrddarkr
5

oma-pdf

Convert PDF files into structured Markdown with text, tables, headings, and images.

Community
Intermediate
ssdeanxssdeanx
43

browser

Automate Chrome browser tasks via Chrome DevTools Protocol over WebSocket.

Community
Intermediate
SecurityRoninSecurityRonin
1

browser-automation

Automate browser tasks and testing across Playwright, Puppeteer, Selenium, and CDP workflows.

Official
Intermediate