skills.rest
ovisan
ovisanCOMMUNITY
Explore all skills by this author →
GitHub

browser-tools

Automate Chrome browser interactions via Chrome DevTools Protocol and Puppeteer.

2|Updated Mar 29, 2015
Search Tags:#javascript#browser automation#web scraping#frontend testing#puppeteer#dom inspection#chrome devtools protocol
One-click install
npx skills add https://github.com/ovisan/dotfiles --skill browser-tools-ovisan
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browser-tools
Source: https://github.com/ovisan/dotfiles/tree/main/.agents/skills/browser-tools
Command: npx skills add https://github.com/ovisan/dotfiles --skill browser-tools-ovisan

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires puppeteer-core, puppeteer, puppeteer-extra, puppeteer-extra-plugin-stealth, @mozilla/readability, jsdom, turndown, turndown-plugin-gfm, cheerio.

What problem does it solve? Manually testing web pages, debugging frontend behavior, and scraping JavaScript-rendered content is slow and error-prone. This Skill gives an AI agent direct control over a real Chrome browser so it can navigate pages, execute JavaScript, inspect the DOM, and extract content programmatically. ## Core Features & Use Cases - Browser Automation via CDP: Launch Chrome with remote debugging on port 9222, navigate tabs, evaluate arbitrary JavaScript, and capture screenshots using Puppeteer. - Interactive Element Picking: Let users visually click DOM elements in the browser to obtain CSS selectors, supporting multi-select with Cmd/Ctrl+Click. - Content Extraction & Debugging: Convert web pages to clean Markdown using Mozilla Readability and Turndown, inspect cookies for session debugging, and scrape Hacker News with Cheerio. - Use Case: A developer testing a frontend asks the agent to open the staging site, click through a checkout flow, read the resulting page state, and screenshot the result to verify the UI. ## Quick Start Ask the agent to start the browser and navigate to a URL, for example: open example.com in Chrome and tell me the page title.

Frequently Asked Questions about browser-tools

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

FAQPage Schema
How do I automate Chrome with Puppeteer and the DevTools Protocol?▼

Launch Chrome with the --remote-debugging-port=9222 flag, then connect using puppeteer-core's browserURL option pointing at http://localhost:9222. From there you can navigate pages, evaluate JavaScript, take screenshots, and read cookies.

How do I extract readable article content from a web page as Markdown?▼

Load the page in a real browser, grab the rendered HTML via the CDP DOM.getOuterHTML call, then parse it with Mozilla Readability and convert the result with Turndown. This handles JavaScript-rendered pages that plain HTTP fetches miss.

Can I reuse my existing Chrome login sessions for automation?▼

Yes. The start script supports a --profile flag that rsyncs your default Chrome profile into a separate data directory, preserving cookies and logins while excluding session lock files so a second instance can run.

Why does the script fail to connect to the browser?▼

Connection fails when Chrome is not running with remote debugging enabled on port 9222. Run the browser-start script first, which launches Chrome with the correct flags and waits until the debugging endpoint responds.

When should I use DOM evaluation instead of screenshots?▼

Prefer direct DOM evaluation with document.querySelectorAll and innerHTML when you need structured page state, since it is faster and machine-readable. Use screenshots only when visual verification of layout or rendering is required.

Related Skills

Explore More Software Engineering Skills→
devskaledevskale
1

web-browser

Control Chrome via DevTools Protocol to automate browsing tasks.

Community
Intermediate
hellosimplerickhellosimplerick

agent-browser

Automate browser navigation, form filling, data extraction, and screenshot capture.

Community
Intermediate
MathiasPaulenkoMathiasPaulenko

WaveXis Network Testing

Capture and manipulate HTTP/HTTPS traffic for performance auditing and API testing.

Community
Advanced
HouseGarofaloHouseGarofalo
3

playwright-mcp

Automate browser interactions and web scraping with the Playwright MCP server.

Official
Advanced