web-browser
Allows to interact with web pages by performing actions such as clicking buttons, filling out forms, and navigating links. It works by remote controlling Google Chrome or Chromium browsers using the Chrome DevTools Protocol (CDP). When Claude needs to browse the web, it can use this skill to do so.
When & Why to Use This Skill
This Claude skill enables advanced web interaction by remote-controlling Google Chrome or Chromium via the Chrome DevTools Protocol (CDP). It empowers Claude to navigate complex websites, perform actions like clicking and form filling, execute custom JavaScript, and capture screenshots, effectively transforming the AI into a highly capable web agent for real-time browsing and automation.
Use Cases
- Automated Data Extraction: Navigating dynamic websites and executing custom JavaScript to scrape structured data from complex web elements that require user interaction.
- Web Task Automation: Streamlining repetitive browser-based workflows such as filling out forms, navigating multi-step funnels, and automatically dismissing cookie consent banners.
- UI/UX Monitoring and Auditing: Capturing screenshots and monitoring console logs or network responses to ensure website functionality and visual integrity across different pages.
- Competitive Intelligence: Systematically browsing competitor sites to gather information on pricing, features, or content updates in real-time through automated navigation.
| name | web-browser |
|---|---|
| description | "Allows to interact with web pages by performing actions such as clicking buttons, filling out forms, and navigating links. It works by remote controlling Google Chrome or Chromium browsers using the Chrome DevTools Protocol (CDP). When Claude needs to browse the web, it can use this skill to do so." |
| license | Stolen from Mario |
Web Browser Skill
Minimal CDP tools for collaborative site exploration.
Start Chrome
./scripts/start.js # Fresh profile
./scripts/start.js --profile # Copy your profile (cookies, logins)
Start Chrome on :9222 with remote debugging.
Navigate
./scripts/nav.js https://example.com
./scripts/nav.js https://example.com --new
Navigate current tab or open new tab.
Evaluate JavaScript
./scripts/eval.js 'document.title'
./scripts/eval.js 'document.querySelectorAll("a").length'
./scripts/eval.js 'JSON.stringify(Array.from(document.querySelectorAll("a")).map(a => ({ text: a.textContent.trim(), href: a.href })).filter(link => !link.href.startsWith("https://")))'
Execute JavaScript in active tab (async context). Be careful with string escaping, best to use single quotes.
Screenshot
./scripts/screenshot.js
Screenshot current viewport, returns temp file path
Pick Elements
./scripts/pick.js "Click the submit button"
Interactive element picker. Click to select, Cmd/Ctrl+Click for multi-select, Enter to finish.
Dismiss Cookie Dialogs
./scripts/dismiss-cookies.js # Accept cookies
./scripts/dismiss-cookies.js --reject # Reject cookies (where possible)
Automatically dismisses EU cookie consent dialogs.
Run after navigating to a page:
./scripts/nav.js https://example.com && ./scripts/dismiss-cookies.js
Background Logging (Console + Errors + Network)
Automatically started by start.js and writes JSONL logs to:
~/.cache/agent-web/logs/YYYY-MM-DD/<targetId>.jsonl
Manually start:
./scripts/watch.js
Tail latest log:
./scripts/logs-tail.js # dump current log and exit
./scripts/logs-tail.js --follow # keep following
Summarize network responses:
./scripts/net-summary.js