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 and automation by remote-controlling Chrome or Chromium browsers via the Chrome DevTools Protocol (CDP). It allows Claude to perform human-like actions such as navigating URLs, clicking buttons, filling forms, and executing custom JavaScript, making it an essential tool for real-time web exploration, automated testing, and dynamic data retrieval.
Use Cases
- Automated Web Exploration: Navigating through complex websites to find specific information or perform multi-step workflows that require browser state management.
- Dynamic Data Extraction: Executing custom JavaScript snippets to scrape data from modern, JavaScript-heavy web applications that traditional scrapers cannot handle.
- Visual Verification and Auditing: Capturing high-quality screenshots of web pages to monitor layout changes, verify UI elements, or archive web content.
- Form and Process Automation: Automating repetitive tasks such as filling out web forms, logging into portals, and submitting data across various web interfaces.
- Interactive Element Selection: Using the built-in element picker to precisely identify and interact with specific UI components for debugging or workflow recording.
| 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
./tools/start.js # Fresh profile
./tools/start.js --profile # Copy your profile (cookies, logins)
Start Chrome on :9222 with remote debugging. Auto-detects platform (macOS/Linux/WSL) and searches for Chrome/Chromium. On WSL, automatically adds --no-sandbox flag.
Navigate
./tools/nav.js <https://example.com>
./tools/nav.js <https://example.com> --new
Navigate current tab or open new tab.
Evaluate JavaScript
./tools/eval.js 'document.title'
./tools/eval.js 'document.querySelectorAll("a").length'
./tools/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
./tools/screenshot.js
Screenshot current viewport, returns temp file path
Pick Elements
./tools/pick.js "Click the submit button"
Interactive element picker. Click to select, Cmd/Ctrl+Click for multi-select, Enter to finish.