Web Browser Automation

•
1
•

Enables Claude to interact with live web pages through automated browser control, navigation, and element interaction.

The Web Browser skill empowers Claude to perform real-time web exploration and interaction by remote controlling Google Chrome or Chromium via the Chrome DevTools Protocol (CDP). It provides a robust suite of tools for navigating URLs, executing custom JavaScript within the page context, capturing screenshots, and identifying specific DOM elements. This skill is essential for developers who need Claude to access live documentation, test web interfaces, or automate complex web-based workflows directly from their coding environment.

Características Principales

01Full website navigation and multi-tab management capabilities
021 GitHub stars
03Remote control of Chrome/Chromium via Chrome DevTools Protocol (CDP)
04Interactive element picker for precise selection and interaction with page components
05Custom JavaScript execution for deep page interaction and data extraction
06High-resolution viewport screenshot capture for visual verification

Casos de Uso

01Automated end-to-end testing and visual debugging of web applications
02Extracting real-time data and documentation from websites for coding context
03Performing web-based tasks like form submission and workflow automation
name description isolatedContext license
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.
true
Stolen from Armin who stole it from someone else

Web Browser Skill

Minimal CDP tools for collaborative site exploration.

Start Chrome

```bash ./tools/start.js # Fresh profile ./tools/start.js --profile # Copy your profile (cookies, logins) ```

Start Chrome on :9222 with remote debugging.

Navigate

```bash ./tools/nav.js https://example.com ./tools/nav.js https://example.com --new ```

Navigate current tab or open new tab.

Evaluate JavaScript

```bash ./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

```bash ./tools/screenshot.js ```

Screenshot current viewport, returns temp file path

Pick Elements

```bash ./tools/pick.js "Click the submit button" ```

Interactive element picker. Click to select, Cmd/Ctrl+Click for multi-select, Enter to finish.