LaunchKit · 2026
Back to Skills

browser-use

Use Browser Use cloud API to spin up cloud browsers for Clawdbot.

65
26.4k downloads
by @shawnpana

Setup & Installation

openclaw skills install @shawnpana/browser-use

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install browser-use

Version History

v1.0.2Feb 19, 2026 - Version note by skill developer:

- Documentation reworked and simplified for clarity and easier reference. - Audience broadened: Skill now addresses general browser automation, not just sandboxed/cloud use. - Install modes, tunnel setup, and environment variable explanations are removed for a more concise guide. - New dedicated sections for browser modes, session management, essential commands, and Python execution. - Updated and better-organized CLI command reference. - Usage examples and options for real/Chromium/cloud browsers are clarified with practical guidance. - For full advanced setup details, directs users to the official README.

What This Skill Does

browser-use is a CLI tool for automating web browser interactions from the command line. It maintains persistent browser sessions across commands, enabling multi-step workflows without reinitializing the browser each time. Supports headless Chromium, real Chrome with existing login profiles, and cloud-hosted remote browsers with AI agent capabilities.

Sessions stay open between commands, so complex workflows build incrementally without re-navigating from scratch each time.

When to use it

  • Filling out multi-step web forms automatically
  • Scraping product prices or data from websites
  • Saving screenshots of pages for documentation or monitoring
  • Running parallel research tasks across multiple sites in cloud sessions
  • Testing web app interactions without a dedicated test framework

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: go to example.com, get the main heading text, and save a screenshot

AGENT
  1. 1Opens the page with `browser-use open https://example.com`
  2. 2Runs `browser-use state` to confirm the page loaded and list element indices
  3. 3Runs `browser-use get html --selector h1` to extract the heading
  4. 4Saves a screenshot with `browser-use screenshot page.png`
OUTPUT

Heading text printed to terminal and screenshot saved as page.png