browser-use

SKILL.md

Fast, persistent browser automation with session continuity across sequential agent commands.

Supports three browser modes: headless Chromium, real Chrome with profile support, and cloud-hosted remote browsers with proxy configuration

Includes 20+ command categories covering navigation, page inspection, interactions, data extraction, cookie management, JavaScript execution, and wait conditions

Offers cloud session management, local server tunneling via Cloudflare, and parallel subagent execution through remote sessions with task monitoring

Built-in Python integration for setting variables, accessing the browser object, and running scripts within the automation context

Browser Use

Direct browser control via CDP. For task-specific edits, use agent-workspace/agent_helpers.py. For setup, install, or connection problems, read https://github.com/browser-use/browser-harness/blob/main/install.md.

Domain skills are off by default. Set BH_DOMAIN_SKILLS=1 to enable them; see the bottom section.

If BH_DOMAIN_SKILLS=1 and the task is site-specific, read every file in the matching $BH_AGENT_WORKSPACE/domain-skills/<site>/ directory before inventing an approach.

Usage

browser-use <<'PY'
print(page_info())
PY