Standardmäßig ist der Prompt ausgewählt, der zuerst die Quelle prüft. Sie können zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.
Quelldateien prüfen
Lesen Sie SKILL.md und alle von SkillsMP angezeigten Begleitdateien, bevor Sie sich für eine Installation entscheiden.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.
You are an expert in browser automation using browser-use, a powerful CLI tool designed for persistent, multi-session browser automation. When the user asks you to automate complex browser workflows, manage sessions, or perform long-running automation tasks, follow these detailed instructions.
Core Principles
Persistent sessions -- Maintain browser state across multiple automation runs.
Multi-session support -- Run multiple isolated browser sessions in parallel.
Flexible browser modes -- Support for Chromium (headless), Real (headed), and Remote browser instances.
Cookie management -- Export, import, and manage cookies for authentication persistence.
JavaScript execution -- Execute custom JavaScript in page context for advanced automation.
Installation
# Install via npm
npm install -g browser-use
# Or use with npx
npx browser-use --version
# Install with Python
pip install browser-use
# Verify installation
browser-use --help
Browser Modes
Chromium Mode (Default Headless)
# Launch Chromium in headless mode
browser-use start --mode chromium --headless
# With custom user data directory
browser-use start --mode chromium --user-data-dir ./browser-data
# With custom viewport
browser-use start --mode chromium --viewport 1920x1080
Real Browser Mode (Headed)
# Launch visible Chrome browser
browser-use start --mode real --browser chrome
# Launch Firefox
browser-use start --mode real --browser firefox
# Launch with specific profile
browser-use start --mode real --browser chrome --profile "Profile 1"
# Run multiple sessions in parallel
browser-use parallel --sessions "session-1,session-2,session-3" \
--command"navigate --url https://example.com"# Run different commands per session
browser-use parallel \
--session session-1 --command"navigate --url https://site1.com" \
--session session-2 --command"navigate --url https://site2.com" \
--session session-3 --command"navigate --url https://site3.com"
Cookie Management
Export and Import Cookies
# Export cookies from session
browser-use cookies export --session "user-session-1" --output cookies.json
# Export specific domain cookies
browser-use cookies export --session "user-session-1" --domain "example.com" --output example-cookies.json
# Import cookies into session
browser-use cookies import --session "user-session-1" --input cookies.json
# Import cookies for specific domain
browser-use cookies import --session "user-session-1" --input auth-cookies.json --domain "app.example.com"# Clear all cookies
browser-use cookies clear --session "user-session-1"# Clear cookies for specific domain
browser-use cookies clear --session "user-session-1" --domain "example.com"
# Navigate with custom headers
browser-use navigate --url "https://api.example.com" \
--headers '{"Authorization": "Bearer token123", "X-Custom": "value"}'# Navigate with POST data
browser-use navigate --url "https://example.com/search" \
--method POST \
--data '{"query": "automation", "filters": ["category:tools"]}'# Navigate with referer
browser-use navigate --url "https://example.com/protected" \
--referer "https://example.com/home"# Navigate and wait for specific event
browser-use navigate --url "https://example.com" \
--wait-for-event "load"
Page Interaction Commands
# Scroll to element
browser-use scroll --selector ".footer" --behavior smooth
# Scroll by pixels
browser-use scroll --delta "0,500"# Scroll to top/bottom
browser-use scroll --position top
browser-use scroll --position bottom
# Hover over element
browser-use hover --selector ".dropdown-trigger"# Focus element
browser-use focus --selector "input#search"# Select dropdown option
browser-use select --selector "select#country" --value "US"# Upload file
browser-use upload --selector "input[type='file']" --file ./document.pdf
# Download file
browser-use download --url "https://example.com/file.pdf" --output ./downloaded.pdf
Tab Management
Multi-Tab Operations
# Open new tab
browser-use tab new --url "https://example.com"# List all tabs
browser-use tab list
# Switch to tab by index
browser-use tab switch --index 0
# Switch to tab by URL pattern
browser-use tab switch --url-pattern "example.com"# Close tab
browser-use tab close --index 1
# Close all tabs except current
browser-use tab close --others
# Duplicate tab
browser-use tab duplicate --index 0
This skill enables powerful, persistent browser automation with session management, making it ideal for long-running workflows, authenticated applications, and complex multi-step automations that AI agents need to orchestrate.
