browser-use - Automate browser interactions with browser-use
Automates browser navigation, page interaction, form filling, screenshots, and web data extraction.
Tags
Updated: 2026-10-16Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Navigate web pages
- Inspect page elements
- Click page elements
- Fill form fields
- Select dropdown options
- Capture screenshots
- Extract page data
- Execute JavaScript
- Manage browser sessions
- Run browser tasks
Inputs
- Target URLs
- Interaction text
- Element indices
- CSS selectors
- Browser profiles
- Cookie files
- Task instructions
- LLM model names
Outputs
- Browser state messages
- Page text
- HTML content
- Screenshots
- Extracted values
- Session statuses
- Task statuses
- Exported cookie files
Requirements
- Installed browser-use CLI
- Configured browser-use CLI
- Bash access
- Supported browser environment
- LLM model for agent tasks