mac-use - Control macOS GUI applications visually
Take screenshots, click, scroll, type in macOS GUI apps via OCR
Tags
Updated: 2026-05-28Capabilities
Typical Inputs
Typical Outputs
What this skill does
- list windows
- capture screenshot
- detect text
- click element
- click coordinates
- scroll window
- type text
- press key
Inputs
- app name
- window ID
- element number
- canvas coordinates
- text input
- key combination
Outputs
- window list
- screenshot image
- element map
- clicked element details
Requirements
- macOS
- Apple Vision framework
- Python 3
- screencapture utility
