chainlesschain Computer Use Skill
Desktop-level automation with screenshot, mouse, keyboard, and Vision AI.
Usage
/computer-use <action> [args]
Actions
| Action | Description | Example |
|---|---|---|
screenshot |
Capture full screen | /computer-use screenshot |
click |
Click at pixel coordinates | /computer-use click 500 300 |
type |
Type text via keyboard | /computer-use type "Hello World" |
visual-click |
Click element found by Vision AI | /computer-use visual-click "Settings button" |
analyze |
Analyze screenshot with Vision AI | /computer-use analyze "What's on screen?" |
key |
Press keyboard shortcut | /computer-use key ctrl+c |
move |
Move mouse to coordinates | /computer-use move 400 200 |
Vision AI Integration
The skill can use Vision AI (Claude/GPT-4V/LLaVA) to:
- Find UI elements by visual description
- Analyze screen content
- Identify clickable targets without knowing coordinates