mirror of
https://github.com/hanzoskill/screen-monitor.git
synced 2026-10-30 21:01:25 +00:00
main
Screen-Monitor Skill
Browser-based screen sharing with vision analysis. Works with any multimodal LLM.
Installation
skills install screen-monitor
Or manual:
git clone https://github.com/emasoudy/bot-skills.git
cp -r bot-skills/screen-monitor ~/.bot/skills/
Usage
- Get share link:
screen_share_link - Open link in browser (e.g.,
http://192.168.1.100:18795/screen-share) - Click "Start Sharing"
- Ask questions about your screen
Requirements
- Multimodal LLM (Gemini, Claude, Qwen3-VL, etc.)
- Modern browser with WebRTC
- Optional: ImageMagick for OS fallback
License
MIT - See LICENSE file
Languages
HTML
61.9%
JavaScript
24.3%
Shell
13.8%