web-infra-dev/midscene-skills/desktop-computer-automation
Vision-driven desktop automation using Midscene. Control your desktop (macOS, Windows, Linux) with natural language commands. Operates entirely from screenshots — no DOM or accessibility labels required. Can interact with all visible elements on screen regardless of technology stack. Triggers: open app, press key, desktop, computer, click on screen, type text, screenshot desktop, launch application, switch window, desktop automation, control computer, mouse click, keyboard shortcut, screen capture, find on screen, read screen, verify window, close app, minimize window, maximize window Powered by Midscene.js (https://midscenejs.com)
Risk Score
0
out of 100
Popularity
6
Stars
0
Forks
Feb 12, 2026
Updated
Findings by Severity (Latest Scan)
CodeThreat AppSec
Full SAST + SCA agentic security analysis for MCP servers and Skills.