What problem does it solve?
This Skill provides a lightweight CLI to control a Windows machine remotely via the WinUse HTTP API, eliminating manual GUI interaction and enabling agents to automate desktop tasks over a LAN.
Core Features & Use Cases
- Window Management: list, focus, minimize, maximize, restore, and close windows by handle or fuzzy title.
- Input Automation: send key combinations, type text, paste clipboard contents, and perform mouse moves and clicks.
- Screenshots & Integration: request full-desktop or per-window screenshots and retrieve downloadable URLs for vision models or archival workflows.
- Use Case: Automate a browser workflow by focusing a window, sending keyboard shortcuts to open and navigate tabs, typing search queries, and capturing a screenshot for analysis.
Quick Start
Ask the agent to focus the window titled "kimi", type Hello World, press enter, and take a screenshot.