Drive the desktop — macOS, or the Windows desktop through WSL — when a task needs a native app, dialog, menu bar, file picker or anything the terminal and browser tools cannot reach. Screenshot first, then click and type by coordinates read from that image.
This skill hasn't been reviewed yet
d98cc21
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.