screen-vision
Reads desktop UI controls and coordinates from accessibility data, with optional verified clicks.
Reads desktop UI controls and coordinates from accessibility data, with optional verified clicks.
screen-vision treats the operating system’s accessibility tree as the primary source for desktop UI names, states, types, and rectangles, using OCR or icon vision only to fill gaps. Its CLI probes the host, captures a screenshot plus structured elements, and can click by element ID with dry-run as the default. It targets native, Win32, WinUI, Electron, game, or remote-desktop windows—not browser pages, which should use Playwright.
Resource types
Use cases
Platforms
Runtime
Match Chinese-language requests to suitable installable agent skills.
Build sourced thinking profiles of public figures and apply them to real decisions.
Capabilities
Public GitHub facts last synced Jul 10, 2026.
Build daily or weekly schedules around sleep, chronotype, tasks, and fixed commitments.
Calculate and confirm overtime submissions for YSS employees