CV Plugin Help

Desktop GUI control automates applications by simulating mouse clicks and keyboard input. This Skill captures screenshots and extracts data from visual elements, enabling interaction with software that lacks official APIs.

Yes, you can extract text from screen regions using OCR. The Skill provides optical character recognition to capture text with bounding boxes from specific windows or custom areas of your desktop.

To capture a screenshot of a specific window, use the window management features to list and identify your target. You can then capture the entire desktop, specific windows, or custom regions programmatically.

Reading the UI accessibility tree provides deeper application understanding for desktop automation. This Skill analyzes the GUI structure directly, complementing screen capture and input simulation for robust visual task automation.

Yes, desktop automation includes window management features. You can programmatically list all open windows, focus on specific applications, and move windows to automate your desktop environment layout.

Computer vision enables automation by interacting with visual elements directly, bypassing the need for underlying application APIs. It uses screen capture and OCR to retrieve data from visual elements that traditional scripting cannot access.