一个功能强大的屏幕浏览、OCR识别和屏幕分析技能包，专为AI助手设计

This package appears to do what it says: take screenshots and run OCR/analysis. Before installing or running it, consider the following: - Screenshots capture all visible data on your screen (including passwords, 2FA codes, private messages). Only run these scripts in a trusted environment and be mindful of privacy of captured images and output files. - The Windows installer script (scripts/install_tesseract.py) downloads a .exe from the network and executes it with silent install flags. Verify the download URLs and, if possible, the file checksum/signature before running. Prefer to install Tesseract manually from the official project or your distribution's package manager if you are uncomfortable with automated installers. - Inspect scripts/install_tesseract.py and scripts/setup.py (and any other scripts) before running them to ensure there is no unwanted network behavior or commands. Consider running the package in a disposable VM/container first. - The package does not request credentials, but it will write files (images, text, JSON) to the working directory. Review where output is stored and ensure sensitive captures are handled securely. - If you plan to allow an agent to invoke this skill autonomously, restrict autonomous execution or monitor runs; automated screenshotting has high privacy impact. Disable or limit autonomous invocation if you cannot review each action. - Good checks to perform: run scripts/dependency_check.py to see what is missing, run the examples in a safe environment, and prefer manual installation of Tesseract (brew/apt or official Windows installer you obtained yourself).