A straightforward OCR wrapper around PaddleOCR's API that pulls text from images, PDFs, and screenshots. Returns structured JSON with line-level text and optional bounding boxes. The setup is honest: you need to grab API credentials from paddleocr.com first, but after that it's just a uv run command with a URL or file path. Strong on CJK and handwritten text according to the docs. One thing to know: this is pure text extraction, not document parsing. If you need table structure or reading order from complex layouts, look elsewhere. For "get me the text from this screenshot" tasks, it does the job without ceremony.
npx skills add https://github.com/aidenwu0209/paddleocr-skills --skill paddleocr-text-recognition