This is a wrapper around MinerU's open API for extracting text from PDFs, images, and Office files into Markdown or other formats. It has two modes: flash-extract for quick jobs under 10MB with no auth required, and extract for bigger files that need full-fidelity table/formula/image preservation. The skill handles OCR in 80+ languages and works with URLs or local files. The instructions are thorough about a specific gotcha: when using page ranges with directory output, you need to specify explicit filenames or extracts will overwrite each other. If you're doing document Q&A or conversion work, this gives you a clean pipeline from binary blob to structured text without managing API keys yourself for basic use.
npx skills add https://github.com/tanis90/pdf-converter-mineru --skill pdf-converter