Converts PDFs to Markdown by checking if they have native text or need OCR, though OCR isn't implemented yet. Runs with just Node.js using npx to pull @opendocsg/pdf2md on first use, no installation required. Works well for text-based PDFs like documentation or reports, handles basic tables, but complex multi-column layouts won't survive perfectly. The auto-detect mode is smart enough to tell you when a PDF is scanned and can't be processed. Outputs clean JSON with page counts and paths. If you're building documentation pipelines or need to extract content from standard PDFs without dealing with system dependencies, this does the job without fuss.
npx skills add https://github.com/andreadellacorte/groove --skill pdf-to-markdown