Takes PDFs and converts each page to an image, then runs Claude's vision analysis to extract everything including charts, diagrams, and complex layouts. You get a proper Markdown output with tables, graph descriptions, and visual element summaries. The setup needs pdf2image and poppler-utils, and it's clearly built for presentation decks and technical documents where figures matter more than raw text extraction. Processing is slow compared to text-only PDF readers, but that's the tradeoff when you need to understand what's actually in those charts. The workflow is manual but straightforward: convert with the Python script, read each image with Claude's vision, then consolidate into Markdown. Best for the 20-page deck with infographics, not the 200-page text manual.
npx skills add https://github.com/childbamboo/claude-code-marketplace-sample --skill pdf-vision-reader