What problem does it solve? Reading PDFs through an AI's built-in file reader consumes large amounts of context tokens and often loses tables, headings, and layout structure. This Skill converts PDFs into clean, LLM-friendly Markdown offline via a script, so large documents are processed without consuming tokens and with layout preserved. ## Core Features & Use Cases - Layout-preserving conversion: Uses pymupdf4llm to keep tables, headings, multi-column order, and image links intact in the Markdown output. - Selective processing: Convert specific page ranges (e.g., 1-5 or 1,3,5-10) and optionally extract embedded images as PNG files into a companion folder. - Scan detection: The --info mode reports page count, size, and text density, warning when a PDF is image-based and needs OCR instead. - Use Case: You receive a 100-page research report PDF. Run the converter to get a structured Markdown file, preview the first lines, then file it into your knowledge base or feed it to a wiki-ingest workflow. ## Quick Start Ask the AI to convert a specific PDF file to Markdown, optionally mentioning a page range or that you want the images extracted too.
