Extract text from PDFs and save clean Markdown beside the source file.
npx skills add https://github.com/lttr/dotfiles --skill pdf-to-markdown
Please help me install this Agent Skill. Skill: pdf-to-markdown Source: https://github.com/lttr/dotfiles/tree/main/claude/skills/pdf-to-markdown Command: npx skills add https://github.com/lttr/dotfiles --skill pdf-to-markdown
Extract text from PDF documents and convert it into clean Markdown, including scanned or image-based PDFs, with output saved alongside the original file.
Use the skill on a PDF to generate a Markdown file in the same directory. For example, on document.pdf, the output will be document.md.
High-intent search queries and answers about installing and using this skill.
Extract text from PDF documents and convert it to clean Markdown by running the Skill on your PDF file. It handles both text-based and scanned PDFs using OCR, outputting a Markdown file with the same base name saved in the same directory as your source PDF.
Yes, this Skill handles scanned and image-based PDFs through OCR-friendly transcription. It extracts text from visually encoded pages and formats the output as structured Markdown with proper headings and lists.
Large documents are processed with chunked extraction and parallel processing to handle page-by-page transcription efficiently. The output Markdown file is saved alongside your source PDF for easy access.
Converted Markdown includes structured formatting with headings, lists, and readable text layout. The output file uses the same base filename as the source PDF with a .md extension, saved in the same directory.
No special preparation is required. The Skill works directly on PDF files whether they are text-based, scanned, or image-based documents. Simply run it on your PDF and the Markdown output is generated automatically.
The Skill includes error checking throughout extraction and processing. It validates the transcription quality and handles OCR challenges, though complex layouts or heavily degraded scans may affect extraction accuracy.
SignmanalExtract text, tables, and structured content from PDFs and scanned documents.
UniquecreteConvert PDF documents into structured Markdown with page chunking and optional image extraction.
phuetzExtract text, convert formats, and manipulate pages in PDF documents.
hyperbolic-cConvert PDFs, Word, PPTX, Excel, HTML, EPUB, and images to Markdown.
