Convert PDFs to Markdown using Mistral OCR with local caching.
npx skills add https://github.com/dzackgarza/ai --skill reading-pdfs
Please help me install this Agent Skill. Skill: reading-pdfs Source: https://github.com/dzackgarza/ai/tree/main/opencode/skills/reading-pdfs Command: npx skills add https://github.com/dzackgarza/ai --skill reading-pdfs
Use when reading a PDF — converts to markdown via Mistral OCR with local caching.
Provide the path to a PDF and run the OCR workflow to produce a cached Markdown version in the local pdfs cache.
High-intent search queries and answers about installing and using this skill.
To convert a PDF to Markdown offline, this Skill applies Mistral OCR to the document and caches the extracted text locally. It checks the ~/pdfs directory for existing Markdown to avoid re-processing, downloading missing PDFs like arXiv papers automatically before returning the content.
Running Mistral OCR for PDF conversion requires a Python environment with the mistralai library installed. You must also set the MISTRAL_API_KEY environment variable to authenticate the OCR requests and successfully generate the Markdown output.
Yes, you can avoid re-processing an arXiv paper because the Skill stores original PDFs and generated Markdown in a local cache under ~/pdfs. It checks this cache before applying OCR, returning the existing Markdown immediately if found.
Yes, this PDF to Markdown conversion works for academic papers. The workflow explicitly supports downloading and processing arXiv papers, applying Mistral OCR to extract structured Markdown content from the PDFs for research purposes.
After OCR extraction, the original PDF file is stored alongside the generated Markdown content in the local cache directory at ~/pdfs. This ensures both the source document and the extracted Markdown remain accessible for future offline reference.
smallnestConvert PDFs, Word, Excel, HTML, and images with OCR into Markdown.
PancrePal-xiaoyibaoExtract text from local PDF files into structured Markdown format.
tluisguereroItesmSummarize local PDF, Word, Excel, TXT, and Markdown documents.
lordmacuConvert images and scanned PDFs into plain text using Tesseract OCR.
