Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables/formulas from PDFs (including scanned and photographed documents), OCR, combining or merging multiple PDFs, splitting, rotating, watermarking, creating new PDFs, filling PDF forms, encrypting/decrypting, and extracting images. Routes between pypdf (fast born-digital text), pdfplumber (tables), opendataloader-pdf (born-digital complex layout with optional Docling hybrid), and dolphin v2 (vision-LM OCR, last resort for scanned/photographed/formula-heavy docs). If the user mentions a .pdf file or asks to produce one, use this skill.
2026-07-21