domains / families / documents / pdf
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. PDF manipulation toolkit. Extract text/tables, create PDFs, merge/split, fill forms, for programmatic document processing and analysis.
The anthropics, foryourhealth111-pixel, and zLanqing copies are near-identical reproductions of the same upstream PDF processing guide (pypdf, pdfplumber, reportlab, qpdf, pdftotext). The openai copy is a distinct, shorter skill that adds a visual-review workflow (render pages with pdftoppm, inspect PNGs), dependency installation via uv, temp/output directory conventions, and quality expectations (ASCII hyphens, no placeholder tokens) that the other copies lack. The foryourhealth111-pixel copy adds a scientific-schematics generation step that the others lack. Because the openai and foryourhealth111-pixel copies each contain material steps or constraints the others do not, crowning one would hide real alternatives.