A practical PDF toolkit for agents: extract text and tables from PDFs, perform OCR on scanned documents, merge/split pages, rotate and watermark files, extract images, protect or decrypt PDFs, and generate new PDFs programmatically. The SKILL includes code examples for pypdf, pdfplumber, reportlab, and command-line tools like qpdf and pdftotext.
Trigger this skill whenever a user mentions a .pdf file or asks to produce, modify, extract, or analyse PDF content — e.g., extract tables into CSV/Excel, OCR scanned reports, split a large PDF, or add watermarks and encryption. It's suitable for document processing automation and data extraction tasks.
Works with agents capable of running Python or shell helpers; useful for automation-focused agents and those that can call local binaries (pdfpoppler, qpdf).
Comprehensive PDF processing skill covering text extraction, merging, splitting, OCR, form filling, watermarking, and encryption. 8 scripts are well-structured with proper validation and error handling, but all failed at runtime due to missing Python dependencies (pypdf, pdfplumber, pdf2image, Pillow). The SKILL.md is thorough with code examples and a quick reference table. No security concerns — no network calls, no credential handling, no destructive operations.
pypdfpdfplumberpdf2imagePillowpytesseractWell-crafted utility skill with good documentation. Main limitation is dependency management — scripts crash immediately without the required Python packages. License listed as 'Proprietary' in frontmatter. No reference files (REFERENCE.md, FORMS.md) were bundled, only referenced in SKILL.md.