pdf Claude Code Skill
Claude Code SkillClaude CodeDocuments & Content CreationThe explanation below is AI-generated. Please verify it against the sources.
This skill equips Claude to handle PDF file operations when a user requests work on PDF documents. It draws on Python libraries such as pypdf, pdfplumber, and reportlab, plus command-line utilities like pdftotext, qpdf, pdftk, and pdfimages, along with pytesseract for optical character recognition. Supported operations include reading and extracting text, tables, metadata, and images; merging, splitting, and rotating pages; creating new PDF documents; adding watermarks; encrypting or decrypting files; and making scanned documents searchable through OCR. The skill also references separate guides for filling PDF forms and for more advanced or JavaScript-based techniques. It activates whenever a user mentions a .pdf file or requests PDF-related output.
What you can do with pdf
- Read a PDF and pull out its text, tables, or metadata
- Merge several PDFs into a single file or split one PDF into separate pages
- Rotate pages and add watermarks to existing documents
- Build new PDF files from scratch, including multi-page reports
- Fill in PDF form fields using the referenced forms guide
- Encrypt a PDF with a password or remove existing password protection
- Pull embedded images out of a PDF
- Run OCR on scanned PDF pages so the text becomes searchable