Language: 日本語English

pdf Skill

Author
Anthropic
Topics
Documents & Content Creation
License
Proprietary. LICENSE.txt has complete terms
First seen
2026-07-09
Last confirmed
2026-07-13
Explanation last updated
2026-07-12

The explanation below is AI-generated. Please verify it against the sources.

This item is a Claude "skill" (SKILL.md) that provides a guide for handling PDF files using Python libraries and command-line tools. According to the source, it is meant to be used for reading/extracting text or tables, merging or splitting PDFs, rotating pages, adding watermarks, creating new PDFs, filling forms, encrypting/decrypting files, extracting images, and running OCR on scanned PDFs. It gives concrete code examples using pypdf, pdfplumber, and reportlab, as well as command-line examples with pdftotext, qpdf, and pdftk. The guide notes that more advanced features, JavaScript libraries, and form-filling instructions are covered in separate files (REFERENCE.md and FORMS.md), but the content of those files is not included in this source.

What you can do with pdf

  • Extract text and tables from PDFs (pdfplumber, pypdf)
  • Merge multiple PDFs into a single file (pypdf, qpdf, pdftk)
  • Split a PDF into separate page files (pypdf, qpdf, pdftk)
  • Rotate PDF pages (pypdf, qpdf, pdftk)
  • Create new PDFs, including multi-page documents (reportlab)
  • Add watermarks to existing PDFs (pypdf)
  • Fill out PDF forms (per FORMS.md, using pdf-lib or pypdf)
  • Encrypt/decrypt PDFs and set passwords (pypdf, qpdf)
  • Extract embedded images from a PDF (pdfimages)
  • Run OCR on scanned PDFs to obtain text (pytesseract, pdf2image)
  • Read PDF metadata such as title, author, and creator (pypdf)

Sources

Original description (English)

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.

History of pdf

Back to list