Language:JapaneseEnglish

pdf Claude Code Skill

Author
Anthropic
Topics
Documents & Content Creation
License
Proprietary (see LICENSE.txt)
First cataloged
2026-07-09 (UTC)
Explanation last updated
2026-08-21 (UTC)
Source (GitHub) last updated
2026-02-06 (UTC) (202 days ago)

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

This skill equips the assistant to work with PDF files across a wide range of tasks. According to the SKILL.md source, it supports reading and extracting text or tables, merging and splitting PDFs, rotating pages, adding watermarks, creating new PDF documents, filling forms, encrypting or decrypting files, extracting embedded images, and running OCR on scanned pages to make them searchable. It relies on Python libraries such as pypdf, pdfplumber, and reportlab, along with command-line tools like pdftotext, qpdf, and pdftk. Separate reference files, FORMS.md and REFERENCE.md, are pointed to for form-filling steps and more advanced usage. The skill activates whenever a user references a .pdf file or asks for one to be produced.

What you can do with pdf

  • Extract text and tables from PDF documents
  • Merge multiple PDFs together or split one into separate files
  • Rotate pages and add watermarks
  • Create new PDF documents from scratch
  • Fill in PDF forms (following FORMS.md)
  • Encrypt or decrypt PDF files with passwords
  • Extract embedded images from a PDF
  • Run OCR on scanned PDFs to make the text searchable

Sources

Back to list