#pdf#documents#extraction#office#automation

PDF

Independent PiSkill directory guide. The original skill remains hosted by Anthropic Skills.

What is PDF?

Gives agents workflows for inspecting, extracting, creating, merging, splitting, rotating, watermarking, and otherwise manipulating PDF documents.

What does PDF do?

PDF is an Anthropic skill for inspecting, extracting, creating and manipulating PDF documents. It covers common document operations such as text and table extraction, merging, splitting, rotation, watermarking and generating new PDFs, making it useful for workflows where the final artifact must remain a PDF rather than plain text.

Who is PDF best for?

  • Users processing existing PDF documents
  • Teams combining or reorganizing PDF files
  • Document workflows that need extraction plus transformation
  • Agents producing final PDF deliverables

Common use cases

  • Extract text or tables from a PDF
  • Merge several PDF documents into one file
  • Split or rotate selected pages
  • Create a PDF or apply a watermark to an existing document

How does PDF work?

The skill selects tools based on the specific PDF task rather than using one conversion path for everything. It can inspect the document, extract structured content, transform pages or create a new file, with validation appropriate to the operation being performed.

Key benefits

  • Covers both PDF analysis and file manipulation
  • Useful for common office-document workflows
  • Supports page-level operations as well as extraction
  • Keeps the final deliverable in a standard portable format

Things to know

  • Scanned PDFs may require separate OCR or image-based handling
  • Highly complex forms or interactive PDFs can need specialized tools
  • Extraction quality depends on how the original PDF was produced

Compatible tools

Claude CodeClaude.aiOpenAI Codex

Frequently asked questions

What operations does the PDF skill support?
It supports PDF inspection, extraction, creation, merging, splitting, rotation, watermarking and other common document transformations.
Can it work with scanned PDFs?
The core workflow handles PDFs, but image-only scanned documents may require OCR or additional image-based processing.
← Back to Skills Directory