Skip to content
GitHub

pdf - PDF Toolkit Skill

pdf

PDF Toolkit Skill

Verified Popular Featured Anthropic Document
GitHub

Description

Complete toolkit for PDF reading/writing, text and table extraction, merging/splitting, form filling, and content editing

Use Cases

  • Extract data and tables from PDF reports
  • Batch fill PDF forms
  • Merge multiple PDF files
  • Split large PDF documents
  • Process legal documents and contracts

Core Capabilities

  • Text Extraction: Extract searchable text from PDFs
  • Table Extraction: Identify and extract table data to structured formats
  • Form Processing: Fill and read PDF form fields
  • Document Merging: Combine multiple PDFs into one file
  • Page Operations: Extract, delete, or reorder pages

Example

Please extract from this financial report PDF:
1. All data tables, converted to CSV format
2. Summary of key financial metrics
3. Data points from charts (if identifiable)

Notes

  • Scanned PDFs may require OCR processing
  • Encrypted PDFs need to be decrypted first
  • Table extraction accuracy depends on PDF structure

Applicable Roles

Developer Data Analyst Finance HR Legal Executive

Tags

pdfextractionformsmerge