pdf

name	pdf
description	Extract and analyze text from PDF files, read PDF content, process PDF documents. Use when user wants to read, analyze, or extract information from PDF files.

PDF Processing Skill

This skill helps you work with PDF files by extracting and analyzing their content, with built-in support for handling large files.

Capabilities

• Extract text content from PDF files
• Handle large PDFs with automatic pagination and character limits
• Read specific page ranges
• Show PDF structure summary without full content
• Analyze PDF structure and metadata

When to Use

Use this skill when:

• User asks to read a PDF file
• User wants to extract text from a PDF
• User needs to analyze PDF content
• User mentions working with .pdf files

How It Works

This skill uses Python with the PyPDF2 library to:

1. Open and read PDF files
2. Extract text with automatic limits to prevent overload
3. Support pagination for large documents
4. Provide structured output of the PDF content

Default Limits

• Maximum pages per request: 20 pages
• Maximum characters: 50,000 characters

These limits prevent "PDF too large" errors while still providing useful content.

Usage Examples

# Read PDF (first 20 pages, max 50k chars)
python pdf_reader.py document.pdf

# Show only PDF structure and page overview (for large PDFs)
python pdf_reader.py document.pdf --summary

# Read specific page range
python pdf_reader.py document.pdf --start 5 --end 10

# Read with higher character limit
python pdf_reader.py document.pdf --max-chars 100000

Handling Large PDFs

For large PDFs, use this workflow:

1. First run with --summary to see the PDF structure
2. Then read specific sections using --start and --end

Setup

Make sure you have Python and PyPDF2 installed:

pip install PyPDF2