PDF Utilities Skill

Overview

This skill provides comprehensive PDF processing capabilities including reading PDFs with multiple library backends (tabula, camelot, PyPDF2), extracting tables to DataFrames, editing/extracting page ranges, handling fillable forms, and managing PDF comments. All operations are driven by YAML configuration.

Key Components

ReadPDF Class (read_pdf.py)

Multi-backend PDF reading with table extraction:

• read_pdf(cfg, file_index) - Route to appropriate backend based on config
• from_pdf_tabula(cfg, file_index) - Extract tables using tabula-py
• from_pdf_camelot(cfg, file_index) - Extract tables using camelot
• from_pdf_PyPDF2(cfg, file_index) - Read PDF pages using PyPDF2