What command-line tools are integrated into this skill?

It covers popular CLI utilities like qpdf, pdftotext, and pdfimages for high-performance document operations outside of a Python environment.

Can I use this skill to extract tables from PDFs?

Yes, it includes specific patterns using pdfplumber and Pandas to accurately extract and convert PDF tables into structured data formats.

Does it support OCR for scanned documents?

Yes, the toolkit provides implementations using pytesseract and pdf2image to perform optical character recognition on scanned PDF pages.

Which Python libraries does this skill support?

It provides comprehensive guidance and code examples for pypdf, pdfplumber, reportlab, and pytesseract for various PDF tasks.

Can Claude help me fill out PDF forms with this skill?

Absolutely, the skill includes specialized instructions and references for programmatic form filling using libraries like pdf-lib or pypdf.

PDF Processing Toolkit

Name: PDF Processing Toolkit
Author: prof-ramos

byprof-ramos

•

Developer Tools

Provides comprehensive PDF manipulation capabilities including text/table extraction, document generation, and form handling for automated workflows.

The PDF Processing Toolkit is a specialized Claude Code skill designed to streamline document workflows through programmatic manipulation. It integrates powerful Python libraries and command-line utilities to enable seamless text and table extraction, document merging and splitting, and automated PDF generation from scratch. Whether you are building automated reports, processing bulk documents for data analysis, or handling complex form filling, this skill provides the patterns and best practices needed to implement robust PDF solutions quickly and efficiently.

Key Features

01Merge, split, rotate, and manage document metadata

02Secure documents with password protection and watermarking

03Extract text and structured tables with layout preservation

04Implement OCR for scanned documents and extract embedded images

05Programmatically generate complex PDFs using reportlab and Platypus

061 GitHub stars

Use Cases

01Generating dynamic business reports and invoices directly from application data

02Batch processing and merging multiple documents into unified archives for compliance

03Automating the extraction of financial data from PDF tables into Excel or Pandas DataFrames

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add prof-ramos/.codex pdf

For use in Claude.ai and ChatGPT

Download Skill