Can this skill handle scanned PDF files?

Yes, the toolkit includes implementation patterns for using pytesseract and pdf2image to perform OCR and extract text from scanned documents.

Can I use this to fill out PDF forms programmatically?

Yes, it includes guidance for filling out PDF forms and refers to specialized documentation for tools like pdf-lib.

Which Python libraries are supported for PDF creation?

The skill provides detailed guides for using reportlab and its Platypus engine to create complex, multi-page PDFs with custom styling.

Does it support command-line PDF tools?

Absolutely. It covers essential CLI tools such as qpdf for merging/splitting, pdftotext for extraction, and pdftk for page rotation.

Is it possible to add security to documents?

Yes, the toolkit provides code snippets for password-protecting documents with user and owner encryption using the pypdf library.

PDF Processing Toolkit

Name: PDF Processing Toolkit
Author: horuz-ai

byhoruz-ai

•

コンテンツ管理

Manipulates, generates, and extracts data from PDF documents using a variety of Python libraries and command-line tools.

The PDF Processing Toolkit is a comprehensive suite for Claude Code designed to handle complex document workflows. It empowers users to programmatically extract text and tables, merge or split documents, fill out forms, and create new PDFs from scratch using industry-standard libraries like pypdf and reportlab. Whether you are automating report generation, performing OCR on scanned documents, or managing security features like password protection and watermarking, this skill provides the implementation patterns and command-line utilities needed to streamline document processing at scale.

主な機能

01Merge, split, rotate, and reorder document pages

02Programmatically create and style PDFs using reportlab and canvas

03Manage document security via password encryption and metadata editing

041 GitHub stars

05Extract text and complex tabular data with layout preservation

06Perform OCR on scanned documents and extract embedded images

ユースケース

01Batch processing large document archives to apply watermarks or standardize metadata

02Automating the extraction of financial data from monthly bank statements into structured data formats

03Generating dynamic business reports, invoices, and certificates from raw application data

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add horuz-ai/claude-plugins pdf

For use in Claude.ai and ChatGPT