Does it support command-line PDF tools?

Yes, it covers popular CLI utilities like qpdf and poppler-utils for quick document merging, splitting, and rotation tasks.

Can this skill handle scanned PDFs?

Yes, it includes specialized guidance on using pytesseract and pdf2image to perform Optical Character Recognition (OCR) on scanned documents.

Can I extract tables directly into pandas DataFrames?

Absolutely. The skill includes patterns for using pdfplumber alongside pandas to convert PDF tables into structured data for analysis.

What Python libraries are primarily used?

The skill provides implementation patterns for pypdf (basic operations), pdfplumber (table extraction), and reportlab (PDF generation).

PDF Processing Toolkit

Name: PDF Processing Toolkit
Author: boku-miyaji

byboku-miyaji

0•

콘텐츠 관리

Manipulates, generates, and extracts data from PDF documents using optimized Python and command-line utility patterns.

The PDF Processing Toolkit is a comprehensive suite designed to help Claude handle complex document workflows. It provides standardized implementation patterns for extracting structured text and tables, merging or splitting files, and creating professional-grade PDFs from scratch using libraries like ReportLab. Beyond basic manipulation, the skill includes advanced capabilities for OCR on scanned documents, metadata management, and programmatic form-filling, making it an essential tool for developers building document automation pipelines or data extraction services.

주요 기능

010 GitHub stars

02High-accuracy text and table extraction with layout preservation

03Comprehensive document manipulation (merge, split, rotate, watermark)

04Advanced OCR capabilities for processing scanned PDF documents

05Programmatic PDF generation with multi-page support and styling

06Security management including encryption and password protection

사용 사례

01Batch processing document archives for searchable text and metadata

02Generating dynamic PDF reports and certificates from application data

03Automating the extraction of financial data from unstructured PDF invoices

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add boku-miyaji/claude_dev pdf

For use in Claude.ai and ChatGPT

Download Skill