Can I create new PDF documents from scratch?

Absolutely. The skill includes comprehensive guides for using the reportlab library to generate new PDFs with custom text, graphics, and multi-page layouts.

How do I merge multiple PDF files with this skill?

You can use the pypdf library's PdfWriter or the qpdf command-line tool, both of which are fully supported and documented within the skill.

Can this skill extract tables from complex PDFs?

Yes, it utilizes the pdfplumber library specifically for its ability to recognize and extract structured table data into Python objects or Pandas DataFrames.

Does it support OCR for scanned documents?

Yes, the skill provides implementation patterns for using pytesseract and pdf2image to process scanned PDFs that do not contain native text.

PDF Manipulation Toolkit

Name: PDF Manipulation Toolkit
Author: Weiwei-Mao

byWeiwei-Mao

0•

コンテンツ管理

Simplifies programmatic PDF processing including text extraction, table parsing, merging, splitting, and document creation.

The PDF Manipulation Toolkit is a comprehensive skill designed to handle complex document workflows within Claude. It provides programmatic access to top-tier Python libraries like pypdf, pdfplumber, and reportlab, as well as powerful command-line tools like qpdf and poppler-utils. Users can automate the extraction of structured table data, perform OCR on scanned documents, generate dynamic reports from scratch, and manage document security through encryption and watermarking. This skill is essential for developers and data scientists building automated document pipelines or performing deep analysis on large PDF datasets.

主な機能

01High-accuracy text and layout-aware table extraction

02OCR capabilities for converting scanned images to searchable text

03Dynamic PDF generation with custom layouts and multi-page support

040 GitHub stars

05Comprehensive document editing including merge, split, and rotate

06Automated form filling and metadata management

ユースケース

01Batch processing document archives for watermarking and password protection

02Automating the generation of branded invoices and research reports

03Extracting financial data from PDF statements into structured CSV or Excel files

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add weiwei-mao/hydrology-skills pdf

For use in Claude.ai and ChatGPT

Download Skill