Can this skill handle scanned PDFs?

Yes, it includes patterns for using pytesseract and pdf2image to perform Optical Character Recognition (OCR) on scanned images or non-selectable PDF text.

Can I use this for command-line PDF tasks?

Absolutely; it covers powerful CLI tools like qpdf, pdftk, and poppler-utils for fast, scriptable document operations without writing Python code.

Does it support password-protected files?

Yes, it includes specific methods for decrypting password-protected files (with the correct credentials) and encrypting new documents for security.

Can I extract tables from complex PDFs?

Yes, the toolkit uses pdfplumber to identify and extract structured tables, which can then be easily converted into Pandas DataFrames for analysis.

Which Python libraries are supported?

The skill provides comprehensive guidance for pypdf for basic operations, pdfplumber for data extraction, and ReportLab for PDF creation.

PDF Manipulation Toolkit

Name: PDF Manipulation Toolkit
Author: Daisuke134

byDaisuke134

•

Productivity & Workflow

Automates PDF manipulation, text extraction, and document generation using Python and command-line tools.

The PDF Manipulation Toolkit is a comprehensive suite designed for advanced programmatic handling of PDF documents. It enables Claude to extract structured data from tables, merge or split documents, and generate professional PDFs from scratch using industry-standard libraries. With support for OCR on scanned documents, form filling, and high-performance command-line utilities like qpdf, this skill is essential for developers building document-heavy workflows, automated reporting systems, or data extraction pipelines.

Key Features

01Generate custom PDFs from scratch using ReportLab templates

02Merge, split, rotate, and password-protect PDF documents

03Automate PDF form filling and metadata management

04Extract text and structured tables with layout preservation

05Perform OCR on scanned documents using Tesseract integration

063 GitHub stars

Use Cases

01Batch processing large document archives for organization, merging, or encryption

02Automating the generation of branded reports, certificates, and business documents

03Extracting financial data from complex invoices and bank statements into structured formats

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add daisuke134/anicca.ai pdf

For use in Claude.ai and ChatGPT

Download Skill