Can I use this to extract structured tables from PDFs?

Yes, it includes specific implementation patterns using pdfplumber and pandas to convert PDF tables into structured formats like DataFrames or Excel files.

Does this skill handle encrypted or password-protected PDFs?

Yes, it includes instructions for encrypting, decrypting, and removing passwords from PDF files using both qpdf and pypdf.

Can Claude create new PDF documents from scratch with this skill?

Absolutely. It features patterns for ReportLab, allowing you to programmatically generate professional PDFs with custom text, graphics, and multi-page layouts.

Which Python libraries does this skill support?

The skill provides comprehensive guidance and code snippets for pypdf, pdfplumber, reportlab, and pytesseract for OCR tasks.

PDF Processing Toolkit

Name: PDF Processing Toolkit
Author: Krosebrook

byKrosebrook

•

Productivity & Workflow

Automates complex PDF operations including text extraction, table parsing, document generation, and form filling using Python and CLI utilities.

This Claude Code Skill provides a comprehensive suite of tools and patterns for programmatically handling PDF documents. It empowers Claude to perform advanced operations like extracting structured data from tables, merging or splitting multi-page documents, generating custom reports with ReportLab, and performing OCR on scanned files. Whether you are building data pipelines for document analysis or automating administrative form-filling tasks, this skill offers standardized implementation patterns for industry-leading Python libraries and command-line utilities.

Key Features

011 GitHub stars

02Document manipulation including merging, splitting, and page rotation

03High-fidelity text and table extraction using pdfplumber

04Programmatic PDF generation and report creation with ReportLab

05Security management including password protection and decryption

06OCR support for processing scanned documents via pytesseract

Use Cases

01Automating the extraction of financial data from PDF invoices into structured spreadsheets

02Generating dynamic PDF reports, certificates, or invoices from application data

03Batch processing and merging multiple documents for archival or distribution purposes

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add krosebrook/source-of-truth-monorepo pdf

For use in Claude.ai and ChatGPT

Download Skill