Which libraries are used for table extraction?

The skill primarily utilizes pdfplumber, which is highly effective at identifying and extracting complex tabular data into formats like Pandas DataFrames.

Can this skill handle scanned PDF documents?

Yes, it provides implementation patterns using pytesseract and pdf2image to perform OCR on scanned files and convert them into machine-readable text.

Does this skill work with command-line tools?

Yes, it integrates with powerful CLI utilities like qpdf and poppler-utils for high-performance merging, splitting, and text conversion tasks.

Is it possible to create PDFs from scratch?

Absolutely. The skill includes guidance for using the reportlab library to generate complex, multi-page PDF documents with custom layouts and graphics.

Can I password-protect or decrypt PDFs with this skill?

Yes, it includes instructions and code snippets for using pypdf and qpdf to add encryption, remove passwords, or manage document permissions.

PDF Processing & Manipulation

Name: PDF Processing & Manipulation
Author: aitytech

byaitytech

•

184

•

Productivity & Workflow

Automates complex PDF workflows including text/table extraction, document merging, form filling, and OCR processing.

This skill equips Claude with a comprehensive toolkit for programmatic PDF management, enabling the automation of document-heavy workflows. It provides optimized patterns for extracting structured data from tables, merging or splitting multi-page documents, and generating professional reports from scratch using Python and CLI tools. By integrating libraries like pypdf, pdfplumber, and reportlab, it allows Claude to handle everything from metadata manipulation and password protection to OCR for scanned documents, making it an essential utility for data processing and administrative automation.

Key Features

01High-fidelity text and table extraction with layout preservation

02Automated PDF form filling and metadata management

03Comprehensive document assembly: merge, split, and rotate pages

04Dynamic PDF generation and report creation with custom styles

05184 GitHub stars

06OCR capabilities for processing scanned documents into searchable text

Use Cases

01Batch processing legal or administrative documents for archival and indexing

02Automating data extraction from financial statements and invoices into structured formats

03Generating personalized PDF certificates, reports, or contracts at scale

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add aitytech/agentkits-marketing document-skills

For use in Claude.ai and ChatGPT

Download Skill