pdf

Extract text, merge, encrypt, and OCR PDFs using Python libraries.

2|1|Updated Mar 1, 2026

Search Tags:#ocr #pdf #merge #text-extraction #form-filling #pdf-processing

Ready to run

npx skills add https://github.com/junDevCodes/Claude-Harness --skill pdf-jundevcodes

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/junDevCodes/Claude-Harness/tree/main/.claude/skills/pdf
Command: npx skills add https://github.com/junDevCodes/Claude-Harness --skill pdf-jundevcodes

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, pdf2image, Pillow, and includes scripts (resource) components.

What problem does it solve?

PDFs often require repetitive manual handling for text extraction, merging, splitting, form processing, and security operations. This Skill centralizes these tasks, enabling automated reading, data extraction, document composition, and transformation to a searchable, editable, and secure PDF workflow.

Core Features & Use Cases

Text extraction and search across multi-page PDFs
Merge, split, rotate, watermark, and create new PDFs
Fill and encrypt/decrypt forms, extract images, and perform OCR on scans
Real-world use case: consolidate hundreds of vendor invoices into a searchable archive and export key fields to CSV

Quick Start

Ask the AI to read a PDF, extract text, and save a merged, searchable document with optional watermark

Frequently Asked Questions about pdf

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I extract text from scanned PDFs using OCR?▼

You can extract text from scanned PDFs by applying OCR to convert document images into searchable and editable data. It leverages pdf2image and Pillow to render pages, enabling automated text extraction across multi-page scans.

Can I merge multiple PDF invoices and export the extracted data to CSV?▼

Yes, you can merge multiple PDF invoices and export extracted data to CSV. It consolidates hundreds of vendor invoices into a searchable archive while extracting key fields for backend processing.

Does this PDF processing approach support form filling and encryption?▼

Yes, this PDF processing approach supports form filling and encryption. It leverages pypdf to read, fill, encrypt, and decrypt forms, providing secure document transformation capabilities for sensitive workflows.

What is the best way to split, rotate, and watermark PDF files in bulk?▼

The best way to split, rotate, and watermark PDF files in bulk is using script-based batch operations. It automates document composition and transformation by leveraging pypdf to apply structural changes across multiple documents.

Do I need Python libraries to extract images and perform text search across PDFs?▼

Yes, you need Python libraries like pdfplumber and pypdf to extract images and perform text search across PDFs. These dependencies enable automated reading and data extraction from multi-page documents within your pipelines.