pdf

Extract text and tables from PDFs using Python libraries.

8|3|Updated Feb 8, 2026

Search Tags:#automation #ocr #pdf #text-extraction #form-filling #document-management #pdf-processing

Ready to run

npx skills add https://github.com/haberlah/dotfiles-claude --skill pdf-haberlah

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

PDFs are everywhere and manually performing common operations is time-consuming and error-prone. This skill provides a cohesive, code-based approach to read, extract, modify, and manage PDF documents, eliminating repetitive work.

Core Features & Use Cases

Read and extract text and tables from PDFs.
Merge, split, rotate pages, watermark, and create new PDFs.
Fill both fillable and non-fillable forms, encrypt/decrypt PDFs, extract images, and run OCR on scanned documents.
Use case: Automatically process a batch of invoices by extracting line-item data and compiling a CSV.

Quick Start

Run the included scripts to extract text from sample.pdf and save it to output.txt.

Frequently Asked Questions about pdf

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

FAQPage Schema

How do I extract text and tables from a PDF for batch processing?▼

To extract text and tables from a PDF, you can use this skill's automated scripts powered by pdfplumber and pypdf. It reads document content and compiles extracted line-item data into outputs like CSV files for batch processing.

Can I fill both fillable and non-fillable PDF forms automatically?▼

Yes, you can fill both fillable and non-fillable PDF forms automatically. The skill processes form digitization workflows with input validation, handling interactive fields and flattened documents seamlessly.

What is the best way to run OCR on scanned PDF documents?▼

The best way to run OCR on scanned PDF documents is using this skill's integrated approach with pdf2image and Pillow. It converts scanned pages into images, enabling accurate text extraction from archival documents.

Does this PDF processing approach support merging, splitting, and watermarking?▼

Yes, this PDF processing approach supports merging, splitting, rotating, and watermarking documents. It provides a cohesive, code-based method to modify and manage PDF files, eliminating repetitive manual editing.

Do I need Python libraries installed to encrypt and extract images from PDFs?▼

Yes, you need Python libraries including pypdf, pdfplumber, pdf2image, and Pillow installed. These dependencies are required to execute security tasks like encryption and decryption, as well as image extraction.

Why does PDF text extraction fail on scanned documents without OCR?▼

PDF text extraction fails on scanned documents without OCR because the content is embedded as images rather than selectable text. Applying OCR via pdf2image converts these scans into readable text data.