quasi:extract

Name: quasi:extract
Availability: InStock
Author: giraphant

Extract chapter-level text from EPUB and PDF files with OCR support.

2|Updated Mar 8, 2026

Search Tags:#ocr #document processing #pdf #text extraction #epub #chapter splitting

Ready to run

npx skills add https://github.com/giraphant/quasi --skill quasi-extract

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: quasi:extract
Source: https://github.com/giraphant/quasi/tree/main/skills/extract
Command: npx skills add https://github.com/giraphant/quasi --skill quasi-extract

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates the extraction of text from digital books (EPUB, PDF) and scanned documents, preparing them for further analysis.

Core Features & Use Cases

EPUB to Text: Converts EPUB files into chapter-level plain text files.
PDF Chapter Splitting: Splits PDF documents into individual chapter text files, handling both digital and scanned (OCR) PDFs.
Use Case: You have a large PDF handbook for a new project. Use this Skill to automatically break it down into individual chapters, making it easy to analyze each section or feed into an AI for summarization.

Quick Start

Extract all chapters from the file '~/Downloads/my_book.epub' into the directory '/tmp/book_chapters'.

Frequently Asked Questions about quasi:extract

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

FAQPage Schema

How do I extract text from EPUB and PDF files into chapters?▼

To extract text from EPUB and PDF files into chapters, you can use this Skill to automatically segment content into individual plain text files and generate a manifest for organized output.

Can I use OCR to extract text from scanned PDFs?▼

Yes, you can perform OCR on scanned PDFs to extract text. The Skill utilizes shell scripts with Tesseract to process scanned documents and convert them into readable chapter text files.

What is the best way to split a large PDF handbook for AI summarization?▼

The best way to split a large PDF for AI summarization is using automated chapter splitting. This Skill breaks PDF documents into individual chapter text files, making it easy to analyze each section independently.

Does this text extraction tool require Tesseract for processing PDFs?▼

Tesseract is required for processing scanned PDFs via OCR. For digital PDFs and EPUB files, the Skill uses Python scripts to extract text directly without needing OCR dependencies.

How does EPUB to text conversion handle chapter splitting?▼

EPUB to text conversion handles chapter splitting by using Python scripts to parse the document structure. It converts the EPUB file into chapter-level plain text files for organized access.

What output format does the PDF and EPUB text extraction generate?▼

The PDF and EPUB text extraction generates plain text files segmented by chapter. It also creates manifest files to provide organized output and track the extracted content structure.