ocr-and-documents

Extract text from PDFs, scanned documents, and images using OCR.

4|Updated Apr 19, 2026

Search Tags:#ocr #document processing #pdf #text extraction #document parsing

Ready to run

npx skills add https://github.com/ragnarokhaa/hermes --skill ocr-and-documents-ragnarokhaa

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/ragnarokhaa/hermes/tree/main/hermes-cerul-tech-news-package/hermes-cerul-tech-news-package/hermes-agent/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/ragnarokhaa/hermes --skill ocr-and-documents-ragnarokhaa

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires PyMuPDF, marker-pdf, python-docx, pymupdf4llm, and includes scripts (resource) components.

What problem does it solve?

This Skill solves the problem of manually extracting text from PDFs and scanned documents, allowing for fast and efficient text extraction in various formats.

Core Features & Use Cases

Text Extraction: Extract text from PDFs, scanned documents, images, and other file formats using OCR and document parsing tools.
PDF & Document Extraction: Handles both text-based PDFs and scanned documents, including OCR for scanned pages.
Use Case: Efficiently convert PDFs to editable text, or extract specific information from scanned documents for easier data processing.

Quick Start

Use the ocr-and-documents skill to extract text from the 'report.pdf' document.

Frequently Asked Questions about ocr-and-documents

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

FAQPage Schema

How do I extract text from scanned PDF documents?▼

This solution extracts text from scanned PDF documents by applying OCR technology and document parsing libraries like PyMuPDF and marker-pdf. It processes both text-based and scanned pages to output editable text for data extraction.

What is the best way to convert scanned documents to editable text?▼

The best way to convert scanned documents to editable text is using a combined OCR and document parsing approach. By utilizing libraries like marker-pdf and python-docx, this method automates text extraction from images and scanned pages for easier data processing.

Does PyMuPDF support text extraction from images?▼

PyMuPDF supports text extraction from images and PDFs, while marker-pdf handles OCR for scanned documents. Together, these dependencies allow you to extract specific information from scanned documents and images without manual transcription.

Can I use python-docx to extract text from PDFs?▼

python-docx processes editable text after extraction, while PyMuPDF and marker-pdf parse the PDFs. You can use this workflow to extract text from PDFs and then process or export the editable text using python-docx for administrative tasks.

Why does text extraction fail on scanned PDF pages?▼

Text extraction fails on scanned PDF pages because they contain images rather than embedded text. This requires OCR technology to recognize the text, which this solution provides using marker-pdf and PyMuPDF to process scanned documents successfully.

Do I need pymupdf4llm to extract text from research papers?▼

pymupdf4llm is included in the dependencies to help extract text from PDFs like research papers. It works alongside PyMuPDF and marker-pdf to ensure efficient text extraction and document parsing for research and data extraction tasks.