ocr-and-documents

Name: ocr-and-documents
Availability: InStock
Author: zhouboyu-xreal

Convert PDFs and scanned documents into editable text using OCR.

Updated Jun 9, 2026

Search Tags:#ocr #pdf #document conversion #text extraction #image processing

Ready to run

npx skills add https://github.com/zhouboyu-xreal/Hermes-Memory --skill ocr-and-documents-zhouboyu-xreal

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/zhouboyu-xreal/Hermes-Memory/tree/main/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/zhouboyu-xreal/Hermes-Memory --skill ocr-and-documents-zhouboyu-xreal

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pymupdf, marker-pdf, python-docx, python-pptx, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Extracting text from PDFs, scanned documents, and images can be a time-consuming task. This Skill automates the process, allowing you to convert documents to editable text with ease.

Core Features & Use Cases

OCR Text Extraction: Convert scanned documents and images into editable text.
PDF Text Extraction: Extract text from PDFs using pymupdf and marker-pdf.
Markdown and JSON Output: Export extracted text in Markdown or JSON format.
Use Case: Quickly extract text from a scanned receipt to add it to your expense tracking system.

Quick Start

Extract text from a PDF using the ocr-and-documents skill: ocr_and_documents.extract_text(file="scan.pdf")

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 a scanned PDF or image document?▼

To extract text from a scanned PDF or image, you need OCR technology to recognize characters. This Skill uses pymupdf and marker-pdf to convert scanned documents and images into editable text automatically.

Can I extract text from PDFs and export it as Markdown or JSON?▼

Yes, you can extract text from PDFs and export it as Markdown or JSON. The Skill processes the document content and outputs structured formats, making it easy to integrate the extracted text into other workflows.

Does this PDF text extraction tool work with Python document libraries?▼

Yes, the PDF text extraction works directly with Python libraries. It utilizes pymupdf and marker-pdf for PDFs, alongside python-docx and python-pptx, enabling automated document conversion within Python environments.

What is the best way to automate text extraction from multiple scanned receipts?▼

The best way to automate text extraction from scanned receipts is using an OCR script. This Skill processes image files via Python, converting scanned receipt images into editable text for expense tracking systems.

Do I need Python to convert scanned documents to editable text?▼

Yes, you need a Python environment to run the conversion process. The Skill relies on Python dependencies like pymupdf and marker-pdf to execute the OCR and document parsing required for text extraction.

Why does my PDF text extraction return unreadable characters for scanned pages?▼

PDF text extraction returns unreadable characters for scanned pages because standard parsers cannot read images. You need OCR to recognize the text within the scanned image, which this Skill applies to convert it properly.