ocr-and-documents

Extract text from PDFs and scanned images using OCR.

7|Updated Mar 26, 2026

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

Ready to run

npx skills add https://github.com/kzinmr/ai-topics --skill ocr-and-documents-kzinmr

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/kzinmr/ai-topics/tree/main/config/hermes/skills/_overrides/ocr-and-documents
Command: npx skills add https://github.com/kzinmr/ai-topics --skill ocr-and-documents-kzinmr

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pymupdf, pymupdf4llm, marker-pdf, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill simplifies the process of converting documents into editable and searchable text, allowing for efficient information extraction and analysis.

Core Features & Use Cases

Text Extraction from PDFs and Scans: Extracts text from a variety of document formats including PDFs, scanned images, and more.
Format-Specific Extraction: Provides different tools for handling PDFs (e.g., pymupdf for text-only PDFs, marker-pdf for scanned PDFs with OCR).
Use Case: For example, when you have a stack of invoices in PDF format that need to be digitized for record-keeping.

Quick Start

Extract text from 'example_report.pdf' with ocr-and-documents extract text document.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 document?▼

To extract text from a scanned PDF, you need OCR capabilities to recognize the text within images. This Skill uses marker-pdf to process scanned PDFs and convert the visual text into editable, searchable text.

What's the best way to pull text from a text-based PDF?▼

For text-based PDFs, direct text extraction is more efficient than OCR. This Skill uses pymupdf to quickly parse and extract text directly from native PDF documents without needing optical character recognition.

Do I need a Python environment to extract text from PDFs and images?▼

Yes, you need a Python environment to run the document conversion and text extraction processes. The Skill requires specific libraries like pymupdf, pymupdf4llm, and marker-pdf installed to handle various formats.

Can I extract text from different document formats like images and scans?▼

Yes, you can extract text from various document formats including native PDFs and scanned images. The Skill provides specific tools like pymupdf for text-only PDFs and marker-pdf for scanned documents to ensure accurate extraction.

Why does my PDF text extraction return garbled or missing characters?▼

Garbled or missing characters during PDF text extraction often occur when processing scanned documents without OCR. Using marker-pdf for scanned PDFs applies optical character recognition to accurately capture the visual text.

Does pymupdf work with scanned PDFs or only text-based documents?▼

pymupdf is designed for extracting text directly from text-based PDFs. For scanned PDFs that contain images of text, you should use the marker-pdf tool included in the Skill to perform OCR extraction.