ocr-and-documents

Name: ocr-and-documents
Availability: InStock
Author: eddielueng

Extract text from PDFs and scanned documents via URL or local OCR tools.

1|Updated Apr 14, 2026

Search Tags:#ocr #markdown conversion #document parsing #scanned documents #research ingestion #web extraction #pdf text extraction

Ready to run

npx skills add https://github.com/eddielueng/hermes-agent-zh --skill ocr-and-documents-eddielueng

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill removes the friction of turning PDFs, scanned documents, and mixed-format files into readable, searchable text and structured output.

Core Features & Use Cases

Remote-first extraction from URLs: Uses web_extract for remote PDF URLs (including arXiv-style links) to convert content into markdown.
Local extraction with the right engine: Uses pymupdf for fast text-based PDFs and marker-pdf for OCR/scanned documents, equations, and complex layouts.
Format coverage beyond plain PDFs: Handles DOCX (python-docx), PPTX (powerpoint skill), and additional document types via marker-pdf, including table-oriented outputs and image extraction.

Quick Start

Use the ocr-and-documents skill to extract text from the file invoice.pdf by choosing web_extract for a URL or running local extraction with pymupdf for text-based PDFs and marker-pdf for scanned/OCR needs.

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 using OCR?▼

To extract text from scanned PDFs, use marker-pdf for OCR processing and complex layout handling. It digitizes scanned pages and retrieves text from documents with equations or intricate structures.

What is the best way to convert remote research papers from URLs to markdown?▼

Use web_extract for remote-first extraction to convert research papers from URLs, including arXiv-style links, directly into markdown format for downstream analysis and ingestion.

Does pymupdf work for fast text extraction from text-based PDFs?▼

Yes, pymupdf is the recommended engine for lightweight local text extraction from text-based PDFs. Use marker-pdf instead when you need OCR for scanned documents or complex layout handling.

Can I parse DOCX and PPTX files for document digitization?▼

Yes, document parsing covers DOCX files via python-docx and PPTX files through the powerpoint skill, converting mixed-format documents into structured text and table outputs.

How do I retrieve tables and images from complex PDF layouts?▼

Use marker-pdf to retrieve tables and images from complex PDF layouts. It handles equation recognition and table-oriented outputs during the OCR and document parsing workflow.

When should I choose marker-pdf over pymupdf for PDF text extraction?▼

Choose marker-pdf over pymupdf when your PDFs require OCR for scanned pages, equation parsing, or complex layout handling. Use pymupdf only for fast, lightweight extraction from text-based PDFs.