ocr-and-documents

Extract text from PDFs and scanned documents using pymupdf or marker-pdf OCR.

Updated May 23, 2026
One-click install
npx skills add https://github.com/zengbaocheng/hermes-tech-hub --skill ocr-and-documents-zengbaocheng
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/zengbaocheng/hermes-tech-hub/tree/main/productivity/ocr-and-documents
Command: npx skills add https://github.com/zengbaocheng/hermes-tech-hub --skill ocr-and-documents-zengbaocheng

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Manual reading and data extraction from PDFs and scanned documents is time-consuming and error-prone. This Skill provides reliable text extraction and structure-aware parsing to enable searchable archives and downstream processing.

Core Features & Use Cases

  • OCR-enabled text extraction for scanned PDFs and images.
  • Markdown output and table/image extraction for easy integration into workflows.
  • Flexible modes using pymupdf for fast, local extraction or marker-pdf for OCR and advanced layout analysis.
  • Use Case: Convert a batch of scanned invoices into searchable text and structured data for indexing.

Quick Start

Use the OCR-and-document extraction on a local file like document.pdf to obtain markdown and optional metadata.

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 and images?

Using OCR to extract text from scanned PDFs and images with marker-pdf enables searchable archives and downstream processing. It handles multilingual content, tables, and images, providing structured data for indexing and knowledge extraction tasks.

Can I convert a PDF to Markdown and extract tables at the same time?

Converting PDFs to Markdown while extracting tables and images is supported via marker-pdf OCR. This structure-aware parsing outputs Markdown with integrated tables and images, enabling easy workflow integration for research and archival tasks.

What is the best way to parse specific page ranges from a local PDF file?

Parsing specific page ranges from local PDFs is achievable using page-range controls in both pymupdf and marker-pdf modes. This yields targeted text and metadata extraction, enabling fast local processing without OCR overhead.

Does this text extraction tool work with URLs and multilingual content?

Yes, text extraction works with local files and URLs while handling multilingual content. It processes PDFs and scanned documents across research and archival tasks, producing searchable text and optional metadata.

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

Choose pymupdf for fast, lightweight local PDF text extraction without OCR needs, and choose marker-pdf for OCR-enabled extraction with advanced layout analysis. Both modes yield searchable text and optional Markdown output.

Why does my PDF text extraction lose formatting and table structures?

PDF text extraction loses formatting and table structures when lacking advanced layout analysis. Using marker-pdf OCR with Markdown output preserves document structure, tables, and images, yielding structured data for reliable downstream processing.