ocr-and-documents

Name: ocr-and-documents
Availability: InStock
Author: dq666dinger

Extract text and structured data from PDFs using pymupdf and marker-pdf.

1|Updated May 10, 2026

Search Tags:#ocr #pdf #markdown #pymupdf #document-processing #text-extraction #marker-pdf

Ready to run

npx skills add https://github.com/Dq666dinger/my-hermes --skill ocr-and-documents-dq666dinger

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/Dq666dinger/my-hermes/tree/main/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/Dq666dinger/my-hermes --skill ocr-and-documents-dq666dinger

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Documents and PDFs often contain valuable text, but extracting it from scans or poorly structured files is tedious and error-prone. This skill provides reliable text extraction from both native PDFs and scanned documents using lightweight pymupdf or high-accuracy OCR with marker-pdf, delivering clean output for downstream workflows.

Core Features & Use Cases

Text-based extraction from PDFs using pymupdf for fast, lightweight processing.
OCR-based extraction from scanned documents using marker-pdf for high accuracy and layout-aware results.
Output in Markdown, with optional image extraction and table/metadata support for research, analytics, and archival tasks.

Quick Start

Run the lightweight pymupdf workflow on a PDF to extract plain text, or run marker-pdf for OCR on scanned documents to produce Markdown output.

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?▼

Extract text from scanned PDFs using the marker-pdf library for layout-aware OCR processing. This handles scanned manuscripts and reports, outputting clean structured text for downstream research or archival workflows.

What is the best way to convert PDFs to Markdown format?▼

Convert PDFs to Markdown using marker-pdf for OCR-based extraction or pymupdf4llm for text-based files. This generates structured Markdown outputs capturing document layout, tables, and metadata for research and analytics workflows.

Does pymupdf support extracting images and tables from native PDFs?▼

Yes, pymupdf supports extracting images, tables, and plain text from native PDFs. It provides a fast, lightweight workflow for digitizing text-based reports and administrative documents without requiring OCR.

When should I use marker-pdf instead of pymupdf for document processing?▼

Use marker-pdf for scanned documents requiring high-accuracy OCR and layout-aware extraction, while pymupdf handles fast text-based extraction from native PDFs. Choose based on whether your input files are scanned images or native text.

Can I extract structured data like tables and metadata from PDFs?▼

Yes, you can extract structured data including tables, images, and metadata from documents. The skill utilizes pymupdf and marker-pdf to process archival files, delivering structured JSON and Markdown outputs for analytics.

What are the limitations of OCR-based text extraction from PDFs?▼

OCR-based extraction using marker-pdf requires more processing overhead than native text extraction. For clean, text-based PDFs, lightweight pymupdf extraction is preferred to avoid unnecessary OCR latency on digital documents.