ocr-and-documents

Extract text from PDFs and documents using OCR or text-based parsers.

Updated Mar 24, 2026

Search Tags:#documents #ocr #pdf #pymupdf #text-extraction #marker-pdf #web_extract

Ready to run

npx skills add https://github.com/1thirteeng3/greenmoire --skill ocr-and-documents-1thirteeng3

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/1thirteeng3/greenmoire/tree/main/integrations/hermes-agent/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/1thirteeng3/greenmoire --skill ocr-and-documents-1thirteeng3

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Extract text from PDFs and scanned documents using OCR or text-based parsers.

Core Features & Use Cases

Remote URL extraction via web_extract for PDFs and hosted documents
Local text-based PDF extraction with pymupdf for fast, on-device parsing
OCR-based extraction with marker-pdf for scanned documents and complex layouts
DOCX support guidance (via python-docx) and PPTX reference through related skills

Quick Start

Provide a file path or URL and extract the text from it using the best available extractor.

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 PDFs and documents?▼

To extract text from scanned PDFs, use marker-pdf for OCR-based extraction to convert complex layouts and images into searchable, machine-readable text.

What is the best way to extract text from a local PDF without OCR?▼

For local text-based PDF extraction, use pymupdf to quickly parse and extract machine-readable text directly from native digital PDF files on-device.

Can I extract text from PDFs hosted on a remote URL?▼

Yes, you can extract text from remotely hosted documents using the web_extract feature to retrieve and process PDFs directly from their web URLs.

Does this OCR text extraction approach handle DOCX and PPTX files?▼

Yes, the workflow provides guidance for DOCX support via python-docx and references related skills for PPTX handling alongside its primary PDF extraction capabilities.

When should I use marker-pdf versus pymupdf for PDF text extraction?▼

Use marker-pdf for scanned documents and complex layouts requiring OCR, whereas pymupdf is suited for fast, local text-based extraction from native digital PDFs.

What are the limitations of using pymupdf for PDF text extraction?▼

pymupdf is limited to text-based extraction and cannot perform OCR on scanned documents or images, requiring marker-pdf for converting image-based PDFs into searchable text.