ocr-and-documents

Extract text and structured content from PDFs and scanned documents into Markdown.

1|Updated May 16, 2026
One-click install
npx skills add https://github.com/devMoez/titan --skill ocr-and-documents-devmoez
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/devMoez/titan/tree/main/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/devMoez/titan --skill ocr-and-documents-devmoez

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Extracting readable text from PDFs, scanned documents, and complex page layouts is slow and error-prone when done manually or with basic converters.

Core Features & Use Cases

  • URL-first extraction: Uses web_extract for PDFs available by URL (e.g., arXiv PDFs) to convert them to Markdown without local dependencies.
  • Lightweight local extraction (pymupdf): Fast, reliable extraction for text-based PDFs, plus optional Markdown and table extraction.
  • High-quality OCR & layout extraction (marker-pdf): Handles scanned documents, OCR, equations/LaTeX, forms, and complex layouts with strong multi-language support.
  • Use case: Convert a research paper PDF into clean Markdown for summarization and quoting, while preserving tables where possible.

Quick Start

Ask the AI to extract text from the attached file 'paper.pdf' and return Markdown using the URL-first flow when a URL is provided.

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 or arXiv document image?

Extract text from scanned PDFs or arXiv documents by using URL-based extraction for online files or local OCR pipelines for scanned images, converting them into readable Markdown text while preserving structural layout.

What is the best way to convert research papers to Markdown while preserving tables?

The best way to convert research papers to Markdown while preserving tables is using local extraction pipelines: pymupdf for text-based PDFs and marker-pdf for complex layouts, ensuring table structures remain intact.

Can I use marker-pdf for OCR-heavy documents and LaTeX equations?

Yes, marker-pdf supports OCR-heavy documents and LaTeX equations by applying high-quality layout extraction and multi-language OCR to accurately parse complex forms and scientific notation from scanned pages.

Do I need web_extract to parse PDFs available by URL?

Yes, you need web_extract first to handle URL availability for PDFs like arXiv papers, enabling URL-first extraction to convert online documents to Markdown without local dependencies.

Why does PDF table extraction fail on complex scanned layouts?

PDF table extraction fails on complex scanned layouts when using basic text converters instead of OCR-heavy pipelines; switching to marker-pdf applies advanced layout extraction to accurately parse table structures.

Are there disk space requirements for local PDF OCR processing?

Local PDF OCR processing requires disk space checks when using marker-pdf for OCR-heavy documents, ensuring sufficient storage exists for handling complex layouts and batch processing large document sets.