ocr-and-documents

Extract text, tables, and metadata from PDFs and scanned documents.

Updated May 14, 2026
One-click install
npx skills add https://github.com/SethyPagna/Secretary-Jarvis --skill ocr-and-documents-sethypagna
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/SethyPagna/Secretary-Jarvis/tree/main/src/capabilities/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/SethyPagna/Secretary-Jarvis --skill ocr-and-documents-sethypagna

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill removes the manual effort of reading PDFs, scanned pages, and image-based documents by turning them into searchable text and structured output.

Core Features & Use Cases

  • Extract text from text-based PDFs with a lightweight local parser.
  • Perform OCR on scanned documents and complex layouts when higher fidelity is needed.
  • Recover tables, images, metadata, and markdown output for research papers, reports, invoices, and archived files.
  • Prefer a remote URL extraction path first when the document is available online, then fall back to local processing for files on disk.

Quick Start

Ask the skill to extract the text, tables, or markdown from the document you uploaded, using OCR if it is scanned and web extraction if you only have a URL.

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 and tables from a scanned PDF?

To extract text and tables from a scanned PDF, use OCR and layout analysis to convert the document into searchable text and structured markdown. This handles complex reading orders and recovers tables.

Can I convert a PDF document to markdown from a remote URL?

Yes, you can convert a PDF to markdown from a remote URL. The system uses web extraction first for accessible online links and then falls back to local parsing for files on disk.

When do I need OCR for PDF table extraction?

You need OCR for PDF table extraction when the source file is a scanned document or image rather than a text-based PDF. This ensures higher fidelity layout analysis and accurate table capture.

Does marker-pdf support processing equations and forms in documents?

Yes, marker-pdf supports processing equations and forms in documents. It performs advanced OCR and layout analysis to handle complex structures, equations, and forms effectively.

What is the best way to get metadata and images from research papers?

The best way to get metadata and images from research papers is using a local parser that applies lightweight extraction or advanced OCR to retrieve document metadata, images, and text.

Can I extract content from specific page ranges in a large PDF?

Yes, you can extract content from specific page ranges in a large PDF. Page range processing allows you to target specific sections, avoiding the need to parse the entire document.