ocr-and-documents

Extract text from PDFs and scanned documents using OCR and parsing tools.

Updated Apr 29, 2026
One-click install
npx skills add https://github.com/fikriaf/agentos --skill ocr-and-documents-fikriaf
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/fikriaf/agentos/tree/main/src/agentos/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/fikriaf/agentos --skill ocr-and-documents-fikriaf

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill addresses the challenge of extracting text from various document formats, including PDFs, scanned documents, and images, making information easily accessible and usable.

Core Features & Use Cases

  • Text Extraction from PDFs: Extract text from PDFs using web_extract for remote URLs or local text-based PDFs.
  • OCR for Scanned Documents: Use marker-pdf for OCR on scanned documents with support for multiple languages.
  • Document Parsing: Extract tables, equations, and other structured data from documents.
  • Use Case: If you have a scanned PDF of a research paper and need to extract the text for analysis, this skill can help you do so efficiently.

Quick Start

Extract text from a scanned document using the ocr-and-documents skill with the command: ocr-and-documents(document.pdf).

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 document?

To extract text from a scanned PDF, you can use OCR tools like marker-pdf to recognize text in multiple languages. This process parses scanned documents and images to convert them into accessible, editable text.

Can I extract text from a PDF hosted at a remote URL?

Yes, you can extract text from a PDF hosted at a remote URL. The extraction process uses web_extract to fetch remote documents and parse the text content directly from the online source.

What is the best way to parse tables and equations from PDFs?

The best way to parse tables and equations from PDFs is by using document parsing libraries like marker-pdf. These tools perform structured data extraction to accurately capture complex elements alongside standard text.

Does this text extraction approach work for local text-based PDFs?

Yes, this text extraction approach works for local text-based PDFs. It utilizes pymupdf to parse local files, efficiently extracting native text without requiring optical character recognition.

Do I need web_extract and pymupdf to extract text from documents?

Yes, you need web_extract for remote URLs and pymupdf for local text-based PDFs. These dependencies are required alongside marker-pdf to execute text extraction and handle different document formats properly.

What are the limitations of OCR for scanned documents?

OCR for scanned documents may struggle with low image quality or complex layouts. While marker-pdf supports multiple languages and structured data parsing, extraction accuracy heavily depends on the clarity of the original scanned document.