skills.rest
attentiondotnet
attentiondotnetCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

ocr-and-documents

Extract text from PDFs, DOCX, PPTX, and scanned documents via OCR.

Updated Mar 30, 2026
Search Tags:#ocr#pdf#pymupdf#document-processing#text-extraction#marker-pdf#scanned-documents
One-click install
npx skills add https://github.com/attentiondotnet/hermes-agent --skill ocr-and-documents-attentiondotnet
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/attentiondotnet/hermes-agent/tree/main/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/attentiondotnet/hermes-agent --skill ocr-and-documents-attentiondotnet

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill enables extraction of text from PDFs and scanned documents using OCR and document parsing tools, reducing manual review and data-entry effort.

Core Features & Use Cases

  • Remote URL extraction with web_extract for online PDFs.
  • Local text-based PDF extraction with pymupdf for fast results.
  • OCR-based extraction with marker-pdf for scanned documents and complex layouts.
  • Support for DOCX and PPTX via complementary skills for broader document workflows.
  • Use Case: Convert a batch of scanned conference papers into searchable text with preserved layout.

Quick Start

Extract text from a local PDF or scanned document using pymupdf first and fall back to marker-pdf OCR when needed.

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 using OCR?▼

Text extraction from scanned PDFs requires OCR to recognize characters from document images. This skill applies marker-pdf for OCR-based extraction, handling complex layouts and scanned documents when standard text-based extraction is insufficient.

What is the best way to extract text from a remote PDF URL?▼

Extracting text from a remote PDF URL is handled by web-based extraction first. This skill applies web_extract for online PDFs, fetching remote documents before parsing text with pymupdf or falling back to marker-pdf OCR.

Can I use pymupdf for fast local PDF text extraction?▼

Yes, pymupdf supports fast local text-based PDF extraction. This skill relies on pymupdf to quickly parse text from local files, automatically falling back to marker-pdf OCR if the document requires scanned image processing.

Does this PDF text extraction support DOCX and PPTX documents?▼

Yes, text extraction supports DOCX and PPTX documents via complementary skills. The skill uses python-docx and python-pptx for optional document-format support, enabling broader document workflows alongside standard PDF and OCR processing.

When do I need OCR for PDF text extraction instead of standard parsing?▼

OCR is needed for PDF text extraction when handling scanned documents or image-based files without embedded text. Standard parsing with pymupdf works for text-based PDFs, but marker-pdf OCR processes scanned images and preserves complex layouts.

Related Skills

Explore More Data & Analytics Skills→
bahayonghangbahayonghang
16

multimodal-looker

Extract text, entities, and relationships from images, PDFs, and charts.

Community
Basic
anzx01anzx01
2

pdf-reader

Extract plain text from PDF documents for indexing and downstream processing.

Community
Basic
GregsGreyCodeGregsGreyCode
6

ocr-and-documents

Extract text from PDFs and scanned documents into Markdown output.

Community
Intermediate
paxlabs-incpaxlabs-inc
7

ocr-and-documents

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

Community
Intermediate