skills.rest
photonics-dhl
photonics-dhlCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

ocr-and-documents

Extract text and structured data from PDFs and documents using OCR and parsing tools.

Updated Apr 30, 2026
Search Tags:#ocr#pdf#research#arxiv#text-extraction#document-extraction
One-click install
npx skills add https://github.com/photonics-dhl/Hermes --skill ocr-and-documents-photonics-dhl
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/photonics-dhl/Hermes/tree/main/hermes-home/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/photonics-dhl/Hermes --skill ocr-and-documents-photonics-dhl

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 and parsing tools to convert content into searchable text and structured data.

Core Features & Use Cases

  • Remote URL extraction: Use web_extract to fetch and convert documents from URLs.
  • Local text-based PDFs: Rely on pymupdf for fast, accurate text extraction.
  • OCR for scanned documents: Use marker-pdf to OCR and preserve layout, tables, and code blocks.
  • DOCX/PPTX support: Leverage Python-docx for DOCX and reference PPTX via the powerpoint skill.

Quick Start

Upload a document or specify a URL and I will extract its text and structure using the best available tool.

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 using OCR?▼

To extract text from scanned PDFs, this Skill uses marker-pdf for OCR, preserving the original layout, tables, and code blocks during conversion into searchable text.

What is the best way to extract text from a research paper on arxiv?▼

For arxiv research papers, the Skill uses web_extract to fetch and convert the document from its remote URL, or relies on pymupdf for local text-based PDF files to produce accurate text extraction.

Can I extract text from DOCX and PPTX files?▼

Yes, DOCX text extraction is handled by python-docx, while PPTX processing is referenced through the powerpoint skill to convert your documents into structured text.

Does pymupdf work for text extraction from all PDF documents?▼

pymupdf is used specifically for fast, accurate text extraction from local text-based PDFs. Scanned documents require OCR instead, which uses marker-pdf to process the image-based content.

How does the Skill choose between URL extraction and local PDF parsing?▼

The workflow prefers web_extract to fetch and convert documents from remote URLs, and uses pymupdf for local text-based PDFs, automatically selecting the best available tool based on your input.

Related Skills

Explore More Education & Research Skills→
attentiondotnetattentiondotnet

ocr-and-documents

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

Community
Intermediate
alibabaalibaba
10.5k

pdf-extractor

Extract text, tables, and metadata from PDF documents into JSON.

Official
Intermediate
wangx7wangx7

pptx

Automates PowerPoint (.pptx) creation, editing, and analysis workflows using PptxGenJS and LibrePDF conversion.

Community
Advanced
GregsGreyCodeGregsGreyCode
6

ocr-and-documents

Extract text from PDFs and scanned documents into Markdown output.

Community
Intermediate