skills.rest
Hermesagents
HermesagentsCOMMUNITY
Explore all skills by this author →
GitHub

ocr-and-documents

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

Updated Aug 27, 2026
Search Tags:#ocr#pdf#pymupdf#document-processing#text-extraction#marker-pdf#web_extract
One-click install
npx skills add https://github.com/Hermesagents/hermes-agents --skill ocr-and-documents-hermesagents
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/Hermesagents/hermes-agents/tree/main/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/Hermesagents/hermes-agents --skill ocr-and-documents-hermesagents

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Extract text from PDFs and scanned documents automatically to enable search, indexing, and data reuse across research, admin, and archival workflows.

Core Features & Use Cases

  • Remote extraction from URLs using web_extract to convert online documents to Markdown text.
  • Local extraction using pymupdf for text-based PDFs and marker-pdf for OCR/scanned documents, with options for tables, images, and markdown output.
  • Real-world use cases include extracting article text from arXiv PDFs, digitizing scanned invoices, and converting documents for searchability and downstream analytics.

Quick Start

Provide a document URL or local path and I will extract text using web_extract for URLs, or pymupdf for text-based PDFs and marker-pdf for OCR documents.

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 for search indexing?▼

To extract text from scanned PDFs, this tool applies marker-pdf for OCR processing. It converts scanned invoices and archives into searchable text or Markdown output, enabling downstream search and indexing.

What is the best way to convert an online PDF to Markdown text?▼

The best way to convert online PDFs to Markdown is using the web_extract function for remote URLs. This automatically retrieves the document and extracts its text content without requiring a local download.

Does pymupdf work for extracting text from text-based PDFs?▼

Yes, pymupdf works specifically for extracting text from text-based PDFs. It parses the embedded text directly, while marker-pdf is used instead for scanned documents that require OCR.

Can I extract text from research papers on arXiv using this tool?▼

Yes, you can extract text from arXiv research papers by providing the document URL. It uses web_extract to retrieve and convert the online academic PDF into searchable Markdown text.

What are the limitations of extracting text from DOCX and PPTX files?▼

For DOCX and PPTX files, the extraction process relies on separate workflow guidance rather than direct automated parsing. The core implementation focuses primarily on PDF formats and scanned documents using OCR.

When do I need OCR for document processing versus direct text extraction?▼

You need OCR for document processing when handling scanned documents or images without embedded text, utilizing marker-pdf. Direct text extraction with pymupdf applies only to text-based PDFs.

Related Skills

Explore More Data & Analytics Skills→
anxiety135790anxiety135790

ocr-and-documents

Extract text from PDFs, scanned documents, and images into plain text or markdown.

Community
Advanced
alibabaalibaba
10.5k

pdf-extractor

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

Official
Intermediate
igorrazvodovskyigorrazvodovsky
1

pdf-processing

Extract text and tables from PDFs using pdfplumber.

Community
Intermediate
heysuhasheysuhas
2

ocr-and-documents

Extract text, tables, and images from scanned PDFs and office files.

Community
Intermediate