skills.rest
Plaidmustache
PlaidmustacheCOMMUNITY
Explore all skills by this author →
GitHub

ocr-and-documents

Extract text from PDFs and scanned documents into Markdown or plain text.

Updated May 4, 2026
Search Tags:#ocr#pdf#pymupdf#document-processing#arxiv#text-extraction#marker-pdf
One-click install
npx skills add https://github.com/Plaidmustache/hermes-nulab --skill ocr-and-documents-plaidmustache
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/Plaidmustache/hermes-nulab/tree/main/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/Plaidmustache/hermes-nulab --skill ocr-and-documents-plaidmustache

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Manually extracting text from PDFs and scanned documents is time-consuming and error-prone. This skill provides OCR-based and document-parsing workflows to convert content into searchable, editable text suitable for research, archiving, and data extraction.

Core Features & Use Cases

  • OCR-enabled extraction: Converts scanned PDFs and images to searchable text using marker-pdf.
  • Fast, local processing: Uses pymupdf for quick text extraction on digital PDFs.
  • Versatile outputs: Produces plain text or Markdown for indexing, notes, or archival records.

Quick Start

Extract text from a sample PDF by running the pymupdf extractor on 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?▼

To extract text from a scanned PDF, this skill uses marker-pdf for OCR-based extraction, converting image content into searchable and editable text suitable for archiving and research workflows.

What is the best way to convert a digital PDF to markdown?▼

The best way to convert a digital PDF to markdown is using pymupdf, which provides fast local text extraction and structures the output into plain text or Markdown formats for indexing.

Can I extract text from a document URL without downloading the file?▼

Yes, you can extract text from a document URL using the web_extract fallback feature, which fetches URL-based documents and processes them through the available OCR or text extraction workflows.

Does pymupdf work for OCR on scanned images?▼

Pymupdf does not handle OCR on scanned images; it is designed for fast text extraction on digital PDFs. For scanned documents and images, marker-pdf is used as the OCR fallback.

How do I process arxiv PDFs for research data extraction?▼

You process arxiv PDFs for research data extraction by running the local extractors to convert the academic documents into structured Markdown, making the content searchable for data indexing.

Related Skills

Explore More Education & Research Skills→
nyxoraAInyxoraAI
5

ocr-and-documents

Convert PDFs and scanned images into machine-readable text using OCR.

Community
Advanced
WILLOSCARWILLOSCAR
497

pdf-text-extractor

Extract plain text from PDF documents and generate index files.

Community
Intermediate
HemantSudarshanHemantSudarshan

embedding-strategies

Compare and optimize embedding models for AI-driven search and retrieval.

Community
Advanced
guccangguccang
3

ocr-and-documents

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

Community
Advanced