skills.rest
lucasfth
lucasfthCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

ocr-and-documents

Extract text from PDFs and scanned documents via OCR.

1|Updated Apr 30, 2025
Search Tags:#ocr#pdf#pymupdf#document-processing#text-extraction#marker-pdf#web-extract
One-click install
npx skills add https://github.com/lucasfth/config --skill ocr-and-documents-lucasfth
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/lucasfth/config/tree/main/.hermes/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/lucasfth/config --skill ocr-and-documents-lucasfth

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Extract text from PDFs and scanned documents. Use web_extract for remote URLs, pymupdf for local text-based PDFs, marker-pdf for OCR/scanned docs. For DOCX use python-docx, for PPTX see the powerpoint skill.

Core Features & Use Cases

  • Flexible extraction: prioritize remote extraction with web_extract, then switch to local or OCR-powered methods as needed.
  • Supports PDFs, scanned documents, and other formats via marker-pdf and pymupdf; can output Markdown, JSON, and structured data.
  • Real-world use: researchers can ingest arXiv PDFs and generate searchable text for analysis.

Quick Start

Extract text from document.pdf using the primary local extractor (pymupdf) by default, or marker-pdf if OCR is required.

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 PDF or scanned document?▼

You can extract text from PDFs and scanned documents using pymupdf for local text-based PDFs or marker-pdf for OCR, yielding searchable structured text and Markdown output.

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

For remote PDF URLs, use web_extract first to retrieve the document remotely, falling back to pymupdf for text-based PDFs or marker-pdf for OCR if local processing is required.

Does this document text extraction approach support DOCX and PPTX files?▼

Yes, document text extraction supports DOCX files using python-docx for parsing, while PPTX files are handled through a dedicated powerpoint skill to extract structured text.

When do I need OCR for PDF text extraction?▼

You need OCR for PDF text extraction when handling scanned documents lacking embedded text layers, utilizing marker-pdf to recognize and extract the text into searchable Markdown formats.

How do I convert a scanned PDF to Markdown?▼

To convert a scanned PDF to Markdown, apply marker-pdf for OCR processing, which recognizes the text and structures the output directly into Markdown format for researchers and professionals.

What are the limitations of using pymupdf for text extraction?▼

The limitation of pymupdf for text extraction is that it primarily handles text-based PDFs and cannot perform OCR on scanned documents, requiring a fallback to marker-pdf for image-heavy or scanned files.

Related Skills

Explore More Data & Analytics Skills→
89jobrien89jobrien
4

PDF Processing

Extract text and tables from native and scanned PDFs using pdfplumber.

Community
Advanced
Himanshu040604Himanshu040604

rag-implementation

Developes RAG systems integrating vector databases and advanced retrieval strategies for LLM applications.

Community
Advanced
shuyu-labsshuyu-labs
288

office-to-md

Convert Word, Excel, PowerPoint, and PDF documents to Markdown with preserved headings, tables, and images.

Official
Advanced
kaminocorpkaminocorp
228

ocr-and-documents

Extract text from PDFs and scanned documents into Markdown.

Official
Intermediate