skills.rest
rickyananda
rickyanandaCOMMUNITY
Explore all skills by this author →
GitHub

ocr-and-documents

Extract text from PDFs, scans, and office documents into markdown.

1|Updated May 18, 2026
Search Tags:#ocr#pdf#markdown#tables#arxiv#document extraction
One-click install
npx skills add https://github.com/rickyananda/hermes-skills --skill ocr-and-documents-rickyananda
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/rickyananda/hermes-skills/tree/main/productivity/ocr-and-documents
Command: npx skills add https://github.com/rickyananda/hermes-skills --skill ocr-and-documents-rickyananda

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill turns PDFs, scans, and mixed document files into readable text and structured markdown, reducing manual copying, retyping, and document triage.

Core Features & Use Cases

  • Fast extraction from text-based PDFs using a lightweight local parser for quick reading and search.
  • High-quality OCR and layout-aware conversion for scanned pages, tables, equations, forms, and complex documents.
  • Remote URL-first workflow for arXiv papers and online PDFs, plus support guidance for DOCX and PPTX when those formats are involved.
  • Example: a researcher can convert an arXiv paper, preserve tables and equations, and review the output without opening a PDF viewer.

Quick Start

Ask the assistant to extract the attached PDF into markdown, or if you have a URL, tell it to try the online extractor first and fall back to local OCR only if 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 a scanned PDF into markdown?▼

To extract text from a scanned PDF into markdown, use marker-pdf for high-accuracy OCR and layout analysis. It handles scanned pages, tables, and equations, converting them directly into clean, structured markdown output.

Can I convert arXiv papers to markdown directly from a URL?▼

Yes, you can convert arXiv papers to markdown directly from a URL. The workflow supports remote URL-first extraction for online PDFs, pulling the document content and preserving its structure without requiring a local download.

What is the best way to extract tables and equations from a PDF?▼

The best way to extract tables and equations from a PDF is using marker-pdf. It performs layout-aware conversion to accurately capture complex document structures, preserving tables and equations as formatted markdown.

Does this PDF extraction approach work with DOCX and PPTX files?▼

Yes, this PDF extraction approach works with DOCX and PPTX files. It supports common office formats alongside text-based PDFs, scanned pages, HTML, EPUB, and images for comprehensive document text extraction.

Why use PyMuPDF instead of marker-pdf for document extraction?▼

Use PyMuPDF instead of marker-pdf for fast extraction from text-based PDFs. PyMuPDF is a lightweight local parser used for quick reading and search, while marker-pdf handles heavy OCR and complex layout analysis.

Related Skills

Explore More Education & Research Skills→
ruiyangruiyiruiyangruiyi

ocr-and-documents

Extract text and tables from PDFs and scans into Markdown.

Community
Intermediate
u9401066u9401066

pdf-reader

Extract text, figures, and citations from PDFs into Markdown.

Community
Intermediate
smilebank7smilebank7
2

Extract Materials

Extract text, tables, and equations from PDFs, PPTX, DOCX, and images into Markdown.

Community
Intermediate
juliuss1907juliuss1907

ocr-and-documents

Extract text from PDFs, scanned documents, and images using OCR.

Community
Intermediate