skills.rest
ruiyangruiyi
ruiyangruiyiCOMMUNITY
Explore all skills by this author →
GitHub

ocr-and-documents

Extract text and tables from PDFs and scans into Markdown.

Updated May 26, 2026
Search Tags:#ocr#table extraction#markdown conversion#document parsing#scanned documents#research ingestion#pdf text extraction
One-click install
npx skills add https://github.com/ruiyangruiyi/hermes-agent --skill ocr-and-documents-ruiyangruiyi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/ruiyangruiyi/hermes-agent/tree/main/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/ruiyangruiyi/hermes-agent --skill ocr-and-documents-ruiyangruiyi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

OCR and document parsing remove the need to manually read and copy text from PDFs, scanned documents, and image-based files, turning them into usable text for research, notes, and downstream processing.

Core Features & Use Cases

  • URL-first extraction: If a document has a URL, you can convert it via web extraction (PDF-to-Markdown) before attempting local processing.
  • Lightweight text-based PDF extraction: Use pymupdf for fast, dependency-light extraction of text, tables, and basic metadata from text-based PDFs.
  • High-quality OCR and layout analysis: Use marker-pdf for scanned PDFs (90+ languages), equations/LaTeX, forms, and complex layouts, with optional image export and structured JSON output.
  • Use case: Convert an arXiv PDF into Markdown for summarization, then extract tables from a separate report PDF into clean table representations for analysis.

Quick Start

Ask the AI to extract text as Markdown from the URL or local file you provide, using web extraction when available and falling back to local OCR when 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 and convert it to Markdown?▼

To extract text from a scanned PDF and convert it to Markdown, apply an OCR-intensive conversion tool like marker-pdf. This approach handles scanned documents in 90+ languages and preserves complex layouts into Markdown-ready text.

What is the best way to extract tables from a PDF for research analysis?▼

The best way to extract tables from a PDF for research analysis is using a lightweight library like pymupdf. It provides fast, dependency-light extraction of tables and basic metadata directly from text-based PDF files for downstream processing.

Can I convert an arXiv PDF to Markdown directly from a URL?▼

Yes, you can convert an arXiv PDF to Markdown directly from a URL by using a URL-first web extraction path. This method retrieves and converts the document to Markdown before attempting any local file processing.

Does this PDF text extraction approach work with equations and LaTeX?▼

Yes, PDF text extraction works with equations and LaTeX when using a layout-aware OCR converter like marker-pdf. It is specifically designed to handle complex layouts, forms, and mathematical equations during the document parsing process.

When should I use pymupdf instead of marker-pdf for document parsing?▼

You should use pymupdf instead of marker-pdf for lightweight text-based PDFs where you need fast extraction of text and tables. Use marker-pdf for OCR-intensive tasks involving scanned documents, complex layouts, or equations.

Can I export extracted PDF tables and content as structured JSON?▼

Yes, you can export extracted PDF tables and content as structured JSON. By using an OCR-intensive, layout-aware converter like marker-pdf, you can generate structured JSON outputs alongside optional image exports during document parsing.

Related Skills

Explore More Education & Research Skills→
huidgehuidge
2

ocr-and-documents

Extract text from PDFs and scanned documents into Markdown.

Community
Advanced
cccnam5158cccnam5158
13

document-summary

Distill large documents into one-line, paragraph, and detailed summaries.

Community
Advanced
otrebuotrebu
4

scratchpad-fetch

Fetch multiple URLs with curl and aggregate content into a timestamped Markdown file.

Community
Basic
kngender5kngender5

ocr-and-documents

Extract text, tables, and equations from PDFs and scanned documents using OCR.

Community
Advanced