skills.rest
hungthinh04
hungthinh04COMMUNITY
Explore all skills by this author →
GitHub

ocr-and-documents

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

Updated May 12, 2026
Search Tags:#ocr#pdf#text extraction#research papers#markdown conversion#document parsing#scanned documents
One-click install
npx skills add https://github.com/hungthinh04/Hermes_AI_Agent --skill ocr-and-documents-hungthinh04
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/hungthinh04/Hermes_AI_Agent/tree/main/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/hungthinh04/Hermes_AI_Agent --skill ocr-and-documents-hungthinh04

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

It removes the manual effort of pulling text from PDFs, scanned files, and mixed document formats so you can reuse the content immediately.

Core Features & Use Cases

  • Remote first: Prefers web-based extraction for document URLs, which is ideal for online reports and research papers.
  • Lightweight parsing: Uses pymupdf for fast text extraction, Markdown conversion, table reading, image export, and metadata inspection.
  • High-accuracy OCR: Uses marker-pdf for scanned documents, complex layouts, equations, forms, and multilingual OCR.
  • Document workflows: Supports splitting, merging, searching, and batch processing of document files for archival and research tasks.

Quick Start

Ask the skill to extract clean text or Markdown from the attached PDF or URL, using OCR only when the document is scanned or layout-heavy.

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 high-accuracy OCR, layout analysis, and multilingual text recognition. It automatically switches to OCR-heavy parsing when documents are scanned or layout-heavy.

Can I convert a research paper URL directly to Markdown?▼

Yes, you can convert a research paper URL to Markdown. The skill prefers web-based extraction for online files and uses pymupdf for fast Markdown conversion and metadata inspection.

What is the best way to parse tables and images from a local PDF file?▼

The best way to parse tables and images from a local PDF file is using lightweight parsing via pymupdf, which handles table reading, image export, and metadata inspection efficiently.

Does this tool support splitting, merging, and batch document conversion?▼

Yes, this tool supports splitting, merging, searching, and batch document conversion. These document workflows are designed for managing archival files and processing research tasks at scale.

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

You should use marker-pdf instead of pymupdf when handling scanned documents, complex layouts, equations, forms, or multilingual OCR. Pymupdf is reserved for fast text extraction and lightweight parsing.

Related Skills

Explore More Education & Research Skills→
attentiondotnetattentiondotnet

ocr-and-documents

Extract text from PDFs, DOCX, PPTX, and scanned documents via OCR.

Community
Intermediate
malue-aimalue-ai
36

raglite

Index local PDF, Markdown, and plain text documents into structured Markdown for semantic search.

Official
Intermediate
InverterNetworkInverterNetwork

ocr-and-documents

Extract text and structured data from PDFs and scanned images using OCR.

Official
Intermediate
heysuhasheysuhas
2

ocr-and-documents

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

Community
Intermediate