skills.rest
Hongyu-yu
Hongyu-yuCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

markitdown

Converts documents, images, and audio/video transcripts to Markdown via OCR and parsers.

16|Updated Dec 28, 2025
Search Tags:#pdf#markdown#xlsx#pptx#docx#ai-enhanced#file-conversion
One-click install
npx skills add https://github.com/Hongyu-yu/matsci-ai-skills --skill markitdown-hongyu-yu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: markitdown
Source: https://github.com/Hongyu-yu/matsci-ai-skills/tree/main/skills/markitdown
Command: npx skills add https://github.com/Hongyu-yu/matsci-ai-skills --skill markitdown-hongyu-yu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires markitdown, openai, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

MarkItDown streamlines the conversion of diverse file formats into Markdown to create token-efficient, AI-ready content for research, documentation, and collaboration.

Core Features & Use Cases

  • AI-enhanced image descriptions for figures and diagrams using OpenRouter
  • Azure Document Intelligence integration for complex PDFs
  • Batch processing with parallel conversion of many files
  • Literature conversion with metadata extraction and index generation
  • Broad format support: PDF, DOCX, PPTX, XLSX, EPUB, images, audio, HTML, CSV, JSON, XML, ZIP, YouTube transcripts
  • Plugin system and extensible converters

Quick Start

Install MarkItDown with all features and run a simple conversion to Markdown, for example converting a sample.pdf with MarkItDown.

Frequently Asked Questions about markitdown

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert PDF and Word documents to Markdown for AI processing?▼

Converting PDF and Word documents to Markdown is automated by transforming diverse file formats into clean, searchable text. This skill handles DOCX and PDF conversion into token-efficient Markdown, creating AI-ready content for research and documentation workflows.

Can I extract text from images and audio files using OpenAI integration?▼

Extracting text from images and audio files using OpenAI integration is supported through AI-enhanced image descriptions via OpenRouter and audio transcript conversion. The skill transforms visual and audio content into structured Markdown for data extraction workflows.

What is the best way to batch convert Excel and PowerPoint files to Markdown?▼

Batch converting Excel and PowerPoint files to Markdown is best handled through parallel processing capabilities. This skill supports batch conversion of XLSX and PPTX files, streamlining the transformation of multiple spreadsheets and slides into Markdown simultaneously.

Does Azure Document Intelligence work for converting complex PDFs to Markdown?▼

Azure Document Intelligence works for converting complex PDFs to Markdown through direct integration. The skill leverages Azure DI to handle intricate PDF structures, ensuring accurate text extraction and formatting when standard conversion methods are insufficient.

What file formats are supported when converting documents to Markdown?▼

Supported file formats for converting documents to Markdown include PDF, DOCX, PPTX, XLSX, EPUB, HTML, CSV, JSON, XML, and ZIP archives. The skill also handles images, audio, video transcripts, and YouTube transcripts for comprehensive content conversion.

Do I need Python 3.10 or higher to run file conversion to Markdown?▼

Python 3.10 or higher is required to run file conversion to Markdown. The skill requires Python 3.10+ and may need optional format-specific dependencies to process certain file types like PDFs, spreadsheets, or audio files correctly.

Related Skills

Explore More Content & Communication Skills→
exiaoexiao
37

documents

Manage and process DOCX, PDF, PPTX, and XLSX office documents.

Community
Advanced
shynlee04shynlee04

web-search

Search the web and extract content via Tavily and Exa using the inference.sh CLI.

Community
Intermediate
trungkiet2005trungkiet2005

markitdown

Convert diverse document formats to Markdown for AI processing.

Community
Advanced
ajithkumar31082004-bitajithkumar31082004-bit

doc-reader

Extract text from PDFs, Office files, images, and code into a structured JSON envelope.

Community
Intermediate