skills.rest
danieldekay
danieldekayCOMMUNITY
Explore all skills by this author →
GitHub

markitdown

Convert PDFs, Word, slides, spreadsheets, images, audio, HTML, and data formats into Markdown.

1|2|Updated Jan 7, 2026
Search Tags:#ocr#pdf#markdown#batch-processing#document-conversion#ai-descriptions
One-click install
npx skills add https://github.com/danieldekay/copilot-config-promptops --skill markitdown-danieldekay
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: markitdown
Source: https://github.com/danieldekay/copilot-config-promptops/tree/main/skills/markitdown
Command: npx skills add https://github.com/danieldekay/copilot-config-promptops --skill markitdown-danieldekay

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Converts diverse documents into clean, token-efficient Markdown, making content easier to read by humans and AI models.

Core Features & Use Cases

  • Batch convert a wide range of formats (PDF, DOCX, PPTX, XLSX, EPUB, images with OCR, audio transcripts, HTML, CSV, JSON, XML, ZIP, and YouTube transcripts) into Markdown.
  • AI-assisted extraction and description for visual content via OpenRouter/OpenAI integration and optional Azure Document Intelligence.
  • Automations and scripting support with batch processing to streamline scientific workflows and documentation.

Quick Start

Run a sample file through MarkItDown and review the resulting Markdown output.

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 into Markdown for AI ingestion?▼

You can convert PDFs, Word files, and other diverse formats into clean, token-efficient Markdown. This process makes the content easier to read by humans and optimizes it for AI model ingestion.

Can I extract text from images using OCR and generate Markdown?▼

Yes, images can be processed using OCR to extract text and convert it into Markdown. Optional AI-assisted extraction and description for visual content are also available via OpenRouter and OpenAI integration.

Does this document conversion tool support batch processing for multiple files?▼

Yes, the tool supports batch processing to streamline scientific workflows and documentation. It applies batch conversion across a wide range of formats including PDF, DOCX, PPTX, XLSX, and HTML.

Do I need an OpenAI API key to get AI descriptions for visual content?▼

Yes, AI-assisted extraction and description for visual content requires an OpenAI or OpenRouter integration. Azure Document Intelligence is also optionally supported for advanced document extraction.

What is the best way to convert audio transcripts and YouTube videos into Markdown?▼

The tool directly converts audio transcripts and YouTube transcripts into clean Markdown. This enables efficient processing and token-friendly ingestion of multimedia content alongside standard document formats.

What file formats are supported for converting to Markdown?▼

Supported formats include PDF, DOCX, PPTX, XLSX, EPUB, images, audio, HTML, CSV, JSON, XML, and ZIP files. These diverse documents are converted into token-efficient Markdown.

Related Skills

Explore More Education & Research Skills→
Victory-HugoVictory-Hugo
1

markitdown

Convert PDF, DOCX, PPTX, XLSX, and other documents to Markdown.

Community
Advanced
karrtik159karrtik159

rag-implementation

Build RAG systems with vector databases and semantic search.

Community
Advanced
paidethonpaidethon

azure-ai

Access Azure AI services including search, speech, OpenAI, document intelligence, and content safety.

Community
Advanced
samuelmukotisamuelmukoti

ocr-and-documents

Extract text from PDFs and documents using OCR and local parsers.

Community
Intermediate