markitdown

Convert PDFs, DOCX, PPTX, XLSX, HTML, CSV, JSON, XML, ZIP, EPUBs, images, and audio into Markdown.

Updated Feb 14, 2026
One-click install
npx skills add https://github.com/liutao96/skill --skill markitdown-liutao96
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: markitdown
Source: https://github.com/liutao96/skill/tree/main/markitdown
Command: npx skills add https://github.com/liutao96/skill --skill markitdown-liutao96

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Converting a wide variety of documents into consistent, Markdown-formatted text to enable easy ingestion by LLMs, repositories, and knowledge bases.

Core Features & Use Cases

  • Supports PDFs, DOCX, PPTX, XLSX, HTML, CSV, JSON, XML, ZIP, EPUBs, images (with OCR), and audio transcription.
  • Includes optional AI enhancements (image descriptions) and external services (Azure Document Intelligence, OpenRouter) for richer outputs.
  • Provides script-based batch processing and references for extended workflows, making it suitable for research, content teams, and data pipelines.

Quick Start

Convert a sample document such as sample.pdf to Markdown and review the output.

Frequently Asked Questions about markitdown

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

FAQPage Schema
How do I convert PDFs and DOCX files into Markdown for LLM ingestion?

MarkItDown converts PDFs and DOCX files into Markdown by extracting text and structure into consistent, token-efficient representations for AI workflows and knowledge bases. It supports script-based batch processing for large document pipelines.

Can I extract text from images using OCR and convert it to Markdown?

Yes, MarkItDown supports OCR for images to extract text and convert it into Markdown. It also offers optional AI-generated image descriptions to provide richer outputs for downstream AI workflows.

What document formats are supported for Markdown conversion?

MarkItDown supports PDFs, DOCX, PPTX, XLSX, HTML, CSV, JSON, XML, ZIP, EPUBs, images, and audio transcription. It converts these diverse formats into consistent Markdown-formatted text for easy ingestion.

Do I need Python to run document conversion tasks in batch pipelines?

Yes, MarkItDown requires Python to perform document conversion, extraction, and enhancement. It provides script-based batch processing and references for extended workflows, making it suitable for research and data pipelines.

Does MarkItDown work with Azure Document Intelligence for PDF conversion?

Yes, MarkItDown supports external services like Azure Document Intelligence and OpenRouter for richer outputs during PDF conversion. These optional cloud-assisted processing features enhance the extracted Markdown content.

What is the best way to automate XLSX and PPTX conversion for content teams?

MarkItDown provides script-based batch processing to automate XLSX and PPTX conversion into Markdown. This approach enables consistent, token-efficient representations suitable for research, content teams, and data pipelines.