markitdown

Convert PDFs, Word, PowerPoint, Excel, HTML, CSV, JSON, XML, ZIP, EPUB, images, and URLs to Markdown.

1|Updated Mar 11, 2026
One-click install
npx skills add https://github.com/SciMate-AI/scicli --skill markitdown-scimate-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: markitdown
Source: https://github.com/SciMate-AI/scicli/tree/main/internal/skills/bundled/claude-scientific-skills/skills/markitdown
Command: npx skills add https://github.com/SciMate-AI/scicli --skill markitdown-scimate-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Convert documents from a wide range of formats into clean, machine-friendly Markdown to simplify downstream processing, search, and integration with AI models.

Core Features & Use Cases

  • Supports PDFs, DOCX, PPTX, XLSX, HTML, CSV, JSON, XML, ZIP, EPUB, YouTube URLs, images (with OCR), and more.
  • Maintains structure like headings, tables, lists, and metadata, enabling consistent reviews, notes, and AI-assisted analysis.
  • Real-world use cases include converting research papers for summarization, preparing technical documentation, and extracting data from spreadsheets for analysis.

Quick Start

Convert a sample document, such as document.pdf, to Markdown to observe the conversion 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 to Markdown for AI processing?

To convert PDF and Word documents to Markdown, you can use automatic format detection that transforms DOCX and PDF files into clean, machine-friendly text, streamlining extraction and integration with AI models.

What is the best way to extract tables and lists from Excel and PowerPoint into Markdown?

Extracting tables and lists from Excel and PowerPoint into Markdown preserves the original document structure, enabling consistent formatting for AI-assisted analysis and technical documentation preparation.

Can I convert images and YouTube URLs to Markdown using OCR?

Yes, you can convert images and multimedia URLs like YouTube to Markdown, using OCR capabilities and optional AI-assisted enhancements to extract text and metadata for downstream pipelines.

Does this document conversion approach support frontmatter metadata and automatic format detection?

Yes, document conversion supports automatic format detection for files like HTML, CSV, JSON, XML, ZIP, and EPUB, while maintaining frontmatter metadata to ensure uniform formatting across diverse inputs.

How do I process research papers and technical documentation into uniform Markdown formatting?

Processing research papers and technical documentation into uniform Markdown formatting standardizes headings, metadata, and structures, facilitating automated summarization, review, and search integration.

What are the limitations of converting complex XLSX and PPTX files to Markdown?

When converting complex XLSX and PPTX files to Markdown, limitations may arise with intricate layout fidelity, though the process maintains core structural elements like lists, tables, and metadata.