markitdown

Convert documents, media, and archives into clean Markdown.

74|5|Updated Dec 10, 2025
One-click install
npx skills add https://github.com/dralkh/seerai --skill markitdown-dralkh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: markitdown
Source: https://github.com/dralkh/seerai/tree/main/skills/markitdown
Command: npx skills add https://github.com/dralkh/seerai --skill markitdown-dralkh

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

It removes the manual effort of turning scattered documents, media, and web content into clean Markdown that is easy to search, review, and reuse.

Core Features & Use Cases

  • Multi-format conversion: Convert PDFs, DOCX, PPTX, XLSX, images, audio, HTML, CSV, JSON, XML, ZIP archives, EPUBs, and YouTube transcripts into structured Markdown.
  • Research and literature workflows: Batch-convert paper collections, extract metadata, build indices, and organize outputs for systematic review or academic note-taking.
  • AI-enhanced document understanding: Add detailed image descriptions, OCR for scans, and transcription for audio to improve the quality of converted content.
  • Use case: A researcher can feed a folder of papers and slides into the skill, then receive searchable Markdown notes plus an organized catalog for downstream analysis.

Quick Start

Ask the skill to convert your attached document or folder of files into Markdown, and specify whether you want standard conversion, batch processing, or AI-enhanced descriptions.

Frequently Asked Questions about markitdown

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

FAQPage Schema
How do I convert PDF research papers to Markdown for literature reviews?

Batch document conversion tools convert PDF research papers to Markdown by parsing files and applying OCR to extract structured text. This skill processes collections of research papers and outputs clean Markdown notes with organized catalogs for systematic literature review.

Can I extract text from scanned PDF images using OCR for Markdown conversion?

Yes, you can extract text from scanned PDF images using OCR for Markdown conversion. The skill applies OCR to scanned documents and images, transforming them into searchable Markdown text. It also supports optional OpenRouter-based image description for enhanced document understanding.

Does this Markdown conversion tool support audio transcription and YouTube transcripts?

Yes, this Markdown conversion tool supports audio transcription and YouTube transcripts. It converts audio recordings and YouTube transcripts into structured Markdown, allowing you to integrate spoken content and video subtitles into your searchable research notes and literature review pipelines.

How do I batch convert DOCX, PPTX, and XLSX files into Markdown?

You can batch convert DOCX, PPTX, and XLSX files into Markdown by feeding a folder of mixed documents into the skill. It processes multi-format files, including presentations and spreadsheets, extracting content to build searchable Markdown notes and organized indices for downstream analysis.

Do I need an OpenAI API key to convert documents to Markdown?

You need an OpenAI API key or OpenRouter access to enable AI-enhanced document understanding, such as detailed image descriptions and audio transcription. Standard document conversion to Markdown can proceed, but AI-enhanced features require configuring your API keys in the environment.

What is the best way to convert ZIP archives and EPUBs to clean Markdown?

The best way to convert ZIP archives and EPUBs to clean Markdown is using a multi-format conversion tool that automatically parses archived and ebook files. This skill extracts content from ZIPs and EPUBs, structuring the text into editable Markdown for review and reuse.