Open Skills Logo
Open Skills

markitdown

Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more.

Author

@K-Dense-AI

Category

Document Processing

Install

Hot:75

Download and extract to your skills directory

Copy command and send to AI Agent for auto-install:

Download and install this skill https://openskills.cc/api/download?slug=k-dense-ai-skills-markitdown&locale=en&source=copy

MarkItDown - Multi-format Document to Markdown Tool

Overview of Skills


MarkItDown is a Python tool developed by Microsoft that converts 15+ file formats—including PDFs, Office documents, images, audio, and more—into Markdown. It offers OCR recognition, AI image descriptions, and speech-to-text transcription.

Use Cases

1. Processing Scientific Literature


Researchers can convert academic papers in PDF format to Markdown to make it easier to perform literature reviews and content analysis with AI tools. Markdown is more friendly to LLMs, effectively reducing token usage.

2. Batch Document Conversion


Developers can process large numbers of Word, Excel, and PowerPoint files in bulk, converting them into Markdown for building knowledge bases, generating documentation websites, or preparing AI training data.

3. Extracting Multimedia Content


Extract OCR text from images, obtain transcripts from audio files, and capture subtitles from YouTube videos. Suitable for content creators, analysts, and users who need to process multimedia materials.

Core Features

1. Multi-format Document Conversion


Supports one-click conversion of many file formats including PDF, DOCX, PPTX, XLSX, HTML, CSV, JSON, XML, ZIP, EPUB, and more—preserving the original document’s table structure, formatting, and metadata.

2. AI-Enhanced Image Processing


Integrates the OpenRouter API to generate detailed AI descriptions for PPTX slides and images. Ideal for presentation decks and technical documents containing many charts and visualizations.

3. Intelligent Content Extraction


  • OCR Recognition: Extract text from scanned PDFs and images

  • Audio Transcription: Convert audio files such as WAV and MP3 into text

  • Video Subtitles: Directly retrieve video transcription text from a YouTube URL

    • Frequently Asked Questions

    What file formats does MarkItDown support?


    MarkItDown supports 15+ file formats, including PDF, Word (DOCX), Excel (XLSX), PowerPoint (PPTX), HTML, CSV, JSON, XML, images (JPEG, PNG, GIF, WebP), audio (WAV, MP3), ZIP archives, EPUB e-books, and YouTube video subtitles retrieved via URL.

    How do I use the AI-enhanced features?


    The AI image description feature requires an OpenRouter API key. In Python code, initialize MarkItDown with an OpenAI-compatible client and specify the llm_client, llm_model, and llm_prompt parameters. Using a Claude model is recommended for more accurate scientific and technical image descriptions.

    Is MarkItDown a free tool?


    Yes. MarkItDown uses the MIT open-source license and is completely free to use. However, AI-enhanced features (such as image description) require calling the OpenRouter API, which incurs corresponding API call costs depending on the chosen model and number of calls.