← ClaudeAtlas

docs-convert-markitdownlisted

Use when converting documents to Markdown for LLM use - PDF, DOCX, PPTX, XLSX, images, scanned or tesseract or OCR needs, audio transcription, HTML, CSV, JSON, XML, ZIP, EPUB, or YouTube URLs. markitdown runs no local OCR and installing tesseract does not change that, so this names what to reach for instead.
bitranox/bitranox-skills · ★ 1 · Data & Documents · score 57
Install: claude install-skill bitranox/bitranox-skills
# MarkItDown - File to Markdown Conversion > Adapted from the MarkItDown skill in K-Dense-AI/claude-scientific-skills (MIT). See THIRD_PARTY_NOTICES.md. ## Overview MarkItDown is a Python tool developed by Microsoft for converting various file formats to Markdown. It's particularly useful for converting documents into LLM-friendly text format, as Markdown is token-efficient and well-understood by modern language models. **Key Benefits**: - Convert documents to clean, structured Markdown - Token-efficient format for LLM processing - Supports 15+ file formats - Optional AI-enhanced image descriptions - Scanned-document text via Azure Document Intelligence (a remote service); markitdown itself runs no local OCR - Speech transcription for audio files ## Supported Formats | Format | Description | Notes | |-------------|--------------------------|------------------------------------------| | **PDF** | Portable Document Format | Full text extraction | | **DOCX** | Microsoft Word | Tables, formatting preserved | | **PPTX** | PowerPoint | Slides with notes | | **XLSX** | Excel spreadsheets | Tables and data | | **Images** | JPEG, PNG, GIF, WebP | EXIF metadata + optional LLM description | | **Audio** | WAV, MP3 | Metadata + transcription | | **HTML** | Web pages