{"skill":{"slug":"markdown-converter","displayName":"Markdown Converter","summary":"Convert documents and files to Markdown using markitdown. Use when converting PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx, .xls), HTML, CSV, JSON, XML, images (with EXIF/OCR), audio (with transcription), ZIP archives, YouTube URLs, or EPubs to Markdown format for LLM processing or text analysis.","description":"---\nname: markdown-converter\ndescription: Convert documents and files to Markdown using markitdown. Use when converting PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx, .xls), HTML, CSV, JSON, XML, images (with EXIF/OCR), audio (with transcription), ZIP archives, YouTube URLs, or EPubs to Markdown format for LLM processing or text analysis.\n---\n\n# Markdown Converter\n\nConvert files to Markdown using `uvx markitdown` — no installation required.\n\n## Basic Usage\n\n```bash\n# Convert to stdout\nuvx markitdown input.pdf\n\n# Save to file\nuvx markitdown input.pdf -o output.md\nuvx markitdown input.docx > output.md\n\n# From stdin\ncat input.pdf | uvx markitdown\n```\n\n## Supported Formats\n\n- **Documents**: PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx, .xls)\n- **Web/Data**: HTML, CSV, JSON, XML\n- **Media**: Images (EXIF + OCR), Audio (EXIF + transcription)\n- **Other**: ZIP (iterates contents), YouTube URLs, EPub\n\n## Options\n\n```bash\n-o OUTPUT      # Output file\n-x EXTENSION   # Hint file extension (for stdin)\n-m MIME_TYPE   # Hint MIME type\n-c CHARSET     # Hint charset (e.g., UTF-8)\n-d             # Use Azure Document Intelligence\n-e ENDPOINT    # Document Intelligence endpoint\n--use-plugins  # Enable 3rd-party plugins\n--list-plugins # Show installed plugins\n```\n\n## Examples\n\n```bash\n# Convert Word document\nuvx markitdown report.docx -o report.md\n\n# Convert Excel spreadsheet\nuvx markitdown data.xlsx > data.md\n\n# Convert PowerPoint presentation\nuvx markitdown slides.pptx -o slides.md\n\n# Convert with file type hint (for stdin)\ncat document | uvx markitdown -x .pdf > output.md\n\n# Use Azure Document Intelligence for better PDF extraction\nuvx markitdown scan.pdf -d -e \"https://your-resource.cognitiveservices.azure.com/\"\n```\n\n## Notes\n\n- Output preserves document structure: headings, tables, lists, links\n- First run caches dependencies; subsequent runs are faster\n- For complex PDFs with poor extraction, use `-d` with Azure Document Intelligence\n","tags":{"latest":"1.0.0"},"stats":{"comments":1,"downloads":42944,"installsAllTime":506,"installsCurrent":505,"stars":183,"versions":1},"createdAt":1767651965151,"updatedAt":1778485729679},"latestVersion":{"version":"1.0.0","createdAt":1767651965151,"changelog":"","license":null},"metadata":null,"owner":{"handle":"steipete","userId":"s179zksw999xz8ms4cy7pb2fr183m5jq","displayName":"Peter Steinberger","image":"https://avatars.githubusercontent.com/u/58493?v=4"},"moderation":null}