office-to-md

The office-to-md skill converts Office and document files into clean Markdown using markitdown, Microsoft’s open-source document-to-Markdown conversion tool. It solves the problem of making content from formats like Word, Excel, PowerPoint, PDF, HTML, images, audio, and ZIP archives easier to search, version control, reuse, and process with AI systems. By transforming rich document formats into Markdown, the skill helps users extract readable text and structured content from files that are otherwise harder to inspect or manage programmatically.

Its main capabilities include Office document conversion and Markdown export. The skill supports Word documents with text, tables, headings, lists, hyperlinks, and basic formatting; Excel spreadsheets converted into Markdown tables; PowerPoint presentations represented as slide-based sections; PDFs with text extraction; HTML converted into clean Markdown; images with OCR through a vision model; audio transcription; and ZIP files containing processable documents. It can be used through the markitdown Python API or command-line interface, and it integrates with the office-mcp server through the docx_to_md tool.

This skill is useful for anyone who needs to extract, archive, review, or transform document content into a lightweight text format. Typical users include technical writers, analysts, researchers, developers, operations teams, and AI workflow builders who want to convert Office files into Markdown notes, documentation, tables, searchable text, or AI-friendly inputs. It is especially helpful when preparing documents for documentation pipelines, knowledge bases, source control, or downstream language-model processing.