Markitdown-Skill-for-non-multimodal-agent

Use when a NON-multimodal agent (a text-only LLM backend that cannot read attachments) receives a document — PDF, Word (docx), PowerPoint (pptx), Excel (xlsx/xls), EPUB, HTML, CSV, JSON, XML, or ZIP — and you need its CONTENT to read, summarize, quote, or store it. The model can't open the file itself, so convert it to Markdown first with the markitdown MCP server (local, free, no API key). An OPTIONAL OCR layer reads scanned PDFs and images via an OpenAI-compatible vision model, but ONLY when a key is configured. Skip for files the agent can already read as plain text, and for plain images when no OCR key is set.

by @keepyaoung (Tommy, Joon Shin)·MIT-0