document-converter

To convert a PDF to Markdown for research text extraction, you provide the document's absolute file URI or HTTP URL to the agent. The Skill uses Microsoft MarkItDown to transform the file into LLM-ready Markdown text while preserving structural elements like headings and sections.

Yes, you can extract tables and slide structures from XLSX and PPTX files into Markdown. The conversion process supports academic workflows including XLSX table ingestion and PPTX slide analysis, transforming structured Office documents into clean Markdown text for downstream analysis.

Yes, this document conversion tool requires Microsoft MarkItDown as a core dependency to function. It supports optional markitdown-mcp tool integration for MCP-based conversion workflows, and also provides a CLI fallback for straightforward batch or single-file processing.

The best way to extract Abstract and Methods sections from a research paper is to convert the document to Markdown first. By transforming the PDF into structured Markdown, you enable the agent to isolate specific sections and generate a study summary with integrated citations.

Supported file formats for converting documents to Markdown include PDF, DOCX, PPTX, XLSX, HTML, CSV, JSON, XML, and images. These formats are processed into Markdown text suitable for LLM consumption, preserving structural elements like lists and tables when possible.

Yes, you can use local files and HTTP URLs for document conversion to Markdown. The Skill accepts local absolute file:// URIs, such as file:///absolute/path/to/paper.pdf, as well as standard HTTP URLs to fetch and convert remote research documents.