MarkItDown Document Ingestion

When to use

Use this skill when a research task includes a document or file that should become readable Markdown before analysis:

• public PDFs, reports, whitepapers, policy files, manuals, or papers;
• DOCX / PPTX / XLSX files shared as research sources;
• HTML files, CSV, JSON, XML, EPUB;
• trusted small ZIP bundles of public documents after size/file-count inspection;
• source packs that need to feed a source ledger or research brief.

The goal is not to make the document “true”. The goal is to create a readable analysis copy, then run the normal research evidence gate.

Recommended local tool

Microsoft MarkItDown is the preferred lightweight converter when available: