Top 200 ReposEXPLORERTurning PDFs, scans and office files into text and structured data agents can use.
Agent Mode in Excel plans formulas, sheets and charts from a prompt, checks and fixes its own results, and reports its validation steps; Microsoft reports 57.2% accuracy on SpreadsheetBench in its own evaluation.
Install Anthropic's xlsx skill in Claude Code so the agent writes live formulas, recalculates the workbook with LibreOffice and checks it for formula errors.
Run PaddleOCR's PP-StructureV3 pipeline on scans to recover layout, tables, formulas and reading order as Markdown or JSON.
Run MarkItDown on PDFs, Word, PowerPoint and Excel files to get structure-preserving Markdown an LLM can read cheaply.