Convert Excel spreadsheets to LLM-friendly text

The specific problem with Excel spreadsheets

A grid has no reading order, so flattening it is a lossy act. Two things disappear by default: the sheet and header labels that tell you what a number means, and the formulas, which export as computed values so the reasoning behind each figure is gone.

• Label every sheet and repeat the header row, so a value is never presented without the column it belongs to.
• Export formulas alongside values when the logic matters, not just the result.
• Trim to the used range. Trailing empty rows and columns consume tokens and tell the model nothing.
• Watch the width. A wide sheet consumes budget faster than any other format, because every row repeats every column.

What LLM-friendly text means

LLM-friendly text is not just extracted text. It is labeled, grouped, and ordered so the model can tell where each section came from and how it relates to the task.

Riflet focuses on building that context file from mixed sources, not only converting one isolated file.

Workflow

Use the conversion as part of a complete context bundle.

• Add your Excel spreadsheets to Riflet.
• Add supporting notes, briefs, or source files if they explain the document.
• Remove sections that do not matter for the question.
• Export Markdown or text for your AI tool.

Quality checks

AI is best at reasoning over spreadsheet text and structure, not recalculating a workbook as a spreadsheet engine.

After export, skim the headings and source boundaries. The best bundle should make sense to a human before it goes to an AI.