Xlsx

Reach for this one when you need Claude to touch a spreadsheet and you care about the formulas surviving the edit. The big idea is that it pushes you toward live Excel formulas over Python-computed hardcodes, so a sum or growth rate stays updatable when the source data changes. It splits the work sensibly: pandas for reading and analysis, openpyxl for formulas and formatting, and a bundled recalc.py that runs LibreOffice to recalculate and report errors like #REF! or #DIV/0! as JSON. The financial-model conventions are opinionated, with blue inputs, black formulas, and zeros shown as dashes, so existing templates should win if you're editing one. My honest take: the recalc step is the part that earns its keep, since openpyxl alone will happily write formulas that are broken. You do need LibreOffice installed, which is the main setup friction.

GitHub stars: 1.4K
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add Prat011/awesome-llm-skills --skill xlsx --agent claude-code

Installs into .claude/skills of the current project.

Files

Requirements for Outputs

All Excel files

Zero Formula Errors

Every Excel model MUST be delivered with ZERO formula errors (#REF!, #DIV/0!, #VALUE!, #N/A, #NAME?)

Preserve Existing Templates (when updating templates)

Study and EXACTLY match existing format, style, and conventions when modifying files
Never impose standardized formatting on files with established patterns
Existing template conventions ALWAYS override these guidelines

Financial models

Color Coding Standards

Unless otherwise stated by the user or existing template

Industry-Standard Color Conventions

Blue text (RGB: 0,0,255): Hardcoded inputs, and numbers users will change for scenarios
Black text (RGB: 0,0,0): ALL formulas and calculations
Green text (RGB: 0,128,0): Links pulling from other worksheets within same workbook
Red text (RGB: 255,0,0): External links to other files
Yellow background (RGB: 255,255,0): Key assumptions needing attention or cells that need to be updated