Analyzing Spreadsheets

Built for when you need to generate, modify, or analyze Excel files programmatically without breaking formulas. Uses pandas for data operations and openpyxl for preserving formatting and Excel-specific features. The standout requirement is zero formula errors at delivery, enforced through mandatory recalculation with LibreOffice after any formula changes. Follows strict financial modeling conventions for color coding and structure. Good for automating spreadsheet workflows where you need the output to actually work when someone opens it in Excel, not just technically valid XLSX files full of #REF! errors. Explicitly scoped to spreadsheets only, so don't reach for this when you're dealing with Word docs or PDFs.

install copies · 90 days. Times the install command was copied on this site in the last 90 days, bots filtered.: 52
GitHub stars: 224
last updated: Jun 10, 2026

View on GitHub

Install

$ npx -y skills add telagod/code-abyss --skill analyzing-spreadsheets --agent claude-code

Installs into .claude/skills of the current project.

Files

XLSX Processing

Create, edit, analyze .xlsx files. LibreOffice required for formula recalculation via recalc.py.

Iron Rule

Zero formula errors at delivery. All formulas must compute — no #REF!, #DIV/0!, #VALUE!, #N/A, #NAME?. Always run recalc.py after writing formulas.

Decision Matrix

Task	Tool	Reference
Data analysis, bulk ops, simple export	pandas	recipes.md
Formulas, formatting, Excel features	openpyxl	recipes.md
Financial model standards	—	financial-model.md
Recalculate formulas	`recalc.py`	recipes.md

Common Workflow

Choose tool: pandas for data, openpyxl for formulas/formatting
Create/Load workbook
Modify data, formulas, formatting
Save
Recalculate (MANDATORY if formulas): python recalc.py output.xlsx
Verify & fix errors — check JSON output, fix #REF! / #DIV/0! / #VALUE! / #NAME?