xlsx Skill
Skill Claude Code Documents & Content CreationThe explanation below is AI-generated. Please verify it against the sources.
xlsx is a Claude skill that should be triggered whenever a spreadsheet file (.xlsx, .xlsm, .csv, .tsv) is the primary input or output — including opening, editing, fixing, creating, or converting such files, or cleaning up messy tabular data. According to the SKILL.md, it is not meant to be used when the deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration. The skill provides detailed workflows using pandas for data analysis and openpyxl for formulas/formatting, plus a recalc.py script (requiring LibreOffice) to recalculate formulas and detect Excel errors such as #REF!, #DIV/0!, #VALUE!, #N/A, and #NAME?. It also defines output requirements, including professional fonts, zero formula errors, preservation of existing template conventions, and — for financial models — specific color-coding and number-formatting standards. The SKILL.md emphasizes using live Excel formulas (with cell references to assumption cells) rather than hardcoding Python-calculated values into cells.
Overview
This is not a standalone SaaS product; it is a skill definition (SKILL.md) intended for use by an AI agent (Claude) to guide how it creates, edits, and analyzes spreadsheet files using Python libraries (pandas, openpyxl) and a LibreOffice-based recalculation script.
What you can do with xlsx
- Open, read, edit, or fix existing .xlsx, .xlsm, .csv, or .tsv files (e.g., add columns, compute formulas, format, chart, clean messy data)
- Create a new spreadsheet from scratch or from other data sources
- Convert between tabular file formats
- Restructure messy tabular data (malformed rows, misplaced headers, junk data) into a proper spreadsheet
- Use pandas for reading, analyzing, and bulk-exporting spreadsheet data
- Use openpyxl for formulas, formatting, and Excel-specific features, while keeping calculations as live formulas rather than hardcoded values
- Recalculate formulas and detect Excel errors (#REF!, #DIV/0!, #VALUE!, #N/A, #NAME?) with scripts/recalc.py (requires LibreOffice)
- Apply output requirements such as a consistent professional font, zero formula errors, and preservation of existing template conventions
- Apply financial-model conventions for financial spreadsheets: color coding (blue=hardcoded inputs, black=formulas, green=intra-workbook links, red=external links, yellow=key assumptions) and number formats (currency, percentages, negative numbers in parentheses, multiples as 0.0x, years as text)
Sources
Original description (English)
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
History of xlsx
- Skill Added xlsx