XLSX — Excel Workbook Creation, Editing & Analysis
Builds Excel workbooks with live formulas and professional formatting, then verifies every formula with a LibreOffice recalculation pass.
What it does
This skill kicks in whenever the deliverable is a spreadsheet file (.xlsx, .xlsm, .xltx, or CSV/TSV destined for Excel). Claude writes formulas, formatting, and multi-sheet structures with openpyxl, moves bulk data with pandas, and previews existing sheets with markitdown.
The standout piece is verification. openpyxl writes formulas without cached values, so the bundled scripts/recalc.py runs the file through LibreOffice, rewrites it in place, and returns JSON with total_formulas, total_errors, and the exact cells that failed. The skill forbids shipping a workbook while errors_found is reported — and warns that a clean recalc proves formulas evaluate, not that they're correct.
It also encodes hard-won practical rules: which post-2007 functions need the _xlfn. prefix, which array functions (XLOOKUP, FILTER, UNIQUE, SORT, SEQUENCE) to avoid entirely, merged-cell write rules, keep_vba=True for macros, external-link data loss, and a full finance-model style guide (blue inputs, black formulas, $#,##0, percentages stored as fractions).
Who it's for
- Financial analysts building forecasts, DCFs, and budget models
- Accountants and planners who need live formulas instead of hardcoded numbers
- Data folks turning raw CSVs into polished, shareable Excel deliverables
- Anyone tired of AI-generated spreadsheets full of
#NAME?cells
Examples
- Build a model: "Create a 5-year revenue forecast with growth rates in dedicated assumption cells." → Blue input cells, black formula cells,
$#,##0currency formats, verified by recalc. - Edit an existing file: "Update only the yellow input cells in this budget workbook." → Existing formulas and conventions are preserved untouched.
- Clean and export: "Merge these three CSVs into a multi-sheet workbook and add SUMIFS totals at the bottom of each sheet."
· · · Install guide · · ·
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on Claude Skill Mart. Copy the skills/xlsx folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/k-dense-ai-xlsx/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/sas && mkdir -p ~/.claude/skills && cp -r /tmp/sas/skills/xlsx ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Open your terminal.
- Create the skills directory:
mkdir -p ~/.claude/skills - Clone the repository:
git clone https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/sas - Copy just this skill:
cp -r /tmp/sas/skills/xlsx ~/.claude/skills/ - Check prerequisites: Python 3.8+ and LibreOffice. Verify with
soffice --version(macOS:brew install --cask libreoffice; Ubuntu:sudo apt install libreoffice). - Install Python packages if any import fails:
pip install openpyxl pandas markitdown - Restart Claude Code and try a prompt like "Build me an Excel model projecting 5 years of revenue."
- Review LICENSE.txt inside the skill folder — it is proprietary — before any commercial use.