Agent skill · data analytics · borghei
xlsx-toolkit
Audit Microsoft Excel (.xlsx) workbooks for formula density, external references, named ranges, hidden sheets, and data validation. Use when reviewing a financial model, sharing a workbook externally, or checking for data leakage.
Why this skill is useful
Provides domain-specific knowledge for auditing Excel workbooks that the AI wouldn't reliably generate on its own.
What it needs
Requires python installed locally. About 3k tokens when loaded. Last updated 2026-07-21. 462 stars on the source repository.
What this skill does
Xlsx Toolkit Audit .xlsx files using the standard library only — no openpyxl required. Reads OOXML directly via zipfile + xml.etree. --- Table of Contents Keywords Quick Start Core Workflows Tools Reference Guides Templates Best Practices --- Keywords xlsx, Excel, spreadsheet, workbook, financial model, formula audit, hidden sheets, external references, named ranges, data validation --- Clarify First Before running the audit, confirm these inputs. If any is unknown or vague, ASK — do not assume: [ ] Audit purpose (pre-send leak check, financial-model review, or handoff portability check) — selects the workflow and what you flag [ ] Recipient context (external partner, another team, their machine) — sets the tolerance for hidden sheets and external links [ ] Which sheets are inputs vs calculations (for model review) — drives where to focus formula-density reading Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact. Quick Start Outputs: sheet count and names, hidden-sheet count, cell count per sheet, formula count per sheet, external link count, named range count, data validation rule count. --- Core Workflows Workflow 1: Pre-Send Workbook Audit Goal: Catch the issues that embarrass the sender — leftover hidden sheets, broken external links, unused named ranges, formulas referencing local file paths. Steps: 1. Run audit 2. Hidden sheets > 0 → confirm intentional or delete 3. External links > 0 → verify links point to public / shared sources, not your local drive 4. Named-range count anomalies (very high) → likely cruft from prior model versions; clean up 5. Re-run until clean Time Estimate: 5-10 minutes per workbook. Workflow 2: Financial Model Review Goal: Quantify the rough complexity of a financial model before reading cell-by-cell. Steps: 1. Run audit; capture per-sheet cell counts and formula counts 2. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills borghei/xlsx-toolkit