Skip to content
cccskills
FreePublished on GitHub

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.

The English summary is being prepared. Showing the original description.

Works withExcel

Run score Not tested

See how to install

Files included (4)

  • SKILL.md6.9 KB
  • assets/workbook_handoff_checklist.md2.0 KB
  • references/financial_model_audit_guide.md5.2 KB
  • scripts/xlsx_auditor.py7.8 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Xlsx Toolkit

Audit .xlsx files using the standard library only — no openpyxl required. Reads OOXML directly via zipfile + xml.etree.


Table of Contents


Keywords

xlsx, Excel, spreadsheet, workbook, financial model, formula audit, hidden sheets, external references, named ranges, data validation


Clarify First

Before running the audit, settle the inputs below. When one is missing or vague and would change the result, ask about it; when it wouldn't, use a sensible default and say which one you used.

  • 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.

Ask about the two or three inputs that matter most for this request, not the whole list. If the user wants a result straight away, produce it and state your assumptions at the top.

Quick Start

python scripts/xlsx_auditor.py model.xlsx

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. Sheets with formula density > 70% are calculation sheets; should be well-structured
  3. Sheets with formula density 0-10% are inputs; should be obviously labeled
  4. Sheets with formula density 10-70% are mixed — easiest place for errors to hide
  5. Cross-reference with references/financial_model_audit_guide.md

Time Estimate: 30-60 minutes per model audit (audit + targeted reading).

Workflow 3: Workbook Handoff Check

Goal: Ensure a workbook handed off to another team or partner won't break on their machine.

Steps:

  1. Run audit
  2. External links → re-link to shared paths (OneDrive, SharePoint, S3) or hard-code values
  3. Custom named ranges → document if recipient is expected to extend; remove if internal
  4. Macros (xlsm) → audit shows non-.xlsx extension expected; convert if recipient cannot run macros
  5. File size > 10 MB → consider splitting or removing image / chart blobs

Time Estimate: 10-20 minutes per workbook.


Tools

xlsx_auditor.py

Reads a .xlsx file as a ZIP archive and parses OOXML directly.

python scripts/xlsx_auditor.py model.xlsx
python scripts/xlsx_auditor.py model.xlsx --json

Reports:

  • Sheet list with name, hidden status, cell count, formula count, formula density %
  • Total cell and formula counts
  • Named ranges and their scopes
  • External link references (file paths or URLs)
  • Data validation rule count
  • File size

Limits:

  • Does not evaluate formulas. To check whether formulas are correct, use Excel itself or a financial-model-checker library.
  • Does not read cell values for non-shared-string cells beyond counting; full value extraction requires more parsing than this tool does.

Reference Guides

  • references/financial_model_audit_guide.md — Patterns for auditing financial models; common error categories; defensive structure tips

Templates

  • assets/workbook_handoff_checklist.md — Pre-send xlsx sign-off checklist

Best Practices

  • Hide internal-only sheets only when intended. If a sheet is hidden because it's WIP, delete it before sending.
  • Avoid external links across handoffs. A formula referencing 'C:\Users\you\Desktop\old-model.xlsx' is the workbook equivalent of leaving your laptop name in the document author field.
  • Name your inputs. Cells like Inputs!B7 mean nothing. Named ranges like WACC and RevenueGrowth survive structural changes.
  • One model, one purpose. Workbooks that calculate, present, and serve as a database of records always end up broken.

Scope & Limitations

In Scope:

  • Read-only audit of .xlsx files with scripts/xlsx_auditor.py, which parses OOXML with zipfile and xml.etree and needs no openpyxl
  • Per-sheet name, hidden status, cell count, formula count and formula density, plus named ranges, external link references, data validation rule count and file size
  • Three workflows: pre-send audit, financial model review, and workbook handoff check
  • A financial model audit guide covering structure, formula and value layers, common error categories and defensive model structure

Out of Scope:

  • Calculating or checking formula results; the tool counts formulas but does not evaluate them
  • Editing workbooks, fixing links or removing hidden sheets; the tool only reads
  • Building or reviewing the financial analysis itself (see finance/financial-analyst/)
  • Analysing the data held in the workbook (see data-analytics/data-analyst/)

Important Caveats:

  • A clean audit says nothing about whether the numbers are right. The guide's spot-checks and reconciliation still need a person.
  • The tool does not extract full cell values, so it cannot find hardcoded numbers inside formula ranges or wrong inputs.
  • Formula-density bands (under 10 percent, 10 to 70 percent, over 70 percent) are a heuristic for where to look first, not a classification of the sheet.

Integration Points

  • Pairs with finance/ skills for financial-model review
  • Pairs with c-level-advisor/cfo-advisor for board-pack workbook review
  • Used by data-analytics/ for ad-hoc analytics handoff

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

This skill should be used when the user asks to "check accessibility", "audit WCAG compliance", "scan HTML for a11y issues", "check color contrast", or "find accessibility violations in web pages".

The English summary is being prepared. Showing the original description.

borghei/Claude-Skills971Updated Oct 23, 2026

Design and analyze A/B tests: sample size, test duration, and statistical significance for conversion experiments. Use when setting up an A/B test, calculating sample size, designing an experiment, or analyzing results.

The English summary is being prepared. Showing the original description.

borghei/Claude-Skills971Updated Oct 23, 2026

Design and run statistically rigorous A/B tests and experiments. Use when planning experiments, calculating sample sizes, designing test variants, selecting metrics, analyzing results, or when someone says "let's test that."

The English summary is being prepared. Showing the original description.

borghei/Claude-Skills971Updated Oct 23, 2026

Sales execution across pipeline, discovery, demos, negotiation, and closing. Use when qualifying opportunities, running MEDDIC discovery, building account plans, handling objections, structuring proposals, or forecasting pipeline.

The English summary is being prepared. Showing the original description.

borghei/Claude-Skills971Updated Oct 23, 2026

Design ad creative across Google, Meta, LinkedIn, Twitter/X, and TikTok with platform format specs, headline formulas, and A/B testing. Use when writing ad copy, generating headline variations, creating ad sets, or validating creative.

The English summary is being prepared. Showing the original description.

borghei/Claude-Skills971Updated Oct 23, 2026

aeo

Free

Answer Engine Optimization (AEO): optimize content to be cited by LLMs (ChatGPT, Claude, Perplexity, Gemini) in their answers. Use when designing content for LLM citation, auditing citability, or structuring Q&A schema.

The English summary is being prepared. Showing the original description.

borghei/Claude-Skills971Updated Oct 23, 2026

See all skills by borghei

Report a problem with this skill