Menu

Individual skill

spreadsheet-audit-live

0upvotes

Audit the user's REAL spreadsheet by opening it in the Cowork sandbox — not by reading a description of it. Use when asked to check this sheet before we present it, audit the model in my Drive, why don't these numbers add up, or is this spreadsheet safe to build on. Pulls the file via the Google Drive connector (or an uploaded .xlsx), opens it programmatically in the sandbox to trace formulas, hunts hardcodes / broken ranges / unit mixes, and produces a ranked findings artifact with a verified-vs-suspect ledger and a fix list.

skills/spreadsheet-audit-live/SKILL.md

Read pinned source

Source commit e0009a385c480fb0b5687e7412df67c7c64f7cee

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
No
Observed behavior
Not checked yet
Last checked
Nov 12, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
1,541
Repository last updated
Nov 11, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Spreadsheet Audit (Live)

Spreadsheets fail silently — the SUM that stops at row 40, the hardcoded 1.1 typed over a formula, the column that's monthly in one section and annual in another. In Claude Cowork this skill opens the *actual file* in the sandbox and traces the real formulas, so the mistake is caught before the meeting corrects it.

## What This Skill Produces

- **Findings ranked by damage** — each with cell location, what's wrong, and what it's currently mis-stating
- **The verified/suspect ledger** — which load-bearing outputs were traced clean and which remain unverified (unverified ≠ wrong; the label is the honesty)
- **The fix list** — ordered, with make-it-robust upgrades where they matter
- **A findings artifact** — the above as a shareable report, plus (on request) a corrected copy of the sheet

## Required Inputs

Ask for these if not provided:
Back to top