- Home
- Skills
- Finance & Accounting
- Spreadsheet Formula Audit Fix
More screenshots
Works with the AI Agents you already use
Spreadsheet Formula Audit Fix
Audit a spreadsheet's formulas, find the silent errors, and fix them safely.
$5
Spreadsheet Formula Audit Fix
Example session with this skill installed
Apply the skill to this case: A pricing spreadsheet inherited from a former colleague produced quotes that were sometimes a few percent off, but no one could say why.
- Read your context and instructions
- Compiled the spreadsheet formula audit
Situation: A pricing spreadsheet inherited from a former colleague produced quotes that were sometimes a few percent off, but no one could say why. Evidence: The audit found 214 formulas, 38 containing hard-coded numbers, and a sum range that missed the last two rows added that month. One lookup used an approximate match on unsorted data, so some prices matched the wrong tier. Decision: Replace hard-coded numbers with input cells, extend the sum range, change the lookup to an exact match, and add control totals comparing quote totals to the sum of line items. Outcome: Quotes matched the independent calculation exactly on all tests, and the control totals now fail loudly if a future row falls outside a range. The owner approved two corrected historical quotes found by the audit.
Connects securely to your tools. The creator never sees your data.
About this skill
Spreadsheet errors are usually silent: a hard-coded number inside a formula, a range that misses new rows, a lookup that returns the wrong match, or a copied formula that drifted by one column. The total still looks plausible. This skill inventories every formula, tests each type of risk, fixes the worst risks with traceable changes, and leaves a file whose formulas can be checked by someone else. This skill gives you a counted diagnosis, a decision table, a fill-in template, a checklist, and a scoring rubric, plus a runnable script (formula_audit.py) that Scans a CSV export of formulas for hard-coded numbers, error values, and approximate-match lookups, reports the hard-coded share against the 5 percent systematic-fix trigger, and writes an audit report. It is built for the bottleneck moment: when the usual quick fix has already failed, or when a silent failure is worse than a loud one. Follow the protocol in order, record numbers rather than impressions, and use the quality gate before you call the work done.
Results depend on the quality of your evidence set: a partial formula export, missing input cells, or totals no one can trace will limit the diagnosis, and the skill says so rather than filling gaps with guesses. The script is a helper for counting and reporting; it does not replace judgement about safety, permission, or whether a fix is correct. Thresholds are starting points to adapt to your context, not universal constants.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 23 days ago