More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Excel Export Checker

    1

    Check any Excel or CSV export in seconds and see what's wrong with it before you use it. Free and read-only.

    Free

    1 useSecurity scanned
    Excel Export Checker

    Excel Export Checker

    Example session with this skill installed

    Check ventas_octubre.xlsx before I build the monthly report. Is it ok to use?

    • Read your context and instructions
    • Compiled the excel export checker

    ventas_octubre.xlsx scores

    24 out of 100, so it would give wrong totals if you used it as it is. (Demo data is fictitious.)

    The three things that matter most

    2,527 amounts are stored as text, like '833.247,77' in row 6. SUM and pivot tables skip them, so the totals come out low.
    2. There's a TOTAL GENERAL row at row 1215 mixed with the data. Any sum over the column counts it twice.
    3.

    The Fecha column mixes formats: 817 dates written with numbers (05/10/2026, 05.10.26) and 387 with the month in words (5-oct-2026), so sorting and filtering by date won't work.

    Also worth knowing: 259 cells have broken accents ('Carlos Peña'), 3 rows are exact duplicates, the header repeats 4 times inside the data, and there are 3 title rows above the real header on row 5. The NIT column has codes with leading zeros, so keep it as text.

    The file wasn't changed. You can fix these by hand, or I can clean it with Messy Excel Fixer if you have it.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Before you build a pivot or import an export into anything, it's worth knowing what's wrong with it. This skill reads the file and tells you, in plain words, with a score from 0 to 100.

    It looks for the things that quietly break totals: numbers stored as text that SUM skips, total rows mixed with the data, the header repeated after every page break, duplicates, dates in two or three formats, the decimal comma and dot mixed in one column, and accents broken by a bad export ("Peña" instead of "Peña"). Each problem comes with an example and the row where it is, so you can go straight to it.

    It only reads. Your file isn't changed, nothing gets uploaded, and there are no API keys.

    It was written with Latin American and European files in mind, where the decimal comma and dd/mm dates cause most of the trouble, but it works with any export from an ERP, bank, POS or accounting system.

    If the file needs fixing, the companion skill Messy Excel Fixer cleans it and checks the totals for you.

    It checks one sheet at a time and expects one table per sheet. It reads the values Excel last saved, not live formulas. Old .xls files need to be saved as .xlsx first.

    How to use

    1. 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. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 6 days ago

    • Free with an Agensi account

    Requires

    Python
    openpyxl for Excel files (pip install openpyxl)

    Permissions

    Terminal / Shell
    Read Files
    Listed6 days ago

    What's inside

    Frequently Asked Questions

    Numbers stored as text, total rows mixed with the data, repeated headers, duplicates, dates in more than one format, decimal comma and dot mixed in a column, broken accents, title rows above the header and extra spaces.

    No. It only reads. You get a report with the row of each problem, and you decide what to fix.

    Yes. One Python script and its instructions. It needs Python 3.9+ and, for Excel files, openpyxl.

    90 or more is ready to use. 60 to 89 needs a quick cleanup. Below 60, the totals will come out wrong if you use the file as it is.

    Save the .xls as .xlsx, and put each table on its own sheet. Then run it again.

    New in Finance & Accounting