Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Spreadsheet Edit Check: Did Any Formulas Get Lost?

    1

    Use after an agent edits or exports an Excel workbook. Compares original and edited formulas, follows row moves, and reports formulas replaced by values, broken references and stale totals.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Spreadsheet Edit Check: Did Any Formulas Get Lost?

    Spreadsheet Edit Check: Did Any Formulas Get Lost?

    Example session with this skill installed

    Verify the formula preservation in 'Financial_Model_v2.xlsx' after the Q4 row insertions. Compare it against the v1 baseline.

    • Read your context and instructions
    • Compiled the spreadsheet edit check
    • Generated the document

    I have completed the formula preservation audit for Financial_Model_v2.xlsx. The checklist below itemizes the mapping from the v1 baseline to the current version, identifying one anomaly where a formula was replaced by a constant.

    Formula Preservation Checklist

    Version and Scope

    • Original: Financial_Model_v1.xlsx
    • Derived Copy: Financial_Model_v2.xlsx
    • Worksheets: Operating_Expenses, Revenue_Projections
    • Allowed Edit Area: Rows 45-60 in Operating_Expenses (Row insertions)

    Original Formula Baseline

    WorksheetOriginal AddressFormula TextMapped AddressComparison Result
    Operating_ExpensesB12=SUM(B2:B11)B12Passed
    Operating_ExpensesB62=SUM(B15:B61)B77Passed (Ref Adjusted)
    Revenue_ProjectionsC10=C8*Global_Tax_RateC10Anomaly: Constant
    Revenue_ProjectionsD5#=UNIQUE(A5:A20)D5#Passed (Spill Range)

    Summary

    • Original Formula Count: 42
    • Mapped Count: 41
    • Anomaly Count: 1 (Formula lost to constant in Revenue_Projections!C10)
    • Unchecked Scope: 0 cells

    Calculation State

    • Recalculation Engine: Excel Internal
    • Engine Status: Not triggered during audit
    • Cache Source: Local File Cache
    • Freshness: Stale (Manual calc mode detected)

    Next step
    Restore the formula =C8*Global_Tax_Rate to cell C10 in Revenue_Projections to resolve the detected anomaly.

    Preservation Status: FAILED (1 anomaly remains)

    Financial_Model_v2.xlsx

    PDF · document

    Generated

    Example file from a real run - the skill writes it into your workspace.

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

    About this skill

    Editing spreadsheets with complex logic often leads to broken references or formulas accidentally converted to static values. This skill enforces a rigorous verification process to ensure every formula survives the edit process intact. It treats formula preservation as a distinct requirement from data accuracy.

    What it does

    • Baseline formulas by reading the raw expression text rather than just the cached output values.
    • Map references across row insertions, moves, or sheet renames to verify logical continuity.
    • Audit dynamic arrays by tracking both anchor points and spill ranges for modern Excel functions.
    • Separate concerns between expected authorized changes and accidental formula deletions.
    • Detect anomalies where a formula has been replaced by a constant value, even if the result remains the same.

    How it works

    1. Read the workbook in a mode that extracts formula text for a baseline.
    2. Define the edit scope and expected formula changes based on the task requirements.
    3. Compare the original formulas against the derived copy using mapped addresses.
    4. Generate a preservation checklist itemizing every formula, its current state, and any anomalies.

    Frameworks & tools

    Works with any spreadsheet interface or library that can extract raw formula strings, including OpenPyXL, XlsxWriter, and Excel JavaScript APIs.

    Why this beats prompting it yourself

    Generic prompts often overlook hidden sheets or fail to distinguish between a "correct value" and a "preserved formula." This skill forces a strict mapping audit that prevents accidental data hardening where formulas are lost during cell moves.

    Use cases

    • Auditing a workbook after bulk row insertions or structural refactoring.
    • Verifying template integrity after a user or script has populated input fields.
    • Ensuring dynamic array formulas haven't been "clipped" or overwritten.
    • Documenting formula changes for compliance or audit trails in financial models.

    Known limitations

    Does not verify the mathematical correctness of the logic itself, only its preservation. Unsupported formula types are marked as unverified rather than passed.

    Does not verify mathematical accuracy of formula logic. Unsupported or proprietary formula types are marked as unverified. Requires access to raw formula strings, not just cell values.

    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

    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 7 days ago

    Permissions

    No special permissions declared or detected

    Listed7 days ago

    What's inside

    Frequently Asked Questions

    While standard LLMs check for visual data accuracy, this skill specifically audits the underlying code of the spreadsheet to ensure dynamic formulas haven't been accidentally converted to static values or broken during row moves.

    The skill is designed to work with any AI agent that has access to spreadsheet libraries like OpenPyXL or Excel APIs, allowing it to extract and compare raw formula strings before and after edits.

    Yes, it is specifically built to handle dynamic arrays by tracking both the anchor cell and the spill range to ensure structural changes don't cause #SPILL! errors or formula clipping.

    You will receive the structured logic and verification protocols required to integrate formula auditing into your agent's workflow, along with documentation for implementation across various spreadsheet libraries.

    This skill focuses exclusively on 'formula persistence'—ensuring your logic remains intact and mapped correctly—rather than auditing the mathematical validity or business logic of the formulas themselves.

    New in Data & Databases