Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    becuz profit drop

    1

    Analyzes shop records to identify, rank, and explain profit drops and cash gaps with SQL-backed evidence.

    $1

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    becuz profit drop

    Example session with this skill installed

    Why is my profit down for the last 7 days? Run scenario s01 in sample mode.

    • Read your context and instructions
    • Compiled the becuz profit drop

    I have completed the investigation for scenario s01 over the last 7 days. The analysis compared the current period against the four preceding 7-day windows.

    Profit Drop Analysis: Scenario s01

    CauseImpact (₦)ConfidenceNext Action
    Increased Supplier Cost-45,000HighRenegotiate rates with Bread Vendor B
    Unrecorded Staff Expense-12,500MediumAudit petty cash vouchers for Tuesday
    High Spoilage-8,200HighReduce inventory order for perishables
    Total Explained-65,700--

    Cash Gaps (Separate from Profit)
    The investigation found a cash gap of

    ₦18,200. These are transfer sales recorded at the till that have no matching entry in the bank records.

    Unexplained Variance
    There is a remaining unexplained drop of ₦3,400 that does not match current evidence rules.

    SQL Receipt (Sample s01)

    -- Investigation into Supplier Costs
    SELECT supplier_id, SUM(cost) as total_cost 
    FROM supplier_records 
    WHERE date BETWEEN '2026-10-05' AND '2026-10-12' 
    GROUP BY supplier_id;
    -- Record IDs Found: SUPP_992, SUPP_998, SUPP_1002
    -- Status: Verified by Checker Agent
    

    Next steps

    1. Review the bread supplier invoices (IDs SUPP_992, SUPP_998) to confirm price hikes.
    2. Cross-reference the ₦18,200 transfer gap with the POS terminal logs to identify the missing transaction date.
    3. Update the petty cash log to include the ₦12,500 staff lunch expense found in the bank records.

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

    About this skill

    Struggling to pin down why a small retail business is losing money? Most shop owners guess at the causes, but Becuz provides data-driven answers by analyzing sales, bank, supplier, and expense records. It identifies exactly where profit leaked over any 1 to 28-day window and separates actual profit loss from cash flow gaps.

    What it does

    • Ranked Cause Analysis identifies specific reasons for profit drops with naira impact and confidence levels.
    • Record Validation attaches specific record IDs and SQL "receipts" to every finding to ensure accuracy.
    • Rule-Out Logic lists tested causes that did not contribute to the drop, preventing red herrings.
    • Cash Gap Detection separates missing bank transfers from actual profit margin issues.
    • Unexplained Variance Reporting explicitly states the amount of profit change that remains unaccounted for.
    • Actionable Steps provides one concrete next step for every confirmed cause found in the records.

    How it works

    1. Initialize Sample Mode to test the logic against synthetic shop scenarios (s01 through s05) using DuckDB.
    2. Execute Investigation by passing a JSON payload with the shop owner's question and the desired date range.
    3. Review SQL Receipts which contain the exact queries and record IDs found by the agent.
    4. Transition to Live by connecting your own Zetaris and Nightshift environments for real-world shop data.

    Frameworks & tools

    Built with Python 3.12+ and uv. It uses DuckDB and sqlglot for local analysis, with support for Zetaris Unified Semantic Layer and Meterless Nightshift (NVIDIA Nemotron) for live production environments.

    Why this beats prompting it yourself

    Generic prompts often hallucinate financial calculations or miss the distinction between margin loss and cash gaps. This skill uses a "Checker agent" to re-run SQL queries independently, ensuring every naira figure is derived from records rather than LLM guesswork.

    Use cases

    • Identify why a shop's weekly profit fell despite high sales volume.
    • Detect recorded till sales that never successfully reached the bank account.
    • Analyze if rising supplier costs or increased operational expenses are eating margins.
    • Perform a 28-day audit to rank the top three drivers of financial variance.

    Known limitations

    Restricted to shop money analysis only. Does not write to databases. Requires four prior periods of historical data for comparison. Live mode requires external Zetaris and S3 setup.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Finance & Accounting.

    Explain shop money only. Read-only access. Requires 4 prior comparison periods. Live mode requires manual Zetaris/S3/Nightshift setup. Synthetic data for sample mode only.

    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 buying a skill.

    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 5 days ago

    Software
    PythonNode.jsGit

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Environment Variables
    Listed5 days ago

    What's inside

    Frequently Asked Questions

    The skill distinguishes between actual margin loss (like rising supplier costs) and 'cash gaps' where sales were recorded but the money never hit the bank, ensuring you don't waste time fixing the wrong problem.

    To accurately identify trends and variances, the skill requires at least four prior periods of historical record data to establish a baseline for comparison.

    Unlike generic prompts, this skill uses a 'Checker agent' that validates all findings with SQL-backed 'receipts,' ensuring every naira figure is pulled directly from your records rather than being hallucinated.

    The skill includes a built-in 'Sample Mode' with five synthetic shop scenarios (s01-s05), allowing you to test the logic and output quality before connecting your live data.

    The skill is built for Python 3.12+ environments using DuckDB for local analysis, with production support for Zetaris Unified Semantic Layers and NVIDIA Nemotron via Nightshift.

    No, the skill is strictly read-only; it is designed to analyze and report on financial variances without the risk of modifying or writing back to your source databases.

    New in Finance & Accounting