More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    πŸ“‹ Craft Fair Closeout Checker

    1

    Compare craft-fair stock counts and normalized movements, with optional payment and cash checks. Get local, source-linked discrepancies and explicit unknowns to review.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    πŸ“‹ Craft Fair Closeout Checker

    πŸ“‹ Craft Fair Closeout Checker

    Example session with this skill installed

    Use the supplied fictional examples/market files to compare event stock, payment summaries and cash. Run the helper and report its complete Markdown output. Preserve missing values and source references; do not invent the cause of a difference. This demonstration uses already-normalized files, not a raw-receipt import.

    • Read your context and instructions
    • Compiled the craft fair closeout
    • Generated the data export

    Demonstration context

    This is a tested local Python CLI run on the supplied fictional fixture, not a tested installed-agent session. Actual generated files are closeout.md and closeout.json. CSV files are inputs only; any marketplace-generated CSV artifact label is incorrect.

    Complete closeout.md output

    Craft Fair Closeout

    REVIEW

    Arithmetic comparison of supplied records only. Differences do not establish a cause, revenue or theft. No stock or financial system was changed.

    Stock

    IDLevelExpectedCountedDifferenceResult
    PIN-OWLitem1312-1DIFFERENCE

    PIN-OWL: Recount and check source records; cause remains unresolved.
    Sources: counts.csv data record 1 (ending line 2); movements.csv data record 1 (ending line 2); movements.csv data record 2 (ending line 3)
    References: count sheet A / row 1; tally T1; damage D1

    Payments

    Compare receipts less refunds before fees; this is not profit or a bank-deposit reconciliation.

    • card: DIFFERENCE; difference -0.10; payments.csv data record 1 (ending line 2); tally T2 / provider event P1

    Cash

    MATCH; expected 99; difference 0
    Source: cash.json; cash C1 / cash tally C2 / adjustments A1

    Next step

    Review normalization against originals, recount differences, and record any correction and remaining unknowns. Optional sections omitted from input have not passed a check. Source file hashes and row references are preserved in closeout.json.

    counts.csv

    CSV Β· data export

    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

    Compare your event records

    Craft Fair Closeout Checker helps a craft seller compare what went to an event, what was recorded as sold or otherwise moved, and what came home. Prepare the documented CSV and JSON templates from your own records, then run the local Python helper.

    It produces a readable Markdown report and a JSON report with source hashes and row references. Blank counts stay unknown; duplicate records and invalid inputs stop the run. Optional payment and cash checks require matching event boundaries and calculation bases.

    What you receive

    The ZIP includes skill instructions, a standard-library Python helper, input contract, blank templates and a fictional worked example.

    Preparation and limits

    Someone gathers, normalizes and checks records, recounts discrepancies and decides corrections. No automatic Square, Venmo, Etsy, receipt-image or PDF import. No inventory writeback, tax calculation, profit calculation or proof of missing-sale causes. This is not an audit.

    The CLI was tested on Windows with Python 3.12.14. Agent-host installation, controlled comparison against a strong general-AI prompt, real seller usability and time savings remain untested. The separate Etsy worksheet kit is not included.

    Manual normalization and review against originals are required. No automatic POS, receipt-image, PDF or payment-provider imports. No inventory writeback, tax calculation, profit calculation or proof of missing-sale causes. Agent-host installation and controlled strong-prompt comparison are untested. Real seller usability, time savings and willingness to pay remain unmeasured.

    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 2 months ago

    Requires

    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    File Scopes

    User-selected
    input
    folder/{event.json
    counts.csv
    movements.csv
    payments.csv
    cash.json};
    new
    output
    folder/**

    Reads the user-selected local event.json, counts.csv, movements.csv, and optional payments.csv/cash.json. Writes closeout.md and closeout.json into a new output folder. No network calls, credentials, environment variables or inventory changes. An agent host may separately process prompts; use only records authorized for that host.

    Listed2 months ago

    What's inside

    Frequently Asked Questions

    No. Prepare local CSV and JSON using the documented templates. Native exports are not accepted automatically.

    No. Copy the relevant counts and records manually. The PDF supplement also works independently.

    No. A difference prompts a recount and source check; the cause remains unresolved.

    Only arithmetic agreement with the supplied records. Missing or incomplete records can conceal discrepancies.

    No. Cash float, refunds and adjustments are handled explicitly, but there is no tax, fee, cost or profit calculation.

    A terminal with Python 3.10 or later and prepared local files. The CLI was tested on Windows with Python 3.12.14; agent-host installation is untested.