Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Financial Data Provenance Auditor

    1

    Audits financial app data for traceable sources, stale records, duplicates, and normalization errors.

    $7.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Financial Data Provenance Auditor

    Financial Data Provenance Auditor

    Example session with this skill installed

    Audit these fictional dividend API rows. The provider returns event timestamps in UTC and our app displays dates in America/Sao_Paulo. A retry may have duplicated the event. Preserve the raw values, identify what can be confirmed from this evidence, and propose regression checks.

    SymbolEvent IDRaw ex-date (UTC)AmountCurrencyImport time
    DEMO3evt-172026-04-01T02:00:00Z0.50BRL2026-03-01T12:00:00Z
    DEMO3evt-172026-04-01T02:00:00Z0.50BRL2026-03-01T12:03:00Z

    No provider date-field definition, payout schedule, or import code is available.

    • Read your context and instructions
    • Compiled the financial data provenance

    Summary

    BLOCK for displaying the event date until provider semantics are confirmed. The two rows share symbol, event ID, raw timestamp, amount, and currency but have different import times. This is strong evidence of a likely duplicate import; it does not prove the provider's event-ID guarantees.

    Provenance and findings

    SeverityFindingEvidenceRecommended action
    HighLikely duplicate eventBoth rows have DEMO3 / evt-17 and identical event values; import times differ by three minutes.Confirm the provider guarantees event-ID stability, then add an idempotency key and test a repeated import.
    MediumPossible local-date shift02:00 UTC may fall on the prior calendar date in São Paulo. The sample does not say whether this is a timestamp or date-only event.Check the provider field definition before converting or displaying it. Preserve the raw value.
    UnknownAmount basisThe sample gives 0.50 BRL but no per-share or event-level definition.Do not infer the basis; request provider documentation.

    Regression checks

    1. Reimport the same event and assert only one normalized record remains.
    2. Verify date-only events keep the provider-defined calendar date across timezones.
    3. Quarantine records with unknown currency, symbol mapping, or event identity.
    4. Preserve the raw payload and retrieval timestamp for auditability.

    All instrument names and values are fictional. No investment advice or live-provider validation is implied.

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

    About this skill

    A data-integrity review for products displaying market prices, dividends, or corporate actions. It traces fields to supplied providers or source files, tests ingestion and normalization risks, and distinguishes verified facts from assumptions. It does not provide investment recommendations.

    See it in action: Given a fictional dividend import with two identical records after a retry and a date shifted by a timezone conversion, this skill flags both issues, preserves the source values, and proposes idempotency and date-validation tests.

    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 4 days ago

    Requires

    None required beyond a compatible AI agent. Optional: file-reading capability for local CSV, JSON, SQL, or source files. No external account or API credential is needed.

    Listed4 days ago

    What's inside

    Frequently Asked Questions