Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Data Quality Guardian — Catch Broken, Missing & Suspicious

    1

    Define business-aware quality checks, investigate suspicious data and prioritize incidents with evidence, ownership and reconciliation.

    $9.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Data Quality Guardian — Catch Broken, Missing & Suspicious

    Data Quality Guardian — Catch Broken, Missing & Suspicious

    Example session with this skill installed

    Illustrative scenario: Review this fictional order dataset under supplied rules: each order_id should identify one current order; amounts must be non-negative; currency is required. Rows: O1,10,USD; O1,10,USD; O2,-5,USD; O3,blank,EUR. A blank amount has no defined meaning. Provide findings and a prevention plan without silently correcting records.

    • Read your context and instructions
    • Compiled the data quality guardian

    Data quality brief — illustrative four-row sample

    Purpose/grain: one current row per order_id under the supplied rule. Full source authority, update versions and reporting criticality are unknown.

    Finding 1: O1 appears twice with identical values. Violates supplied current-order uniqueness rule, pending confirmation that rows are not distinct legitimate events. Preserve raw rows; do not delete automatically.

    Finding 2: O2 amount -5 violates supplied non-negative rule. It could reflect different business semantics such as a return only if the contract allows that; do not change the supplied rule without owner review.

    Finding 3: O3 blank amount is unresolved. No rule defines null as invalid or zero. Quarantine or flag for owner decision; never silently coerce it to zero. Currency values are present in all four rows, but allowed currency domain is not supplied.

    Priority: verify whether these rows feed financial or other consequential reporting, determine blast radius and halt publication only where agreed policy requires. Four sample rows cannot establish production prevalence or root cause.

    Prevention controls: documented grain and uniqueness scope; explicit amount/null semantics; approved currency domain; source-side validation where reliable; actionable rejection reasons; authoritative count/value reconciliation; owners and severity for each rule.

    Investigation: trace duplicate generation and amount mapping through lineage, inspect representative authorized samples and compare control totals. Distinguish symptoms from proven cause.

    Execution notes: no database accessed, rows corrected, alerts configured or report blocked. Findings apply only to the supplied fictional sample.

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

    About this skill

    Data Quality Guardian helps teams detect and investigate missing, duplicated, stale, inconsistent and semantically incorrect data. It starts with intended use, authority, grain, keys, schemas and expected freshness, then profiles actual evidence before proposing thresholds.

    The DQ-90 workflow covers completeness, uniqueness, validity, consistency, distribution, lineage and reconciliation. It distinguishes legitimate nulls or zeros from missing data, business-identity duplicates from exact row equality and suspicious outliers from proven errors. Symptoms, probable causes, root causes and remediation remain separate.

    Use sanitized datasets, metadata and approved business rules to produce quality contracts, incident briefs, quarantine plans and prevention controls. Critical gates should reflect policy and impact rather than causing unnecessary global outages. No anomalies, metrics or live incidents are invented, and absence of alerts does not prove correctness.

    Quality depends on intended use and business semantics. Outliers do not prove corruption and absence of alerts does not prove correctness. Representative data, authoritative reconciliation and domain ownership are needed for production conclusions. Proposed fixes are not executed corrections.

    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 1 month ago

    Permissions

    Read Files
    Write Files

    File Scopes

    Authorized
    task
    inputs
    and
    agreed
    output
    directory
    only

    Use authorized metadata and minimal sanitized samples. Optional read/write files support analysis and reports. Avoid credentials, private endpoints, financial account data or unnecessary PII. No live queries, record changes, publication blocks or alerts assumed; external actions require authorization.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    No. It checks agreed semantics, baseline and business context and treats suspicious values as investigation evidence.

    No. It also considers identity, relationships, values, freshness, lineage and authoritative reconciliation.

    The base workflow produces findings and proposed controls. Record changes require explicit authorization and validated rules.

    New in Data & Databases