Data Quality Clinic

    2

    Audit a dataset against business rules, keys and freshness SLAs, then produce a severity-ranked quality scorecard.

    $14

    Secure checkout via Stripe

    30-day refund guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI tools you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+22 more

    Data Quality Clinic

    Example session with this skill installed

    Audit orders.csv before we publish the weekly revenue report.

    • Primary key: order_id. customer_id must exist in customers.csv.
    • amount must be between 0 and 10,000; status in (paid, refunded, pending).
    • Data should be no more than 24 hours old.
      Give me a scorecard and tell me what blocks release.
    • Read your context and instructions
    • Compiled the data quality clinic
    • Generated the document

    Illustrative example on synthetic data. It follows this skill's quality_rubric.md scorecard template.

    Data Quality Scorecard: orders (weekly revenue feed)

    Verdict: NOT READY. 2 critical findings must be fixed before the report is published.

    Quality Dimension Scores

    DimensionScoreChecksResult
    Completeness92%null profile, 14 columns1 column over threshold
    Uniqueness97%order_id duplicates1,412 duplicate keys
    Referential integrity99.1%customer_id → customers438 orphans
    Validity99.8%amount range, status set96 out-of-range rows
    TimelinessFAILlatest created_at vs 24h SLA41h old

    Critical Findings (must fix before production use)

    Duplicate order_id (1,412 rows, 2.9%). They are all from the 2026-09-27 load, which suggests the pipeline ran twice. Revenue is overstated by about $86K.
    2. Stale data. The latest record is 41 hours old against a 24-hour SLA. The Sunday load did not run.

    High Severity (fix within 5 business days)

    • 438 orders (0.9%) reference customer IDs that are missing from customers. All of them are new signups, which points to a lag in the customers sync.

    Medium / Low (document and monitor)

    • shipping_region is 8% null, all digital orders. This is expected; document it rather than fix it.
    • 96 rows have amount < 0. These are refunds coded as negative orders. Confirm with Finance.

    Checks Performed

    null_counter, duplicate_finder, referential_integrity, value_range_validator, freshness_check

    Next steps

    Deduplicate the 09-27 load, re-run the Sunday job, re-audit, then sign off.

    data-quality-clinic.pdf

    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.

    What you get

    Pre-release pipeline validationData quality scorecard for governanceInvestigating "the numbers look wrong"Onboarding a new data source

    About this skill

    Data Quality Clinic walks your agent through a structured data quality audit before a dataset reaches production reports. It checks completeness (nulls), duplicates, referential integrity between tables, value ranges against your business rules, and freshness against your pipeline SLA. Every finding is mapped to a quality dimension and given a severity (CRITICAL / HIGH / MEDIUM / LOW), so you know what blocks release and what can be monitored.

    Use it when

    • A pipeline just loaded new data and downstream reports are about to consume it
    • A stakeholder says "the totals look wrong" or "this table is stale"
    • You need a formal quality scorecard for a data governance process
    • You are onboarding a new data source

    What's inside (installs as one folder, data-quality-audit/):

    • data-quality-audit/LICENSE
    • data-quality-audit/SKILL.md
    • data-quality-audit/assets/audit_report_template.html
    • data-quality-audit/assets/quality_rubric.md
    • data-quality-audit/references/business_rule_patterns.md
    • data-quality-audit/references/quality_dimensions.md
    • data-quality-audit/scripts/duplicate_finder.py
    • data-quality-audit/scripts/freshness_check.py
    • data-quality-audit/scripts/null_counter.py
    • data-quality-audit/scripts/referential_integrity.py
    • data-quality-audit/scripts/value_range_validator.py

    Please read before buying: this is packaged from my free, MIT-licensed open-source library (https://github.com/nimrodfisher/data-analytics-skills). The same content is available there for free. You are paying for a ready-to-install package. It is a one-time purchase, sold as-is, with no support, updates or maintenance included. The MIT license is included.

    How to install

    Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.

    ~30 seconds
    1. 1

      Download the ZIP

      Free skills download straight away. Paid skills unlock right after purchase.

    2. 2

      Unzip into your skills folder

      Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.

    3. 3

      Ask your agent to use it

      Restart the agent if it was already running. It picks the skill up automatically - no config needed.

    Skills folder by agent

    Click the path to copy it. Create the folder if it does not exist yet.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    30-day refund

    Not a fit? Get your money back

    Trust & safety

    Security scanned

    Verified clean 3 days ago

    • Passed all security checks, Safe to install

    Listed3 days ago
    Updated1 day ago

    What's inside

    Frequently Asked Questions