Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    hr data inventory and quality auditor

    1

    Dirty HR data leads to broken people analytics, failed compliance audits, and reporting errors.

    $2.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    hr data inventory and quality auditor

    hr data inventory and quality auditor

    Example session with this skill installed

    Audit the attached employee_extract.csv and positions.json. Authorization provided by the HRIS Director for the employee and position scopes. Use a stale_after_days parameter of 90.

    • Read your context and instructions
    • Compiled the hr data inventory
    • Generated the data export

    The HR Data Quality audit for the provided extracts is complete. The analysis identified several orphaned positions and duplicate person match keys.

    HR Data Inventory and Quality Audit — Acme Corp, 2024-05-20

    1. Scope, authorisation and assumptions

    • Sources: E1 (employee_extract.csv), E2 (positions.json).
    • Approving Role: HRIS Director.
    • Purpose: Data quality profiling.
    • Granted Scopes: employee, position.

    2. Data inventory and ownership

    DatasetCategoryOwnerStewardPersonal dataFindings
    E1Employee MasterHR OpsJ. DoeYesMissing Lawful Basis
    E2Position MgmtOrg DesignUnassignedNoSteward Gap

    3. Record quality profiles

    Record setIn scopeCompletenessRecords with findingsClean-record rate
    Employees12500.9840200.9840
    Positions13000.9500650.9500

    4. Duplicates, references and consistency

    Record setFindingSeverityRecordsRow pointers
    Employeespossible_duplicate_personHigh4[102, 455, 890, 1102]
    Positionsorphan_referenceMedium12[12, 45, 67, 89...]

    5. Lawful-use, retention and jurisdiction review queue

    Findings indicate 15 records in E1 exceed the defined 90-day staleness parameter. Jurisdiction-specific employment and privacy law review by qualified counsel is needed.

    6. Suppressed and excluded data

    • Suppressed: 2 small groups (n<5) in department-level aggregates.
    • Excluded: 0 records.

    7. Draft actions and items for human review

    • Draft: Reassign Position Steward for E2. Management decision required.
    • Draft: Review possible duplicate persons in E1. Information gap — organizational validation required.

    Next steps

    1. Review the row pointers in section 4 to identify specific duplicate records.
    2. Assign a Steward to the Position Management dataset.
    3. Validate the 15 records flagged for retention policy violations with Legal.

    employee_extract.csv

    CSV · 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

    Dirty HR data leads to broken people analytics, failed compliance audits, and reporting errors. This skill provides a deterministic audit of workforce datasets and record extracts to identify gaps in ownership, documentation, and data integrity. It profiles employee and organizational records for duplicates, orphaned references, and inconsistent dates before you feed them into production systems.

    What it does

    • Inventory auditing checks datasets for missing owners, stewards, lawful basis documentation, and retention policies.
    • Record profiling analyzes employee, position, and org-unit records for completeness and field-level accuracy.
    • Integrity checking detects duplicate keys, possible duplicate persons via match keys, and reporting-line loops.
    • Reference validation identifies orphaned position references and contradictions in employment history dates.
    • Privacy review flags cross-border transfers lacking mechanisms and retention periods exceeding policy limits.
    • Action drafting generates a review queue for data owners and legal counsel while suppressing small group sizes for privacy.

    How it works

    1. Supply data by providing HR dataset metadata or minimal record extracts (CSV/JSON).
    2. Authorize scope by specifying the approving role and granting access to employee, position, organization, or history domains.
    3. Execute audit via a deterministic Python script that processes the request.json against defined quality rules.
    4. Review findings through a structured Markdown report featuring data-owner queues and draft remediation actions.

    Frameworks & tools

    This skill uses a self-contained Python 3 script for data processing. It operates on structured JSON input/output schemas and adheres to strict data minimization principles.

    Why this beats prompting it yourself

    Generic prompts often hallucinate data quality benchmarks or miss subtle reporting-line loops. This skill uses a deterministic script to ensure every count, rate, and duplicate check is mathematically exact and repeatable. It also enforces privacy through automated small-group suppression that a standard prompt would likely ignore.

    Use cases

    • Audit an HR data inventory before a migration or system implementation.
    • Profile workforce records to find duplicate identities or orphaned positions.
    • Build a legal review queue for GDPR or jurisdiction-specific data retention.
    • Validate org-chart integrity and reporting lines before executive reporting.

    Known limitations

    Does not support supplier master data or payroll-specific financial auditing. Cannot perform record merging or automated data cleaning. Requires a minimum group size of 5 for privacy suppression.

    Requires Python 3 for script execution. Minimum group size for reporting is 5 records. No support for supplier/vendor data or automated record merging.

    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 days ago

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Environment Variables
    Listed2 days ago

    What's inside

    Frequently Asked Questions

    This skill uses a deterministic Python-based engine to perform exact mathematical audits, ensuring 100% accuracy in duplicate detection and reporting loops that standard LLM prompting often misses or hallucinates.

    The skill is compatible with any AI agent that supports Python execution environments and can process JSON or CSV data inputs.

    To protect employee privacy, the skill automatically suppresses findings for groups smaller than five individuals and uses a self-contained script to ensure your sensitive data remains within your authorized environment.

    You will receive the complete Python 3 audit script, the structured JSON input/output schemas, and comprehensive documentation on how to map your HR data to the auditor.

    The skill identifies data gaps, duplicates, and orphaned records, then generates a structured Markdown report with specific action queues for your data owners and legal counsel to review.

    No, this skill is designed for diagnostic auditing and reporting; it identifies errors and suggests remediations but will not modify or merge records in your production systems.