More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    🧪 Hiring Screener Audit Harness

    1

    Test an AI or rules-based resume screener for outcome changes, score drift, missing evidence, sensitive-term leakage, and human-review gaps.

    $19

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    🧪 Hiring Screener Audit Harness

    🧪 Hiring Screener Audit Harness

    Example session with this skill installed

    case_id,run_id,input_fingerprint,outcome,score,evidence,human_review,sensitive_terms
    case-07,run-a,sha256:abc,advance,82,"5 years relevant operations experience",yes,
    case-07,run-b,sha256:abc,reject,61,,no,age

    • Read your context and instructions
    • Compiled the hiring screener audit

    Recommendation: DO NOT RELY
    Critical: case-07 changed from advance to reject with the same input fingerprint.
    High: score drift was 21 points; the negative result had no evidence and no human-review path.
    Medium: decision evidence contained a configured sensitive term.
    Next step: isolate the variable, rerun the controlled case, and require human review before any live use.

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

    About this skill

    Hiring Screener Audit Harness helps a hiring operator test a resume-screening system before relying on its shortlist. Supply controlled run results from the screener, including repeated cases and synthetic variants that change only the field being tested. The included local audit checks whether the same case changes outcome, whether scores drift beyond a chosen threshold, whether negative results lack cited evidence, whether sensitive terms appear in decision evidence, and whether a human-review path is missing. It returns structured findings, a severity summary, and a review memo that distinguishes READY FOR HUMAN REVIEW from DO NOT RELY. It audits the screening process rather than ranking real applicants, and it does not claim to certify compliance or prove that a system is unbiased.

    Results are only as representative as the controlled fixtures and screener outputs supplied.
    Synthetic counterfactual tests can reveal concerning differences but cannot establish why a model behaved differently.
    The audit is operational quality assurance, not legal advice, compliance certification, or proof that discrimination is absent.

    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 24 days ago

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    File Scopes

    screening-audit-input/**
    screening-audit-output/**
    *.csv
    *.json
    *.md

    The deterministic helper reads only a supplied CSV and writes findings, a JSON summary, and a Markdown review memo locally. It does not connect to an ATS, submit candidates, or make hiring decisions.

    Listed3 months ago

    What's inside

    Frequently Asked Questions

    The harness acts as a Quality Assurance layer that stress-tests your screener's responses against synthetic variants to detect inconsistent scoring, missing evidence for rejections, and leakage of sensitive terms before you trust the tool with real candidates.

    You will receive the structured audit logic, a template for supplying comparative run results, and a generator that produces the final review memo and severity summary.

    The harness is designed to be agent-agnostic; it audits the JSON or CSV output from any AI or rules-based screener, provided the data includes the applicant's attributes and the system's decision evidence.

    Setup is straightforward: you point the harness to your screening logs and define your score drift threshold; the local audit then processes the comparisons without requiring deep technical integration.

    No, this skill is a diagnostic tool for internal quality control and process auditing; it does not provide legal certification, nor does it guarantee compliance with specific regional hiring regulations.