More screenshots
Works with the AI Agents you already use
🧪 Hiring Screener Audit Harness
Test an AI or rules-based resume screener for outcome changes, score drift, missing evidence, sensitive-term leakage, and human-review gaps.
$19
🧪 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
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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 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
File Scopes
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.