Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mohitagw15856/ai-ethics-review
Conduct a structured ethical review of an AI or ML feature, model, or product.
Passed 18 of 23 test cases with the skill, and 12 of 23 without it.
and 8 more in the full report
6 fixed12 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
We are preparing to launch 'EHR-Predict', an AI feature that flags high-risk hospital patients for ICU escalation. It processes real-time vitals and historical electronic health records to score patient deterioration risk, directly affecting patient care outcomes in emergency wards. A physician reviews all high-risk alerts before taking action. Please perform an AI ethics review for this model. The output should include a system summary table, composite risk tier evaluation based on impact factors, detailed checks on fairness, explainability, data privacy, safety failure modes, governance, societal impact, a numbered mitigation priority list, and a launch readiness checklist.
| Checked | Without skill | With skill |
|---|---|---|
| Includes a Feature Summary section with explicit distinction between who uses the system and who is affected by outputs. | Missed | Passed |
| Structures the transparency analysis table across user disclosure, decision explanation, right to know, and confidence calibration. | Missed | Passed |
| Evaluates safety failure modes specifically covering false positives, false negatives, out-of-distribution inputs, and model degradation. | Passed | Passed |
The instructions your model reads when the skill loads.
This skill produces a structured ethical review of an AI or machine learning feature, model, or product. Output covers fairness, transparency, privacy, safety, accountability, and societal impact — with risk scoring, prioritised mitigations, and a checklist suitable for governance review or responsible AI documentation.
⚠️ This skill provides a structured framework for identifying and documenting ethical risks. It is not a substitute for legal advice, regulated algorithmic impact assessments, or specialist ethics review required in specific jurisdictions (e.g. EU AI Act, UK AI regulation).
Ask the user for these if not provided:
Product / system: [Name and brief description] Review type: [Pre-deployment review / Post-deployment audit / Change review] Risk tier: [High / Medium / Low — based on consequentiality, scale, and affected population] Reviewer: [Name / Team] Date: [Date] Status: [Draft / Approved / Requires escalation]
| What it does | [1–2 sentences — plain English description of the AI feature and its purpose] |
| Who uses it | [End users / internal teams / automated system] |
| Who is affected by its outputs | [May be different from who uses it — e.g. an AI hiring tool is used by HR but affects candidates] |
| Output type | [Recommendation / Classification / Prediction / Generation / Automation / Scoring] |
test cases passed, vs 12 / 23 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.