菜单
Validate AI/ML models and datasets for bias, fairness, and ethical concerns. Use when auditing AI systems for ethical compliance, fairness assessment, or bias detection. Trigger with phrases like "evaluate model fairness", "check for bias", or "validate AI ethics".
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Execute extract and use project memories from previous sessions for context-aware assistance. Use when recalling past decisions, checking project conventions, or understanding user preferences. Trigger with phrases like "remember when", "like before", or "what was our decision about".
Execute automatically formats and validates code files using Prettier and other formatting tools. Use when users mention "format my code", "fix formatting", "apply code style", "check formatting", "make code consistent", or "clean up code formatting". Handles JavaScript, TypeScript, JSON, CSS, Markdown, and many other file types. Trigger with relevant phrases based on skill purpose.
Configure Clerk CI/CD integration with GitHub Actions and testing. Use when setting up automated testing, configuring CI pipelines, or integrating Clerk tests into your build process. Trigger with phrases like "clerk CI", "clerk GitHub Actions", "clerk automated tests", "CI clerk", "clerk pipeline".
Troubleshoot common Clerk errors and issues. Use when encountering authentication errors, SDK issues, or configuration problems with Clerk. Trigger with phrases like "clerk error", "clerk not working", "clerk authentication failed", "clerk issue", "fix clerk".
Implement user sign-up and sign-in flows with Clerk. Use when building authentication UI, customizing sign-in experience, or implementing OAuth social login. Trigger with phrases like "clerk sign-in", "clerk sign-up", "clerk login flow", "clerk OAuth", "clerk social login".
Implement session management and middleware with Clerk. Use when managing user sessions, configuring route protection, or implementing token refresh and custom JWT templates. Trigger with phrases like "clerk session", "clerk middleware", "clerk route protection", "clerk token", "clerk JWT".
| name | validating-ai-ethics-and-fairness |
| description | Validate AI/ML models and datasets for bias, fairness, and ethical concerns. Use when auditing AI systems for ethical compliance, fairness assessment, or bias detection. Trigger with phrases like "evaluate model fairness", "check for bias", or "validate AI ethics". |
| allowed-tools | Read, Write, Edit, Grep, Glob, Bash(python:*) |
| version | 1.24.0 |
| author | Jeremy Longshore <jeremy@intentsolutions.io> |
| license | MIT |
| tags | ["ai","compliance","audit"] |
| compatibility | Designed for Claude Code, also compatible with Codex and OpenClaw |
Validate AI/ML models and datasets for bias, fairness, and ethical compliance using quantitative fairness metrics and structured audit workflows.
pip install fairlearn)pip install aif360) for comprehensive bias analysisExponentiatedGradient from Fairlearn)| Error | Cause | Solution |
|---|---|---|
| Insufficient group sample size | Fewer than 30 observations in a demographic group | Aggregate related subgroups; use bootstrap confidence intervals; flag metric as unreliable |
| Missing sensitive attributes | Protected attribute columns absent from dataset | Apply proxy detection via correlated features; request attribute access under data governance approval |
| Conflicting fairness criteria | Demographic parity and equalized odds contradict | Document the impossibility theorem trade-off; prioritize the metric most aligned with the deployment context |
| Data quality failures | Inconsistent encoding or null values in attribute columns | Standardize categorical encodings; impute or exclude nulls; validate with schema checks before analysis |
| Model output format mismatch | Predictions not in expected probability or binary format | Convert logits to probabilities via sigmoid; binarize at the decision threshold before metric computation |
Scenario 1: Hiring Model Audit -- Validate a resume-screening classifier for gender and age bias. Compute demographic parity across male/female groups and age buckets (18-30, 31-50, 51+). Apply the four-fifths rule. Finding: female selection rate at 0.72 of male rate (critical severity). Recommend reweighting training samples and adjusting the decision threshold.
Scenario 2: Credit Scoring Fairness -- Assess a credit approval model for racial disparate impact. Calculate equalized odds (TPR and FPR) across racial groups. Finding: FPR for Group A is 2.1x Group B (high severity). Recommend in-processing constraint using ExponentiatedGradient with FalsePositiveRateParity.
Scenario 3: Healthcare Risk Prediction -- Evaluate a patient risk model for age and socioeconomic bias. Compute calibration curves per group. Finding: model overestimates risk for low-income patients by 15%. Recommend recalibration using Platt scaling per subgroup with post-deployment monitoring for fairness drift.