validating-ai-ethics-and-fairness

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".

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

65%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is lean and well-structured with specific domain guidance and a useful error-handling table, but it lacks executable code and fails to wire in the bundled scripts and assets, weakening actionability and progressive disclosure.

Suggestions

Reference the bundled scripts in the workflow (e.g., 'Run `python scripts/validate_model.py <model>` to compute the metrics below') so the guidance is executable end-to-end.

Add explicit validation checkpoints between steps (e.g., verify group sample sizes >= 30 before computing metrics; re-validate after mitigation) rather than relying on the separate error table.

Add a 'Bundle' section pointing to scripts/validate_model.py, scripts/validate_dataset.py, scripts/generate_report.py, and assets/report_template.md so the supporting files are discoverable from SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is well-organized into purposeful sections (Prerequisites, Instructions, Output, Error Handling, Examples, Resources) without padding or explaining concepts Claude already knows; brief parenthetical metric glosses are the only mild excess.	3 / 3
Actionability	Guidance is specific (named metrics, libraries, the 0.80 four-fifths threshold, severity bands, mitigation algorithms) but contains no executable code or commands, and the bundled scripts (validate_model.py, validate_dataset.py, generate_report.py) are never referenced from the workflow.	2 / 3
Workflow Clarity	A clear 10-step sequence exists with one verify checkpoint (step 1) and a separate error-handling table, but validation is not woven as explicit checkpoints within the main flow, leaving feedback loops implicit rather than integrated.	2 / 3
Progressive Disclosure	Sections are well organized, but the body points only to external resources (Fairlearn, AIF360, IEEE/EU/ACM) and never signals the bundled scripts/assets (report_template.md, example files), so the bundle structure is not navigated from SKILL.md.	2 / 3
	Total	9 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong: third-person voice, concrete capabilities, explicit "Use when" triggers, and natural trigger phrases. It cleanly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	"Validate AI/ML models and datasets for bias, fairness, and ethical concerns" names multiple concrete targets (models, datasets) and specific concerns (bias, fairness, ethical concerns), matching the multiple-specific-actions anchor.	3 / 3
Completeness	It answers both what ("Validate AI/ML models and datasets for bias, fairness, and ethical concerns") and when ("Use when auditing AI systems for ethical compliance, fairness assessment, or bias detection") with explicit triggers.	3 / 3
Trigger Term Quality	"evaluate model fairness", "check for bias", and "validate AI ethics" are natural phrases a user would actually say, giving good coverage of trigger terms.	3 / 3
Distinctiveness Conflict Risk	The AI ethics/fairness validation niche is specific with distinct triggers unlikely to collide with other skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/ai-ml/ai-ethics-validator/skills/validating-ai-ethics-and-fairness/SKILL.md
Commit: c4eafaf

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.