shap

Explain and audit machine-learning predictions with SHAP. Use for selecting SHAP explainers and maskers, computing and validating feature attributions, handling multi-output explanations, and producing local or global SHAP visualizations.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%Weight 40%Scale 1-5

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

The body is well-structured, executable, and properly split across one-level-deep reference files with explicit navigation. It respects Claude's competence while retaining validation checkpoints and copy-paste code, with only minor conciseness trim possible.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's competence (operating rules, decision tables, executable snippets) with only minor padding such as restated shape rules and explanatory table captions that could be trimmed.	4 / 5
Actionability	Fully executable copy-paste-ready Python for the core workflow, an install snippet, a bundled-script command, and concrete decision tables covering the common cases.	5 / 5
Workflow Clarity	A numbered Standard Workflow with explicit validation checkpoints (additivity assertion via assert_allclose, troubleshooting order, 'never silence an additivity failure until ... checked') and a feedback-loop-style Troubleshooting Order, satisfying the destructive/batch validation requirement.	5 / 5
Progressive Disclosure	A concise overview SKILL.md with a Reference Map pointing one level deep to 8 real reference files, each with a clear 'Load when' trigger, plus one bundled script — all referenced paths verified to exist.	5 / 5
	Total	19 / 20 Passed

Description

92%Weight 40%Scale 1-5

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

A strong, specific, third-person description that clearly states both capabilities and triggering scenarios with minimal fluff. The only gap is coverage of common user synonyms such as 'feature importance' or 'Shapley values'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'selecting SHAP explainers and maskers', 'computing and validating feature attributions', 'handling multi-output explanations', and 'producing local or global SHAP visualizations' — covering the skill comprehensively.	5 / 5
Completeness	Explicitly answers 'what' (explain and audit ML predictions with SHAP) and 'when' via the 'Use for ...' clause enumerating concrete triggering scenarios.	5 / 5
Trigger Term Quality	Natural terms like 'SHAP explainers', 'maskers', 'feature attributions', and 'visualizations' appear, but synonyms a user might naturally say (e.g. 'feature importance', 'model interpretability', 'Shapley values') are absent.	4 / 5
Distinctiveness Conflict Risk	The SHAP-specific niche with distinct triggers (explainer/masker selection, multi-output explanations, SHAP visualizations) carries minimal conflict risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/shap/SKILL.md
Commit: b2a92ba

Reviewed: 3 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.