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.

Well-organized, executable, and validated content with excellent progressive disclosure through verified reference files. Only minor conciseness trimming is warranted given the body length.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes Claude's competence without lecturing on basics, but at ~290 lines across many scenarios a few sections could be tightened further.	4 / 5
Actionability	Fully executable, copy-paste-ready code for binary classification, tree probability output, and permutation explainers, plus a concrete plot-selection table and install commands covering the common cases.	5 / 5
Workflow Clarity	A clearly sequenced 7-step Standard Workflow with explicit additivity validation (assert_allclose against model output) and a 7-step Troubleshooting feedback loop that gates package-specific fixes until checks pass.	5 / 5
Progressive Disclosure	Clear overview with a Reference Map table giving one-level-deep, 'Load when' navigation to eight verified reference files and a bundled script, with detail appropriately split out of SKILL.md.	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 clear, specific, third-person description that concretely enumerates capabilities and provides an explicit 'Use for' trigger clause. Minor synonym coverage for natural user phrasing could be added.

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' — with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what ('Explain and audit machine-learning predictions with SHAP') and when ('Use for selecting... computing... handling... producing...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural technical terms like 'SHAP', 'feature attributions', 'machine-learning predictions', and 'SHAP visualizations' are present, but common synonyms such as 'interpretability' or 'explainability' are missing.	4 / 5
Distinctiveness Conflict Risk	The SHAP-specific, feature-attribution niche has distinct triggers and minimal overlap 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: 49c6e97

Reviewed: 9 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.