shap

Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.

Quality

85%

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

78%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 content is highly actionable and well-structured with strong progressive disclosure to real reference files, but it carries redundant sections and some over-explanation of concepts Claude already knows.

Suggestions

Consolidate overlapping guidance between Quick Start, Core Workflows, Common Patterns, and Best Practices Summary to reduce redundancy and token cost.

Trim explanations of well-known concepts (e.g., SHAP additivity, background-data purpose) and defer deeper theory to references/theory.md.

Add explicit validation checkpoints to the Production Deployment and Model Comparison workflows (e.g., verify explainer round-trips on a held-out sample before serving).

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but repeats guidance across Quick Start, Core Workflows, Common Patterns, and Best Practices sections, and explains concepts Claude already knows (SHAP additivity, baseline purpose) that could be trimmed.	3 / 5
Actionability	Provides numerous copy-paste-ready, executable code examples covering explainer selection, value computation, plotting, performance optimization, and production API integration.	5 / 5
Workflow Clarity	Workflows are clearly sequenced with numbered steps, but they lack explicit validation checkpoints or feedback loops for fragile operations like production deployment and model comparison.	4 / 5
Progressive Disclosure	Clear overview with four real one-level-deep reference files (explainers.md, plots.md, workflows.md, theory.md), each well-signaled with a usage-guidelines section describing when to load them.	5 / 5
	Total	17 / 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.

The description is strong: it clearly defines the skill's purpose, provides an explicit use-trigger clause, lists many concrete actions, and is well-differentiated from other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (explaining predictions, computing feature importance, generating named plot types, debugging, bias/fairness analysis, comparing models, implementing explainable AI) with comprehensive coverage.	5 / 5
Completeness	Explicitly states both what the skill does (SHAP-based interpretability/explainability) and when to use it via a clear 'Use this skill when...' clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good coverage of natural phrases users would say ('feature importance', 'SHAP plots', 'debug my model', model-type names), but a few common synonyms or phrasings are absent.	4 / 5
Distinctiveness Conflict Risk	SHAP is a clearly scoped niche with distinct triggers (named plot types, specific model frameworks) that minimize conflict with other interpretability or general ML skills.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (566 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/coding/shap/SKILL.md
Commit: 3a6c3a9

Reviewed: 1 day 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.