Tessl • The package manager for agent skills

SkillPublic

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

83%

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

70%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 clean progressive disclosure to genuine reference files, but it is verbose for a SKILL.md and its workflows omit explicit validation/checkpoint steps for batch and production operations.

Suggestions

Trim tutorial-style explanations of SHAP semantics (e.g. 'Positive SHAP value → Feature pushes prediction higher') and remove the Quick Start code duplicated inside Workflow 1 to reduce token load.

Add explicit validation checkpoints to the production and batch workflows (e.g. verify cached explainer loads, validate SHAP value shapes against input, sanity-check base_values) so workflow_clarity can exceed 3.

Consolidate the six overlapping workflows and the Troubleshooting Q&A into the referenced workflows.md to keep the overview lean.

Dimension	Reasoning	Score
Conciseness	The 560-line body explains concepts Claude already knows (SHAP value additivity/positivity semantics, baseline selection, output-unit explanations) and duplicates Quick Start inside Workflow 1; mostly efficient but contains padding that could be trimmed.	3 / 5
Actionability	Copy-paste ready executable Python throughout (TreeExplainer setup, beeswarm/waterfall/scatter plots, cohort comparison, MLflow logging, ExplanationService class) covering the common cases with specific calls.	5 / 5
Workflow Clarity	Six numbered workflows with goals/steps are well-sequenced, but they lack explicit validation checkpoints for batch/production operations (Workflow 6) — per the rubric cap, missing validation caps this at 3.	3 / 5
Progressive Disclosure	Clear overview body with well-signaled one-level-deep references to real files (explainers.md, plots.md, workflows.md, theory.md), each described and recommended with loading guidance.	5 / 5
	Total	16 / 20 Passed

Description

90%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, third-person description that clearly states capabilities and explicit use-trigger conditions with comprehensive action coverage. It is slightly verbose but highly informative with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'explaining...predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, implementing explainable AI' — with comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what ('Model interpretability...using SHAP') and when ('Use this skill when explaining...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural terms ('SHAP plots', 'feature importance', 'model bias', 'fairness', 'explainable AI') with plot-type synonyms, but missing a few colloquial phrasings a user might say like 'why did my model predict this'.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear SHAP-specific niche with distinct triggers (SHAP plots, Shapley values, model explanation); minimal conflict risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (561 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/shap/SKILL.md
Revision: 5ce2258

Reviewed: 28 days ago

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.

shap

Table of Contents

Is this your skill?