explaining-machine-learning-models

Build this skill enables AI assistant to provide interpretability and explainability for machine learning models. it is triggered when the user requests explanations for model predictions, insights into feature importance, or help understanding model behavior... Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

Quality

11%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/ai-ml/model-explainability-tool/skills/explaining-machine-learning-models/SKILL.md

Quality

Discovery

22%

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

This description is weak across all dimensions. It relies on vague, abstract language without listing concrete actions, and the 'Use when' clause is entirely boilerplate placeholder text that provides zero actual trigger guidance. The description also violates voice guidelines by using 'enables AI assistant' framing rather than third-person active voice.

Suggestions

Replace the boilerplate 'Use when appropriate context detected' with specific trigger scenarios, e.g., 'Use when the user asks to explain a model prediction, compute SHAP values, visualize feature importance, or understand why a model made a specific decision.'

List concrete actions the skill performs, e.g., 'Generates SHAP explanations, computes feature importance rankings, creates partial dependence plots, produces LIME local explanations, and summarizes model decision boundaries.'

Rewrite in third-person active voice (e.g., 'Provides interpretability analysis for ML models') and add natural trigger terms users would say, such as 'explain prediction', 'why did the model', 'SHAP', 'LIME', 'feature importance', 'model explainability'.

Dimension	Reasoning	Score
Specificity	The description uses vague language like 'provide interpretability and explainability' and 'insights into feature importance' without listing concrete actions (e.g., generate SHAP plots, compute LIME explanations, produce partial dependence plots). It also uses first/second person framing ('enables AI assistant') which would reduce the score further.	1 / 3
Completeness	While it vaguely addresses 'what' (interpretability/explainability) and has a 'Use when' clause, the 'Use when' is entirely boilerplate ('Use when appropriate context detected. Trigger with relevant phrases based on skill purpose') and provides no actual guidance, making it effectively missing.	1 / 3
Trigger Term Quality	It includes some relevant keywords like 'model predictions', 'feature importance', and 'model behavior' that users might naturally say, but misses common variations like 'SHAP', 'LIME', 'explain prediction', 'why did the model predict', 'feature contribution', or specific model types.	2 / 3
Distinctiveness Conflict Risk	The ML interpretability domain is somewhat specific and wouldn't overlap with most skills, but the vague language ('model behavior', 'explanations') could conflict with skills related to general ML help, model debugging, or data science workflows.	2 / 3
	Total	6 / 12 Passed

Implementation

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

This skill is almost entirely boilerplate and abstract description with zero actionable content. It explains what model explainability is and when you might want it, but never provides any executable code for SHAP, LIME, or feature importance analysis. The 'Instructions', 'Output', 'Error Handling', and 'Resources' sections are generic placeholders that add no value.

Suggestions

Replace the abstract 'How It Works' and 'Examples' sections with executable Python code showing actual SHAP value calculation (e.g., `shap.TreeExplainer(model).shap_values(X)`) and LIME usage (e.g., `lime.lime_tabular.LimeTabularExplainer`), with concrete input/output examples.

Remove all boilerplate sections ('Prerequisites', 'Instructions', 'Output', 'Error Handling', 'Resources', 'Integration') that contain only generic placeholder text and provide no skill-specific guidance.

Add a decision matrix or concrete rules for when to use SHAP vs LIME vs permutation importance based on model type (e.g., 'For tree-based models use `shap.TreeExplainer`; for black-box models use LIME').

Include actual visualization code (e.g., `shap.summary_plot()`, `shap.force_plot()`) with expected output descriptions so Claude can generate complete, runnable explainability workflows.

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive explanation of concepts Claude already knows. Sections like 'How It Works', 'When to Use This Skill', 'Integration', 'Prerequisites', 'Instructions', 'Output', 'Error Handling', and 'Resources' are all filler that provide no actionable information. The skill explains what explainability is rather than how to do it.	1 / 3
Actionability	No executable code, no concrete commands, no specific library usage examples. The 'Examples' section describes what the skill 'will do' in abstract terms rather than providing actual SHAP/LIME code. Instructions like 'Invoke this skill when the trigger conditions are met' and 'Provide necessary context and parameters' are completely vague.	1 / 3
Workflow Clarity	The workflow steps ('Analyze Context', 'Select Explanation Technique', 'Generate Explanations', 'Present Results') are abstract descriptions with no concrete implementation details, no validation checkpoints, and no error recovery. The examples describe outcomes without showing how to achieve them.	1 / 3
Progressive Disclosure	Monolithic wall of text with no references to external files and no bundle files to support it. Content is poorly organized with multiple boilerplate sections ('Resources', 'Error Handling', 'Output') that contain placeholder text rather than real content. No structure for navigating to deeper material.	1 / 3
	Total	4 / 12 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 — 9 / 11 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	9 / 11 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 196527a

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.