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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

35%

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

The content reads as a high-level overview rather than an actionable skill: it contains no executable code or commands, generic boilerplate sections add little value, and it fails to connect Claude to the bundled assets and scripts that actually exist.

Suggestions

Replace the abstract 'How It Works' and prose examples with concrete, executable guidance, e.g. a SHAP/LIME code snippet or a command invoking the bundled scripts with real arguments.

Cut the generic filler sections ('Instructions', 'Output', 'Error Handling', 'Resources') that state only 'the skill produces structured output relevant to the task' and similar non-content.

Add explicit, one-level-deep references to the real bundle files (e.g. 'See [explanation_template.html](../assets/explanation_template.html)') and either create or remove the missing scripts listed in scripts/README.md.

Dimension	Reasoning	Score
Conciseness	The body is mostly overview prose and generic filler sections ('Instructions', 'Output', 'Error Handling', 'Resources' say little of substance) rather than explaining basic concepts at length, but it is padded with abstract descriptions that could be tightened and assume Claude's knowledge of SHAP/LIME.	2 / 3
Actionability	There is no executable code, no commands, and no concrete API usage; sections like 'Claude chooses the most appropriate explanation technique' and the generic 'Instructions' ('Provide necessary context and parameters', 'Apply modifications as needed') describe rather than instruct.	1 / 3
Workflow Clarity	'How It Works' gives a 4-step sequence (Analyze Context, Select Technique, Generate Explanations, Present Results) but lacks validation checkpoints or feedback loops, and the example workflows are prose-only without verification steps.	2 / 3
Progressive Disclosure	The body has clear sections but never references the bundled assets (explanation_template.html, example_explanation.json, visualization_styles.css) or scripts, and the scripts README lists files (explain_model.py, feature_importance.py, data_preprocessing.py) that do not exist on disk, so navigation to the bundle is absent.	2 / 3
	Total	7 / 12 Passed

Description

75%

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 answers both 'what' and 'when' with explicit, distinctive ML-explainability triggers, but its specificity is diluted by abstract phrasing, a garbled opening clause, and generic boilerplate filler that weakens trigger-term quality.

Suggestions

Fix the garbled opening ('Build this skill enables AI assistant to provide...') and rewrite as clean third-person voice, e.g. 'Interprets and explains machine learning model predictions...'.

Replace the generic boilerplate ('Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.') with concrete trigger terms users actually say, such as 'explain why a model predicted X', 'feature importance', 'SHAP', or 'LIME'.

List concrete actions (e.g. 'compute SHAP values', 'generate local LIME explanations', 'rank feature contributions') instead of abstract terms like 'interpretability' and 'explainability'.

Dimension	Reasoning	Score
Specificity	Names the domain ('interpretability and explainability for machine learning models', 'explanations for model predictions, insights into feature importance') but the actions are abstract/generic ML terms rather than concrete, comprehensive actions, and the opening 'Build this skill enables AI assistant' is garbled.	2 / 3
Completeness	Explicitly answers both what ('provide interpretability and explainability for machine learning models') and when ('it is triggered when the user requests explanations for model predictions, insights into feature importance, or help understanding model behavior'), satisfying the 'Use when...' equivalent trigger guidance.	3 / 3
Trigger Term Quality	Includes some relevant natural keywords ('explanations for model predictions', 'feature importance', 'understanding model behavior') but pads them with generic boilerplate ('Use when appropriate context detected. Trigger with relevant phrases based on skill purpose') and misses common variations like 'SHAP', 'LIME', or 'why did the model predict'.	2 / 3
Distinctiveness Conflict Risk	Targets a clear niche (ML model interpretability/explainability) with distinctive triggers (model predictions, feature importance, model behavior) that are unlikely to conflict with unrelated skills, despite the generic boilerplate tail.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 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	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 2cafb23

Reviewed: 2 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.