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

42%

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

Fix and improve this skill with Tessl

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

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 body is a readable overview but stays at the level of describing the skill rather than enabling Claude to execute it: no code, no commands, no validation checkpoints, and no links to the bundled scripts and templates that would make it actionable. Generic filler sections (Prerequisites, Output, Resources) crowd out concrete guidance.

Suggestions

Add a Quick Start with an executable example showing how to run the bundled scripts, e.g. `python scripts/explain_model.py --model model.pkl --data X.csv --method shap`, and link the existing assets (explanation_template.html, example_explanation.json, visualization_styles.css).

Replace generic filler sections ('Output: structured output relevant to the task', 'Resources: Project documentation') with concrete guidance, or remove them entirely to improve token efficiency.

Add explicit validation checkpoints to the workflow (e.g., verify the model and data are aligned before generating SHAP values; confirm feature names match between explainer and input) to lift workflow clarity above 2.

Dimension	Reasoning	Score
Conciseness	The body is not egregiously long, but it carries generic filler that adds no value Claude does not already have ('This skill empowers Claude to analyze and explain machine learning models', 'The skill produces structured output relevant to the task', 'Project documentation'). It is mostly efficient but could be tightened, matching the level-2 anchor rather than the lean level-3.	2 / 3
Actionability	The body offers no executable code or commands; it describes ('Calculate SHAP values to determine the contribution', 'Use LIME to generate local explanations') rather than instructs. Despite bundled scripts (explain_model.py, feature_importance.py) being available, the body never shows how to call them, so it matches the vague/abstract level-1 anchor.	1 / 3
Workflow Clarity	'How It Works' provides a four-step sequence (Analyze Context, Select Technique, Generate, Present), but there are no validation checkpoints or feedback loops for what is a fragile interpretability workflow. The generic 'Instructions' list ('Invoke this skill when the trigger conditions are met') adds no real sequencing, matching the level-2 anchor of steps present but checkpoints missing.	2 / 3
Progressive Disclosure	The body has organized sections, but the actual bundle (assets/explanation_template.html, assets/example_explanation.json, scripts/explain_model.py, etc.) is never referenced or linked from the body, so progressive disclosure is not realized against the provided bundle structure. It is better than a monolithic wall of text but references are not clearly signaled, matching level-2.	2 / 3
	Total	7 / 12 Passed

Description

50%

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 targets a clear niche (ML model explainability) but is weakened by broken grammar ('Build this skill enables...'), an unfinished ellipsis, and vacuous trigger guidance ('Use when appropriate context detected'). It conveys what and vaguely when, but not with the concrete, natural triggers needed for top marks.

Suggestions

Rewrite the description in clean third person naming concrete actions and tools, e.g. 'Interpret ML model predictions using SHAP, LIME, and feature importance analysis. Use when the user asks why a model made a prediction, requests feature importance, or needs to explain model behavior.'

Replace vacuous trigger language ('Use when appropriate context detected', 'Trigger with relevant phrases based on skill purpose') with the actual natural phrases users would say (e.g., 'why did the model predict', 'feature importance', 'SHAP values', 'explain this prediction').

Remove the trailing ellipsis and the broken 'Build this skill enables AI assistant' phrasing so the description reads as a single concise, declarative statement.

Dimension	Reasoning	Score
Specificity	The description names the domain ('interpretability and explainability for machine learning models') and a few action-like phrases ('explanations for model predictions, insights into feature importance, or help understanding model behavior'), but offers no concrete techniques such as SHAP or LIME. It is not the vague level-1 ('Helps with documents') yet it falls short of listing multiple specific concrete actions required for a 3.	2 / 3
Completeness	It states what the skill does and includes a 'when' clause, but the trigger guidance is largely vacuous ('Use when appropriate context detected. Trigger with relevant phrases based on skill purpose'). The only semi-explicit triggers appear mid-sentence and are not clearly actionable, so it does not clearly answer 'when' at the level-3 standard.	2 / 3
Trigger Term Quality	It includes some natural phrases a user might say ('explanations for model predictions', 'insights into feature importance', 'help understanding model behavior'), but then pads these with vacuous filler ('Use when appropriate context detected. Trigger with relevant phrases based on skill purpose'). It misses common variations a user would actually say (e.g., 'SHAP', 'feature importance', 'why did the model predict X'), so it cannot reach 3.	2 / 3
Distinctiveness Conflict Risk	The 'machine learning model interpretability and explainability' niche is reasonably distinct and unlikely to conflict with unrelated skills, but the generic trigger language ('appropriate context detected') weakens distinctiveness. It is somewhat specific but could still overlap with general ML/data-analysis skills, matching the level-2 anchor.	2 / 3
	Total	8 / 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
Path: plugins/ai-ml/model-explainability-tool/skills/explaining-machine-learning-models/SKILL.md
Commit: 15940c5

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.