explaining-machine-learning-models

Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.

Quality

68%

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 ./bundled/skills/explaining-machine-learning-models/SKILL.md

Quality

Content

52%

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

The SKILL.md is concise and well-sectioned but fails to operationalize its own bundle: no executable examples, no ordered explanation workflow, and no navigation to the bundled scripts/assets/references that actually exist. It reads as a positioning overview rather than actionable guidance.

Suggestions

Add a concrete usage example or command for the bundled scripts (e.g. `python scripts/explain_model.py --model model.pkl --data X.csv`) to lift actionability.

Provide a numbered explanation workflow with a validation checkpoint (e.g. verify SHAP values against feature importance before reporting) to improve workflow_clarity.

Link the actual bundle files from the body (scripts/explain_model.py, scripts/feature_importance.py, assets/example_explanation.json) so progressive disclosure surfaces the real resources.

Dimension	Reasoning	Score
Conciseness	The body is lean with sectioned lists, no padding or explanation of concepts Claude already knows, and every line carries information; matches the score-3 lean-and-efficient anchor.	3 / 3
Actionability	Despite bundled scripts, the body offers no executable code, commands, or concrete invocation guidance — only descriptive bullets like 'Identify the most important features' and pointer-style 'Not For' redirects to other skills.	1 / 3
Workflow Clarity	When/Not-For/Outputs sections provide a light sequence, but there is no ordered workflow with validation checkpoints for the explanation process; checkpoints are absent or only implicit.	2 / 3
Progressive Disclosure	The body never references the real bundle files (scripts/explain_model.py, assets/, references/); the only links are informal 'use scikit-learn'/'use shap' skill redirects, leaving actual bundled resources un-signaled and disconnected.	1 / 3
	Total	7 / 12 Passed

Description

85%

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 description with concrete actions, an explicit trigger clause, and explicit boundary statements that sharply reduce conflict risk. Trigger-term coverage could be broadened with more user-natural phrasings.

Suggestions

Add user-natural trigger phrases like 'why did the model predict X', 'explain a prediction', or 'SHAP values' alongside the technical terminology to improve trigger_term_quality.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'feature attribution', 'local explanations', and 'behavior summaries' — directly analogous to the score-3 anchor's enumerated action list.	3 / 3
Completeness	Answers 'what' (feature attribution, local explanations, behavior summaries) and 'when' via the explicit 'Use as an explicit/manual helper once a model already exists' trigger clause.	3 / 3
Trigger Term Quality	Relevant terms like 'feature attribution' and 'local explanations' are present, but common user phrasings ('explain a prediction', 'why did the model predict X', 'SHAP values') are only partially covered.	2 / 3
Distinctiveness Conflict Risk	The explicit boundaries ('not for training ownership, leakage auditing, or general ML strategy selection') carve a clear niche that distinguishes it from adjacent ML skills.	3 / 3
	Total	11 / 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: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/explaining-machine-learning-models/SKILL.md
Commit: f627ab5

Reviewed: about 8 hours 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.