Feature Importance Analyzer - Auto-activating skill for ML Training. Triggers on: feature importance analyzer, feature importance analyzer Part of the ML Training skill category.
34
Quality
3%
Does it follow best practices?
Impact
90%
1.11xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./planned-skills/generated/07-ml-training/feature-importance-analyzer/SKILL.mdQuality
Discovery
7%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 severely underdeveloped, essentially serving as a placeholder rather than a functional skill description. It lacks any explanation of capabilities, concrete actions, or meaningful trigger guidance. The redundant trigger terms and absence of a 'Use when...' clause make it nearly useless for skill selection among multiple options.
Suggestions
Add specific actions the skill performs, e.g., 'Calculates and visualizes feature importance scores using SHAP values, permutation importance, and tree-based methods'
Include a 'Use when...' clause with natural trigger terms like 'which features matter', 'variable importance', 'model interpretation', 'feature selection', 'explain model predictions'
Remove the redundant trigger term and expand with user-friendly variations that people would naturally say when needing this capability
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description only names the skill ('Feature Importance Analyzer') without describing any concrete actions. There are no verbs indicating what the skill actually does - no mention of analyzing, calculating, visualizing, or any specific operations. | 1 / 3 |
Completeness | The description fails to answer 'what does this do' beyond the name itself, and provides no 'when should Claude use it' guidance. The 'Triggers on' section just repeats the skill name rather than providing meaningful trigger conditions. | 1 / 3 |
Trigger Term Quality | The trigger terms are redundant ('feature importance analyzer' listed twice) and represent technical jargon rather than natural user language. Missing common variations like 'feature selection', 'variable importance', 'which features matter', or 'model interpretation'. | 1 / 3 |
Distinctiveness Conflict Risk | The term 'Feature Importance Analyzer' is somewhat specific to ML model interpretation, which provides some distinctiveness. However, 'ML Training' category is broad and could overlap with other ML-related skills without clearer boundaries. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a placeholder template with no actual content. It describes capabilities without demonstrating any of them - no code for calculating feature importance (SHAP, permutation importance, etc.), no examples, no workflows. The content would be completely unhelpful for anyone needing to analyze feature importance.
Suggestions
Add executable code examples for common feature importance methods (e.g., SHAP values, permutation importance, tree-based feature importance)
Include a concrete workflow: load model -> compute importance -> interpret results -> visualize
Provide specific examples with sample input/output showing what feature importance analysis produces
Remove the meta-description sections ('When to Use', 'Example Triggers') and replace with actual technical guidance
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is entirely filler text with no actual technical substance. It repeats 'feature importance analyzer' multiple times without providing any concrete information Claude doesn't already know. | 1 / 3 |
Actionability | No executable code, commands, or concrete guidance provided. The content only describes what the skill claims to do without actually showing how to do anything. | 1 / 3 |
Workflow Clarity | No workflow, steps, or process defined. Claims to provide 'step-by-step guidance' but includes zero actual steps for feature importance analysis. | 1 / 3 |
Progressive Disclosure | No references to detailed materials, no code examples, no external files. The structure exists but contains no substantive content to organize. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
81%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 | |
f17dd51
Table of Contents
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.