engineering-features-for-machine-learning
Execute create, select, and transform features to improve machine learning model performance. Handles feature scaling, encoding, and importance analysis. Use when asked to "engineer features" or "select features". Trigger with relevant phrases based on skill purpose.
45
33%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/ai-ml/feature-engineering-toolkit/skills/engineering-features-for-machine-learning/SKILL.mdQuality
Discovery
67%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 covers the basics of what the skill does and when to use it, earning credit for having an explicit 'Use when' clause. However, it is weakened by the meaningless filler sentence 'Trigger with relevant phrases based on skill purpose' which adds no information, and the trigger terms could be more comprehensive to cover natural user language variations. The specificity of actions is moderate but could list more concrete operations.
Suggestions
Remove the vague filler sentence 'Trigger with relevant phrases based on skill purpose' and replace it with additional concrete trigger terms like 'feature extraction', 'one-hot encoding', 'normalization', 'PCA', 'dimensionality reduction'.
Expand the 'Use when' clause to include more natural user phrases such as 'preprocess data for ML', 'reduce features', 'encode categorical variables', or 'analyze feature importance'.
List more specific concrete actions (e.g., 'generate polynomial features, apply one-hot or label encoding, perform PCA, compute SHAP values') to better distinguish from generic ML or data preprocessing skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (feature engineering/ML) and lists some actions (create, select, transform, scaling, encoding, importance analysis), but the actions are somewhat generic within the ML domain and not deeply specific about what concrete operations are performed. | 2 / 3 |
Completeness | Clearly answers both 'what' (create, select, transform features; handles scaling, encoding, importance analysis) and 'when' (Use when asked to 'engineer features' or 'select features'). The explicit 'Use when' clause with trigger phrases is present. | 3 / 3 |
Trigger Term Quality | Includes some natural keywords like 'engineer features', 'select features', 'feature scaling', 'encoding', and 'importance analysis', but the final sentence 'Trigger with relevant phrases based on skill purpose' is vague filler that adds no value. Missing common variations like 'feature extraction', 'one-hot encoding', 'normalization', 'feature importance', 'dimensionality reduction'. | 2 / 3 |
Distinctiveness Conflict Risk | Reasonably specific to feature engineering within ML, but could overlap with general ML/data science skills or data preprocessing skills. The phrase 'improve machine learning model performance' is broad enough to conflict with model tuning or hyperparameter optimization skills. | 2 / 3 |
Total | 9 / 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 almost entirely abstract description with no actionable content. It explains concepts Claude already understands (feature engineering, scaling, encoding), describes its own reasoning process back to itself, and provides no executable code, specific commands, or concrete API references for the 'feature-engineering-toolkit plugin' it claims to use. Multiple sections are generic filler that could apply to any skill.
Suggestions
Replace the abstract 'How It Works' and examples with actual executable Python code showing how to use the feature-engineering-toolkit plugin for specific tasks (e.g., creating interaction terms, running SelectKBest).
Remove sections that explain concepts Claude already knows (what feature scaling is, what encoding is, what feature engineering does) and replace with specific API calls, function signatures, and parameter options.
Remove generic placeholder sections ('Instructions', 'Output', 'Error Handling', 'Resources') that contain no specific information, or populate them with concrete details.
Add validation checkpoints to the workflow, such as verifying data shape after transformations, checking for NaN values after feature creation, and confirming feature importance scores before selection.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive explanation of concepts Claude already knows (what feature engineering is, how ML models work, what scaling/encoding are). The 'How It Works' section describes Claude's own reasoning process back to it. Sections like 'Instructions', 'Output', 'Error Handling', and 'Resources' are vague filler that add no actionable value. The 'When to Use This Skill' section largely repeats the overview. | 1 / 3 |
Actionability | No executable code, no concrete commands, no specific library calls or API references. Examples describe what 'the skill will do' in abstract terms rather than providing actual Python code. The 'Instructions' section is entirely generic ('Invoke this skill when trigger conditions are met'). References to a 'feature-engineering-toolkit plugin' are never concretized with actual usage patterns or API calls. | 1 / 3 |
Workflow Clarity | The 'How It Works' section lists abstract meta-steps (analyzing, generating, executing, providing insights) rather than concrete operational steps. No validation checkpoints, no error recovery loops, no specific commands to run. The examples describe outcomes but not actual step-by-step procedures with verification. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. No bundle files exist to support progressive disclosure. Content is poorly organized with redundant sections (Overview, When to Use, How It Works all overlap). Generic placeholder sections like 'Resources' point to nothing specific. | 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 | |
- Commit
3a2d27d
- Reviewed
Table of Contents
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.