feature-engineering-helper
Feature Engineering Helper - Auto-activating skill for ML Training. Triggers on: feature engineering helper, feature engineering helper Part of the ML Training skill category.
34
Quality
3%
Does it follow best practices?
Impact
86%
1.07xAverage 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-engineering-helper/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 just restating the skill name without explaining capabilities or use cases. It provides no actionable information for Claude to determine when to select this skill over others. The redundant trigger terms and missing concrete actions make this description nearly useless for skill selection.
Suggestions
Add specific concrete actions like 'Creates polynomial features, handles missing value imputation, encodes categorical variables, scales numerical features, generates interaction terms'
Replace redundant trigger terms with natural user phrases: 'feature creation', 'transform columns', 'encode categories', 'scale features', 'create dummy variables', 'binning'
Add explicit 'Use when...' clause: 'Use when preparing data for machine learning models, creating new features from existing columns, or when user mentions feature engineering, data transformation, or preprocessing for ML'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description only names the domain ('Feature Engineering Helper') but provides no concrete actions. There are no specific capabilities listed like 'create polynomial features', 'handle missing values', or 'encode categorical variables'. | 1 / 3 |
Completeness | The description fails to answer 'what does this do' beyond the name, and provides no explicit 'when to use' guidance. The 'Triggers on' section just repeats the skill name rather than describing actual use cases. | 1 / 3 |
Trigger Term Quality | The trigger terms are redundant ('feature engineering helper' listed twice) and overly specific to the skill name itself. Missing natural user terms like 'create features', 'transform variables', 'feature selection', 'data preprocessing', or 'ML features'. | 1 / 3 |
Distinctiveness Conflict Risk | While 'feature engineering' is a specific ML subdomain, the lack of detail about what specific feature engineering tasks it handles could cause overlap with general ML or data preprocessing skills. The category mention helps slightly. | 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 an empty template/placeholder that provides zero actionable content. It describes what a feature engineering skill should do without actually teaching anything about feature engineering. The entire content is meta-description and trigger examples rather than actual guidance, code, or techniques.
Suggestions
Add concrete feature engineering techniques with executable code examples (e.g., handling missing values, encoding categorical variables, feature scaling, creating interaction features)
Include specific workflows for common feature engineering tasks like 'For tabular data: 1. Analyze distributions, 2. Handle nulls, 3. Encode categoricals, 4. Scale numerics'
Provide actual code snippets using pandas/sklearn for common transformations instead of claiming to 'generate production-ready code'
Remove the meta-description sections ('Purpose', 'Capabilities', 'Example Triggers') and replace with actual instructional content
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is extremely verbose with no actual substance. It repeats 'feature engineering helper' 9 times without providing any concrete information about what feature engineering actually involves or how to do it. | 1 / 3 |
Actionability | No concrete code, commands, or specific guidance provided. The skill only describes what it claims to do ('provides step-by-step guidance', 'generates production-ready code') without actually providing any of it. | 1 / 3 |
Workflow Clarity | No workflow, steps, or process defined. The content is purely meta-description about the skill's supposed capabilities rather than actual instructions for feature engineering tasks. | 1 / 3 |
Progressive Disclosure | No structure for discovery or navigation. No references to detailed materials, examples, or related documentation. The content is a shallow placeholder with no depth to disclose. | 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
f17dd51
- 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.