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.
31
0%
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
0%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 essentially a placeholder that restates the skill's name without providing any substantive information about capabilities, concrete actions, or meaningful trigger conditions. It would be nearly impossible for Claude to correctly select this skill from a pool of ML-related skills, as it lacks specificity, actionable trigger terms, and any clear 'what' or 'when' guidance.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Creates new features from raw data, performs one-hot encoding, generates interaction terms, handles feature scaling and normalization, selects important features using statistical methods.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about creating features, encoding categorical variables, feature selection, feature transformation, polynomial features, or preparing data columns for ML models.'
Remove the redundant duplicate trigger term and replace with diverse natural language variations users might actually say, such as 'feature creation', 'variable engineering', 'data features', 'encode columns', 'feature importance'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names a domain ('feature engineering' and 'ML Training') but provides no concrete actions whatsoever. There is no indication of what specific tasks this skill performs—no verbs like 'creates', 'transforms', 'selects', or 'encodes'. | 1 / 3 |
Completeness | The description fails to answer 'what does this do' beyond naming the category, and the 'when' clause is essentially just the skill's own name repeated. There is no explicit 'Use when...' guidance with meaningful triggers. | 1 / 3 |
Trigger Term Quality | The only trigger terms listed are 'feature engineering helper' repeated twice. There are no natural user keywords like 'feature selection', 'one-hot encoding', 'feature transformation', 'create features', 'data preprocessing', etc. | 1 / 3 |
Distinctiveness Conflict Risk | The description is extremely generic within the ML domain. 'Feature engineering helper' could overlap with data preprocessing, data transformation, or any ML pipeline skill. Nothing distinguishes it from related skills. | 1 / 3 |
Total | 4 / 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 shell—a template placeholder that contains no actual feature engineering content whatsoever. It repeatedly references 'feature engineering helper' without defining any techniques, providing any code, or offering any actionable guidance. It fails on every dimension because it is purely meta-description with zero substance.
Suggestions
Add concrete, executable code examples for common feature engineering tasks (e.g., one-hot encoding, scaling, datetime feature extraction, handling missing values) using pandas/sklearn.
Define a clear workflow for feature engineering: data inspection → feature creation → validation → integration into a pipeline, with explicit validation steps.
Remove all the boilerplate 'When to Use' and 'Example Triggers' sections and replace them with actual techniques, patterns, and best practices for feature engineering.
Include specific examples showing input data and expected transformed output to make the skill actionable and copy-paste ready.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is entirely filler and boilerplate. It repeats 'feature engineering helper' 9 times without providing any actual knowledge, techniques, or code. Every token is wasted on meta-description rather than actionable content. | 1 / 3 |
Actionability | There is zero concrete guidance—no code, no commands, no specific feature engineering techniques, no examples of transformations, encodings, or pipelines. It only describes what the skill claims to do without actually doing it. | 1 / 3 |
Workflow Clarity | No workflow, steps, or process is defined. The skill claims to provide 'step-by-step guidance' but contains none. There are no validation checkpoints or sequences of any kind. | 1 / 3 |
Progressive Disclosure | The content is a flat, monolithic block of vague descriptions with no references to detailed materials, no links to examples, and no structured navigation to deeper content. | 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
3076d78
- 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.