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.

Quality

52%

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 ./plugins/ai-ml/feature-engineering-toolkit/skills/engineering-features-for-machine-learning/SKILL.md

Quality

Content

20%Weight 40%Scale 1-3

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

The body is verbose, padded with placeholder sections, and contains no executable code or commands, making it more of a descriptive brochure than actionable guidance. It also fails to point Claude to the bundled assets, scripts, and references that actually ship with the skill.

Suggestions

Replace the narrative 'How It Works' and 'Examples' with executable Python snippets (e.g., a concrete sklearn pipeline for scaling/encoding and a feature-importance call) so Claude has copy-paste-ready guidance.

Add explicit links to the real bundle files — e.g., point to assets/feature_engineering_template.py, assets/example_dataset.csv, and scripts/feature_importance_analyzer.py — instead of the placeholder 'Project documentation' and the non-existent 'feature-engineering-toolkit plugin'.

Cut filler sections ('Output', 'Resources', 'Instructions', 'Prerequisites') that restate generic behavior, and add a validation checkpoint (e.g., verify transformed data has no NaNs / expected shape before fitting) to the workflow.

Dimension	Reasoning	Score
Conciseness	The Overview re-explains what feature engineering is ('It automates the process of creating new features, selecting the most relevant ones...') and sections like 'Output' ('The skill produces structured output relevant to the task') and 'Resources' ('Project documentation') are placeholder filler, matching the level-1 verbose/padded anchor; it is not level 2 because the padding is pervasive rather than a few tighten-able spots.	1 / 3
Actionability	No executable code or commands appear anywhere; the body only describes behavior ('The skill will: 1. Generate code to create interaction terms ... (e.g., age * income)'), matching the level-1 'describes rather than instructs' anchor; it is not level 2 because even the examples are narrative descriptions, not pseudocode Claude can run.	1 / 3
Workflow Clarity	A four-step sequence exists (Analyze Requirements -> Generate Code -> Execute Task -> Provide Insights) but it is generic and lacks any validation or verification checkpoint for data-transforming operations, which the rubric caps at 2; it is not level 3 because there is no validate-fix-retry feedback loop, and not level 1 because a discernible sequence is present.	2 / 3
Progressive Disclosure	The body is sectioned (Overview, How It Works, When to Use, Examples, Best Practices) but never references the actual bundle files in assets/, scripts/, or references/ — the only 'Integration'/'Resources' pointers are to a non-existent plugin and placeholder text; it is not level 3 because the provided bundle is entirely unlinked, and not level 1 because the body itself is reasonably sectioned rather than a monolithic wall.	2 / 3
	Total	6 / 12 Passed

Description

85%Weight 40%Scale 1-3

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 is specific and complete with an explicit trigger clause, but its trigger-term coverage is narrow (only two phrases) and undermined by generic filler ('Trigger with relevant phrases based on skill purpose'). Tightening the trigger list with more natural variations would lift the weakest dimension.

Suggestions

Replace 'Trigger with relevant phrases based on skill purpose' with concrete natural phrases users actually say, e.g. 'feature engineering', 'feature selection', 'scale features', 'encode categorical variables'.

Expand the 'Use when' clause to cover common variations such as 'improve model performance', 'reduce features', or 'prepare features for training' to broaden trigger coverage.

Rephrase the awkward leading 'Execute create, select, and transform features' into clean third-person prose such as 'Creates, selects, and transforms features ...' for readability.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'create, select, and transform features' plus 'feature scaling, encoding, and importance analysis' — matching the level-3 anchor; it is not level 2 because the capability set is comprehensive rather than naming only a domain and a few actions.	3 / 3
Completeness	Explicitly answers both what (create/select/transform features, scaling, encoding, importance analysis) and when ('Use when asked to ...'), satisfying the level-3 anchor; it is not level 2 because an explicit 'Use when' trigger clause is present.	3 / 3
Trigger Term Quality	Offers only two natural phrases ('Use when asked to "engineer features" or "select features"') and then pads with the meaningless filler 'Trigger with relevant phrases based on skill purpose', so coverage of common variations is incomplete; it is not level 3 because it omits frequent variants like 'feature engineering', 'feature selection', or 'scale features'.	2 / 3
Distinctiveness Conflict Risk	Feature engineering is a recognizable ML sub-domain and the trigger phrases are specific to it, making unintended activation unlikely; it is not level 2 because the niche and triggers are distinct rather than broadly overlapping with sibling 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: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/ai-ml/feature-engineering-toolkit/skills/engineering-features-for-machine-learning/SKILL.md
Commit: c4eafaf

Reviewed: 5 days 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.