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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

20%

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

The body is a verbose, descriptive overview that restates concepts Claude already knows and gives no executable code or links to the bundled template, config, dataset, and analyzer scripts. It needs to be condensed into actionable guidance that points to the real bundle assets.

Suggestions

Cut the Overview, Integration, Prerequisites, Instructions, Output, Error Handling, and Resources sections that restate obvious information, and remove explanations of basic concepts (what scaling/encoding do).

Add a Quick-start section with an executable snippet (e.g. scaling + SelectKBest on the bundled dataset) and reference the assets: feature_engineering_template.py, configuration_template.yaml, example_dataset.csv, and feature_importance_analyzer.py.

Insert explicit validation checkpoints in the workflow (e.g. validate data is clean before transforming; verify selected features improve a held-out metric before committing) to close the feedback-loop gap.

Dimension	Reasoning	Score
Conciseness	The body explains basic concepts Claude already knows (what feature engineering is, why scaling matters, one-hot vs label encoding) and pads with generic sections like Overview, Integration, Prerequisites, Instructions, Output, Error Handling, and Resources that restate obvious information.	1 / 3
Actionability	It describes rather than instructs: steps like 'Generate code to create interaction terms' and 'Generate code to calculate feature importance' are abstract with no executable code or commands in the body, despite bundled executable assets existing that are never referenced.	1 / 3
Workflow Clarity	A sequence exists (Analyze, Generate, Execute, Provide Insights) and example walkthroughs are listed, but there are no validation checkpoints or feedback loops for batch/destructive feature transformations, which the rubric caps at 2.	2 / 3
Progressive Disclosure	Bundle files exist (feature_engineering_template.py, configuration_template.yaml, example_dataset.csv, feature_importance_analyzer.py) but the body never references or links to them, so navigation to the detailed materials is missing despite the structure being there.	2 / 3
	Total	6 / 12 Passed

Description

60%

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 clearly enumerates concrete feature-engineering actions but pads the trigger guidance with boilerplate and only gives two natural trigger phrases. Tightening the 'Use when' clause with more natural user phrasing would lift trigger and completeness scores.

Suggestions

Replace 'Trigger with relevant phrases based on skill purpose' with concrete natural-language triggers users would actually say (e.g. 'when the user asks to scale, encode, select, or create features for a model').

Expand trigger coverage beyond 'engineer features'/'select features' to common variations like 'feature engineering', 'feature selection', 'one-hot encoding', 'feature scaling', and 'feature importance'.

Remove redundant filler ('Execute' before 'create, select, and transform') so the description reads in clean third-person imperative voice.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('create, select, and transform features') plus specific techniques ('feature scaling, encoding, and importance analysis'), matching the level-3 anchor of multiple specific concrete actions.	3 / 3
Completeness	It states what the skill does and includes a 'Use when...' clause, but the trigger guidance is partly boilerplate ('Trigger with relevant phrases based on skill purpose') rather than concrete, so the 'when' is present but only partially explicit.	2 / 3
Trigger Term Quality	Includes the natural trigger phrases 'engineer features' and 'select features', but coverage of common variations is thin and the trailing sentence 'Trigger with relevant phrases based on skill purpose' is generic filler rather than natural user language.	2 / 3
Distinctiveness Conflict Risk	The feature-engineering niche is reasonably distinct, but the generic trailing trigger guidance weakens distinctiveness and could overlap with broader ML or data-prep skills.	2 / 3
	Total	9 / 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
Commit: 2cafb23

Reviewed: 2 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.