running-clustering-algorithms

Analyze datasets by running clustering algorithms (K-means, DBSCAN, hierarchical) to identify data groups. Use when requesting "run clustering", "cluster analysis", or "group data points". 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

35%

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

The body is an abstract, prose-level overview that describes rather than instructs: it contains no executable code and does not reference the bundled scripts or assets that would provide concrete guidance. It is padded with generic skill-templating sections (Instructions, Output, Resources, Prerequisites) that add little, and its workflow lacks validation checkpoints.

Suggestions

Reference and use the bundled scripts (e.g. scripts/run_kmeans.py, scripts/cluster_evaluator.py) and assets (assets/config_template.json, assets/example_data.csv) with concrete invocation examples instead of describing them in prose.

Add an actual executable code snippet (e.g. a scikit-learn K-means call with silhouette evaluation) so guidance is copy-paste ready rather than abstract.

Replace the vacuous Instructions/Output/Resources/Prerequisites boilerplate with lean, skill-specific guidance, and add an explicit validate-results checkpoint (e.g. check silhouette score before reporting clusters) to the workflow.

Dimension	Reasoning	Score
Conciseness	Real domain guidance is interspersed with generic boilerplate ('This skill empowers Claude to perform clustering analysis', 'The skill produces structured output relevant to the task.', '1. Invoke this skill when the trigger conditions are met') that could be cut; not as padded as a concept-explaining wall of text, but clearly not lean.	2 / 3
Actionability	There is no executable code or commands anywhere; examples describe abstractly ('The skill will: 1. Load the customer_data.csv dataset. 2. Perform K-means clustering...') and the bundled runnable scripts in scripts/ are never referenced, matching the 'describes rather than instructs' anchor.	1 / 3
Workflow Clarity	A sequenced process is present ('1. Analyzing the Context ... 4. Providing Results'), but there are no explicit validation checkpoints or a validate-fix-retry feedback loop; error handling is vague ('Invalid input: Prompts for correction').	2 / 3
Progressive Disclosure	The body has section structure but never links to the bundled files (run_kmeans.py, run_dbscan.py, run_hierarchical.py, data_loader.py, cluster_evaluator.py, config_template.json, example_data.csv, clustering_visualization.py), so content that should live in those references is instead described vaguely inline.	2 / 3
	Total	7 / 12 Passed

Description

100%

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 strong: it states a concrete capability, lists natural trigger phrases, and provides an explicit 'Use when' clause, cleanly answering both what and when. Its only blemish is the trailing generic phrase 'Trigger with relevant phrases based on skill purpose,' which is filler that adds nothing.

Suggestions

Remove the vacuous trailing phrase 'Trigger with relevant phrases based on skill purpose.' since the 'Use when...' clause already provides explicit triggers.

Consider adding common user phrasings such as 'segment data' or 'K-means clustering' to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names concrete algorithms ('K-means, DBSCAN, hierarchical') and a clear analytical purpose ('identify data groups') rather than vague language; comparable to the multi-action 'score 3' anchor.	3 / 3
Completeness	Explicitly answers both 'what' (analyze datasets by running clustering algorithms to identify data groups) and 'when' via a literal 'Use when requesting...' clause, the score-3 pattern.	3 / 3
Trigger Term Quality	Lists natural phrases a user would actually say ("run clustering", "cluster analysis", "group data points"), matching the 'good coverage of natural terms' anchor, though the trailing 'Trigger with relevant phrases based on skill purpose' is vacuous filler.	3 / 3
Distinctiveness Conflict Risk	Clustering is a clear niche anchored by named algorithms and domain-specific triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 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.