umap-learn

UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.

Quality

75%

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 ./bundled/skills/umap-learn/SKILL.md

Quality

Content

75%Weight 40%Scale 1-5

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

The content is highly actionable with comprehensive executable examples and well-structured progressive disclosure to a real reference file. It is somewhat verbose, repeating concepts Claude knows and duplicating parameter detail found in the API reference, which is the main area to tighten.

Suggestions

Trim explanations of concepts Claude already knows (e.g., 'UMAP follows scikit-learn conventions', 'UMAP uses stochastic optimization, so results will vary') to reduce token cost.

Reduce inline parameter-detail duplication with api_reference.md; keep the inline guide to effects-by-value recommendations and point to the reference for full parameter specs.

Add an explicit validation/check output step to the clustering and pipeline workflows to push workflow clarity toward 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with useful, executable code, but contains several explanations Claude already knows ('UMAP follows scikit-learn conventions', 'UMAP uses stochastic optimization') and repeats parameter detail that also lives in api_reference.md, so it could be tightened.	3 / 5
Actionability	Fully executable, copy-paste-ready code blocks throughout, covering quick start, parameter tuning, supervised/semi-supervised use, clustering with HDBSCAN, transforms, pipelines, and parametric UMAP.	5 / 5
Workflow Clarity	Numbered multi-step workflows (Typical Workflow, Clustering Workflow, ML pipeline) are clearly sequenced with concrete commands; minor gap is the absence of explicit output-validation checkpoints, though the operations are not destructive/batch enough to trigger the cap at 3.	4 / 5
Progressive Disclosure	Good structure with a clearly signaled one-level-deep reference (references/api_reference.md) in the Resources section; bulk API detail is correctly offloaded to the reference file, though some parameter guidance is duplicated inline.	4 / 5
	Total	16 / 20 Passed

Description

75%Weight 40%Scale 1-5

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 conveys concrete capabilities with strong specificity and a clear niche, but omits any explicit 'when to use' trigger guidance. Adding a 'Use when...' clause and synonyms like 'UMAP', 'embedding', and 't-SNE' would raise trigger-term quality and completeness.

Suggestions

Add an explicit 'Use when...' clause naming the user situations that should trigger this skill (e.g., 'Use when reducing high-dimensional data for visualization, clustering, or as ML preprocessing').

Include natural synonyms users actually say — 'UMAP', 'embedding', 't-SNE alternative' — to improve trigger-term coverage.

Keep the third-person voice and concrete action list as-is; they are already strong.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('dimensionality reduction', 'manifold learning for 2D/3D visualization', 'clustering preprocessing (HDBSCAN)', 'supervised/parametric UMAP'), giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	The 'what' is clearly stated via the listed actions, but there is no 'Use when...' clause or equivalent explicit trigger guidance for when Claude should invoke the skill, which caps completeness at 3.	3 / 5
Trigger Term Quality	Good coverage of natural terms (dimensionality reduction, manifold learning, visualization, clustering, HDBSCAN), but missing common synonyms a user might say such as 'UMAP', 'embedding', or 't-SNE'.	4 / 5
Distinctiveness Conflict Risk	The description targets a clear niche (UMAP) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/umap-learn/SKILL.md
Commit: d5ae560

Reviewed: 1 day 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.