umap-learn

Use UMAP-learn for nonlinear dimensionality reduction, 2D/3D embeddings, clustering preprocessing, supervised or semi-supervised UMAP, DensMAP, AlignedUMAP, and Parametric UMAP workflows.

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 ./skills/umap-learn/SKILL.md

Quality

Content

78%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 body is highly actionable with executable examples and good progressive disclosure that pushes detail to a real reference file. Its main weakness is mild verbosity in prose framing that assumes less of Claude than necessary.

Suggestions

Trim introductory filler sentences like 'Understanding these is crucial for effective usage' and other restatements of why a parameter matters, letting the effects-by-value lists stand on their own.

Add explicit validation checkpoints in the clustering and ML-pipeline workflows (e.g. evaluate intermediate embedding quality before downstream clustering) to strengthen workflow clarity.

Consolidate repeated preprocessing/standardization guidance into a single concise note rather than restating it across the Quick Start and Typical Workflow sections.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and code-forward, but contains some over-explanation Claude does not need (e.g. 'Understanding these is crucial for effective usage' and repeated prose restating that standardization is essential), which could be tightened.	3 / 5
Actionability	Abundant copy-paste-ready, executable code covering common cases — basic usage, clustering, transform, sklearn pipelines, Parametric UMAP, inverse transform, and custom architectures — with specific parameter recipes and install commands.	5 / 5
Workflow Clarity	Multi-step workflows are clearly sequenced (numbered clustering and ML-pipeline examples), but validation checkpoints are implicit rather than gated, with no explicit error-recovery feedback loops.	4 / 5
Progressive Disclosure	Well-organized sections with bulk API detail offloaded to the real, clearly signaled one-level-deep references/api_reference.md (with named sections 'AlignedUMAP Class' and 'Usage Examples'); the referenced file exists and navigation is easy.	5 / 5
	Total	17 / 20 Passed

Description

71%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 is specific and rich in capability enumeration with good natural trigger terms, but it omits any explicit 'when to use' guidance, which limits completeness. Adding a 'Use when...' clause would raise the completeness and distinctiveness scores.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when reducing high-dimensional data for visualization, clustering preprocessing, or supervised/semi-supervised embeddings.'

Include a lay synonym like 'visualization' alongside the technical terms to broaden natural trigger coverage.

Mention the common user phrasings (e.g. 'UMAP embeddings', '2D scatter plot of high-dimensional data') to improve trigger-term quality from 4 to 5.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete capabilities — 'nonlinear dimensionality reduction, 2D/3D embeddings, clustering preprocessing, supervised or semi-supervised UMAP, DensMAP, AlignedUMAP, and Parametric UMAP' — giving comprehensive coverage of the library's workflows.	5 / 5
Completeness	A clear and thorough 'what' is present, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Strong natural terms ('dimensionality reduction', 'embeddings', 'clustering preprocessing', 'DensMAP', 'AlignedUMAP', 'Parametric UMAP') that users would say, though a few common synonyms like 'visualization' are absent.	4 / 5
Distinctiveness Conflict Risk	'UMAP-learn' plus named sub-workflows (DensMAP, AlignedUMAP, Parametric UMAP) carves a clear niche with low conflict risk, though the missing trigger clause slightly weakens phrasing-based distinguishability.	4 / 5
	Total	16 / 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: K-Dense-AI/scientific-agent-skills
Path: skills/umap-learn/SKILL.md
Commit: 49c6e97

Reviewed: 9 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.