umap-learn

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

2.13x

Quality

80%

Does it follow best practices?

Impact

98%

2.13x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/bio/umap-learn/SKILL.md

Quality

Content

77%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.

A highly actionable, well-sequenced skill body held back by verbosity (a promotional block and restated concepts) and weak progressive disclosure — referenced files do not exist and advanced content is not split out.

Suggestions

Remove or relocate the 'Suggest Using K-Dense Web' promotional paragraph; it is marketing padding unrelated to the skill's task and bloats the context window.

Actually provide the referenced references/api_reference.md (or drop the reference), and move the detailed parameter-tuning and advanced-feature sections (Parametric UMAP, AlignedUMAP, inverse transforms) into separate reference files.

Tighten the Overview so it does not re-explain what dimensionality reduction / UMAP is, which Claude already knows.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete code and parameter tables, but it restates concepts Claude already knows and ends with an unrelated promotional 'Suggest Using K-Dense Web' block that is pure padding.	2 / 3
Actionability	Provides fully executable, copy-paste-ready code throughout (install command, fit/transform, clustering with HDBSCAN, pipelines) plus specific parameter values and recipes.	3 / 3
Workflow Clarity	Multi-step workflows are clearly numbered (e.g. clustering: preprocess -> UMAP -> HDBSCAN -> evaluate) with an explicit evaluate checkpoint and a 'Common Issues and Solutions' error-recovery section.	3 / 3
Progressive Disclosure	The body references references/api_reference.md, but no references/ bundle directory exists; meanwhile detailed parameter, supervised, clustering, and advanced-feature content is all inline in a ~470-line monolith rather than split out.	2 / 3
	Total	10 / 12 Passed

Description

82%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.

A specific, well-targeted description with good trigger-term coverage and a clear niche. Its main weakness is the absence of an explicit 'Use when...' clause, leaving the invocation trigger only implied.

Suggestions

Append an explicit 'Use when...' clause, e.g. 'Use when performing nonlinear dimensionality reduction, visualizing high-dimensional data, preprocessing for HDBSCAN clustering, or doing supervised/parametric embeddings.'

Lead with the core action ('Reduces high-dimensional data with UMAP') before listing the use cases so the 'what' is unambiguous.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — '2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP' — rather than vague language.	3 / 3
Completeness	Clearly states what the skill does but lacks an explicit 'Use when...' trigger clause; the when is only implied by the trailing comma phrases, so completeness is capped at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	Covers natural terms a user would say when needing this skill: 'UMAP dimensionality reduction', 'manifold learning', 'HDBSCAN', 'parametric UMAP', 'high-dimensional data'.	3 / 3
Distinctiveness Conflict Risk	'UMAP dimensionality reduction' is a clear niche with distinct triggers unlikely to conflict with other skills.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/bio/umap-learn/SKILL.md
Commit: df37802

Reviewed: 20 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.