CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

64

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/umap-learn/SKILL.md
SKILL.md
Quality
Evals
Security

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 body is highly actionable with comprehensive executable examples and good file-based progressive disclosure, but it carries some conceptual padding and advisory rather than explicit validation checkpoints that keep conciseness and workflow clarity from the top score.

Suggestions

Trim general conceptual restatements (the UMAP definition in the Overview and 'Understanding these is crucial' framing) since Claude already knows these.

Convert advisory caveats for the clustering/pipeline workflows into explicit validate→fix→retry steps so the feedback loops are unmistakable.

DimensionReasoningScore

Conciseness

Mostly efficient and code-heavy, but includes some unnecessary prose Claude already knows (e.g., the UMAP definition in the Overview, 'Understanding these is crucial for effective usage') and repeated Recommendation sections that could be tightened.

3 / 5

Actionability

Provides fully executable, copy-paste-ready code covering the common cases — basic usage, clustering with HDBSCAN, transform, supervised/semi-supervised, Parametric UMAP, AlignedUMAP, and inverse transforms.

5 / 5

Workflow Clarity

Multi-step workflows (clustering, ML pipeline integration) are clearly numbered with most checkpoints present, and 'Common Issues and Solutions' provides recovery guidance, though validation is advisory rather than explicit validate→retry loops.

4 / 5

Progressive Disclosure

Bulk API detail is offloaded to references/api_reference.md, which is correctly signaled in a '### references/' section one level deep; the body itself is large with some inlined content that could be further split.

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 is specific and distinctive, listing a comprehensive set of concrete UMAP capabilities, but it lacks an explicit 'when to use' trigger clause, which caps its completeness score.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when the user asks for dimensionality reduction, embeddings, or visualization of high-dimensional data').

Include common synonyms and alternative phrasings users might say, such as 'manifold learning', 'visualization', or 't-SNE alternative'.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — 'nonlinear dimensionality reduction, 2D/3D embeddings, clustering preprocessing, supervised or semi-supervised UMAP, DensMAP, AlignedUMAP, and Parametric UMAP workflows' — giving comprehensive coverage.

5 / 5

Completeness

The 'what' is clear and detailed, but there is no 'Use when...' clause or equivalent explicit trigger guidance; per the rubric this caps completeness at 3.

3 / 5

Trigger Term Quality

Includes natural keywords (UMAP, dimensionality reduction, embeddings, clustering, 2D/3D) but misses common synonyms users might say such as 'visualization', 'manifold learning', or 't-SNE alternative'.

4 / 5

Distinctiveness Conflict Risk

Names UMAP-specific workflows (DensMAP, AlignedUMAP, Parametric UMAP) giving it a clear niche with minimal overlap risk against other skills.

5 / 5

Total

17

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
K-Dense-AI/scientific-agent-skills
Reviewed

Table of Contents

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.