CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

umap-learn

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

Quality

78%

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.

A highly actionable, well-structured body with executable pinned-version code, explicit validation and error-recovery guidance, and a properly signaled one-level reference. Its main weakness is token efficiency: an introductory explanation of what UMAP is and a parameter guide that duplicates the reference file add avoidable tokens.

Suggestions

Cut the overview sentence explaining what UMAP is ('UMAP (Uniform Manifold Approximation and Projection) is a dimensionality reduction technique...') — Claude already knows this — and lead with when to apply the skill.

Compress the Parameter Tuning Guide's 'Purpose/How it works/Effects by value' prose to a compact value-range table, since the full parameter contracts already live in references/api_reference.md; drop the duplicated metric enumeration from SKILL.md.

Add a validation checkpoint (e.g. verify finite coordinates and neighborhood retention) to the Typical Workflow so the primary getting-started path matches the checkpoint quality of the clustering workflow.

DimensionReasoningScore

Conciseness

The opening paragraph explains what UMAP is — a concept Claude already knows — and the Parameter Tuning Guide's 'Purpose/How it works/Effects by value' prose plus the metric enumeration substantially duplicate the same parameter ranges and metric lists in references/api_reference.md. Most content is dense and library-specific, so it is not 2, but the redundant tutorial-style explanation and duplication could be trimmed, which fits anchor 3 rather than 4.

3 / 5

Actionability

Guidance is fully executable throughout: pinned install commands ('uv pip install umap-learn==0.5.12', 'hdbscan==0.8.44'), copy-paste-ready fit/transform/clustering/pipeline/persistence code, and a declared placeholder convention ('data is a finite samples-by-features array and labels must follow the same row order') make the examples covering the common cases directly runnable. Minor undeclared names like input_dim follow the same convention and do not constitute gaps.

5 / 5

Workflow Clarity

Multi-step processes are clearly sequenced with an explicit '4. Evaluate' step in the clustering workflow, a 'Validation:' paragraph, held-out evaluation in the ML pipeline section, and a Common Issues → Solutions recovery table. It is not 5 because the main Typical Workflow has no validation checkpoint and there are no checklists; it is well above 3 because checkpoints and error-recovery guidance are explicitly present in the substantive workflows.

4 / 5

Progressive Disclosure

Structure is good: one clearly signaled, one-level-deep reference (references/api_reference.md) whose cited sections 'AlignedUMAP Class' and 'Usage Examples' exist, with a Resources section directing when to load it. It is not 5 because the parameter and metric detail inlined in SKILL.md overlaps content that lives in the reference file; it is not 3 because references are well signaled, real, and shallow.

4 / 5

Total

16

/

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.

A specific, third-person description that comprehensively enumerates the library's capabilities and named variants, but it omits any explicit 'Use when...' trigger clause, capping its completeness. Adding trigger guidance and natural synonyms like 'visualization' or 'manifold learning' would raise the score.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user mentions UMAP, dimensionality reduction, manifold learning, embedding visualization, or clustering preprocessing on high-dimensional data.'

Add natural trigger synonyms such as 'visualization' and 'manifold learning' so the description matches how users commonly phrase the need.

Clarify the boundary against adjacent skills (e.g. t-SNE/PCA) by naming UMAP as the specific library to reach for in those situations.

DimensionReasoningScore

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 workflows' — giving comprehensive coverage of the library's surface in third-person voice. It is not 4 because the coverage of the library's distinct workflows and variants is comprehensive rather than having minor gaps.

5 / 5

Completeness

The 'what' is clear and concrete, but there is no 'Use when...' clause or equivalent explicit trigger guidance anywhere in the description, which caps completeness at 3 per the judging guidelines. It is not 4 because 'when' is entirely absent rather than merely implicit or less specific.

3 / 5

Trigger Term Quality

Good natural keywords are present ('UMAP-learn', 'dimensionality reduction', 'embeddings', 'clustering'), but common user phrasings like 'visualization', 'manifold learning', or 'visualize high-dimensional data' are missing. It is not 5 because a few natural trigger terms and synonyms are absent; it is not 3 because coverage goes beyond 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

Naming 'UMAP-learn', 'DensMAP', 'AlignedUMAP', and 'Parametric UMAP' establishes a clear niche with mostly distinct triggers. It is not 5 because generic phrases like 'clustering preprocessing' and 'embeddings' carry minor overlap risk with adjacent dimensionality-reduction or clustering skills.

4 / 5

Total

16

/

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.

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

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.