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

78%

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

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 executable examples and clear workflows, supported by a well-signaled API reference. The main weaknesses are moderate verbosity in explanatory prose and a large inline footprint that could be offloaded to additional reference files.

Suggestions

Trim the "How it works" and "Purpose" explanatory lines for each parameter and the overview definition of UMAP; keep the effects-by-value and recommendation lines, which are the actionable parts.

Move the full Parameter Tuning Guide and the Advanced Features detail into a reference file (e.g. references/advanced.md), leaving a concise summary and one-level-deep pointer in SKILL.md to improve progressive disclosure.

Add an explicit validate-then-proceed checkpoint in the clustering workflow (e.g. confirm cluster count/noise before accepting results) to push workflow clarity toward 5.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and actionable, but repeated "Purpose"/"How it works" prose, the overview definition of UMAP, and lines like "Understanding these is crucial for effective usage" are explanation Claude largely already knows and could be trimmed; this is more than minor over-explanation so it sits below a 4.	3 / 5
Actionability	Provides fully executable, copy-paste-ready code for basic usage, clustering, transform, supervised/semi-supervised, pipelines, Parametric UMAP, and inverse transforms, covering the common cases comprehensively.	5 / 5
Workflow Clarity	Clear numbered sequences (clustering: preprocess → UMAP → HDBSCAN → evaluate) with an evaluation checkpoint and a Common Issues troubleshooting feedback section; not a 5 because there are no strict validate-then-proceed gates or checklists for the more complex workflows.	4 / 5
Progressive Disclosure	Good section structure with one clearly signaled, one-level-deep reference to the verified references/api_reference.md; not a 5 because the ~500-line body inlines the full parameter-tuning guide and all advanced features that could be split into separate reference files.	4 / 5
	Total	16 / 20 Passed

Description

82%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, trigger-rich, and clearly distinct, but it omits an explicit "Use when..." trigger clause, which the rubric caps at completeness 3. Adding a concrete trigger phrase would raise the heaviest-weighted dimension.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user needs nonlinear dimensionality reduction, 2D/3D visual embeddings, or clustering preprocessing with UMAP" to satisfy the "when" half of completeness.

Optionally mention a natural alternative term like "t-SNE/PCA alternative for manifold learning or visualization" to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete named workflows — "nonlinear dimensionality reduction, 2D/3D embeddings, clustering preprocessing, supervised or semi-supervised UMAP, DensMAP, AlignedUMAP, and Parametric UMAP" — giving comprehensive coverage that matches the anchor-5 example.	5 / 5
Completeness	The "what" is clear ("Use UMAP-learn for ...") but there is no explicit "Use when..." trigger clause, so per the judging guideline a missing trigger clause caps completeness at 3; it is not a 4 because the "when" is entirely absent rather than merely weak.	3 / 5
Trigger Term Quality	Includes natural domain terms (UMAP-learn, dimensionality reduction, embeddings, clustering) plus synonyms and named variants (supervised/semi-supervised UMAP, DensMAP, AlignedUMAP, Parametric UMAP) that users would actually say.	5 / 5
Distinctiveness Conflict Risk	Targets a clear niche (UMAP-learn specifically) with distinct, specific feature triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 20 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
skill_md_line_count	SKILL.md is long (505 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/umap-learn/SKILL.md
Commit: 1e5eeff

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.