umap-learn

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

Quality

70%

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 ./backend/cli/skills/coding/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 content is highly actionable with comprehensive executable examples and clear workflow sequencing, supported by a real one-level-deep reference file. Its main weakness is conciseness — tutorial prose and duplicated parameter detail inflate the body beyond what Claude needs.

Suggestions

Trim tutorial prose and remove concepts Claude already knows (e.g., the UMAP acronym expansion, the note that optimization is stochastic) to improve token efficiency.

Move the bulk of the Parameter Tuning Guide and metric enumeration into references/api_reference.md, leaving SKILL.md a lean overview with a pointer, to reduce duplication with the reference file.

Add explicit validation/retry checkpoints in the clustering and ML-pipeline workflows (e.g., verify embedding shape and noise-point ratio before fitting HDBSCAN) to strengthen workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is lengthy (~470 lines) with tutorial-style prose re-explaining concepts Claude already knows (e.g., what UMAP is, that it is stochastic) and duplicating parameter detail from the reference file, matching the 'mostly efficient but includes some unnecessary explanation' anchor.	3 / 5
Actionability	Provides numerous copy-paste ready, executable code blocks covering common cases (quick start, tuning recipes, clustering, transform, pipelines, parametric/inverse UMAP), matching the 'fully executable; specific examples cover common cases' anchor.	5 / 5
Workflow Clarity	Multi-step workflows are clearly numbered (clustering steps 1-4, ML pipeline) with evaluation outputs, but explicit validate->fix->retry checkpoints are mostly implicit, matching the 'clear sequence with most checkpoints; minor validation gaps' anchor.	4 / 5
Progressive Disclosure	A real references/api_reference.md bundle exists and is clearly signaled in a Resources section, but the SKILL.md body inlines substantial API parameter detail that overlaps the reference file, matching the 'good structure; minor organization gaps' anchor rather than 5.	4 / 5
	Total	16 / 20 Passed

Description

66%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 well-targeted to UMAP's niche with strong trigger terms, but it lacks an explicit 'Use when...' trigger clause, which caps completeness. It is concise and avoids fluff.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when reducing high-dimensional data for visualization, clustering preprocessing, or supervised/parametric embeddings') to raise completeness above 3.

Include common synonyms and file extensions (e.g., 'manifold learning', 't-SNE alternative', '.npy/.npz arrays') to broaden trigger-term coverage.

Lead with a single verb-led action phrase ('Reduces high-dimensional data...') to sharpen specificity from fragmentary use-cases to comprehensive concrete actions.

Dimension	Reasoning	Score
Specificity	Names the UMAP domain and several concrete use-cases (2D/3D visualization, clustering preprocessing via HDBSCAN, supervised/parametric UMAP), matching the 'lists several specific actions; minor gaps' anchor; not a 5 because the actions are fragmentary use-cases rather than crisp comprehensive verb-led actions.	4 / 5
Completeness	Clearly answers 'what' but 'when' is only weakly implied via use-case enumeration with no explicit 'Use when...' trigger clause, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms a user would say ('dimensionality reduction', '2D/3D visualization', 'clustering', 'HDBSCAN', 'high-dimensional data'); not a 5 because it lacks synonyms and file extensions, and not a 3 because multiple natural phrases are present.	4 / 5
Distinctiveness Conflict Risk	UMAP/HDBSCAN/parametric UMAP is a clear niche with distinct triggers and minimal conflict risk; slight overlap with general clustering skills keeps it just below the unambiguous 5 anchor.	4 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/coding/umap-learn/SKILL.md
Commit: 3a6c3a9

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.