umap-learn
UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.
87
83%
Does it follow best practices?
Impact
89%
2.11xAverage score across 6 eval scenarios
Passed
No known issues
Quality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong, technically specific description that clearly identifies the skill's domain and capabilities with excellent trigger terms for its target audience. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The description is concise and avoids fluff, using appropriate third-person voice.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about UMAP, dimensionality reduction, embedding high-dimensional data, or visualizing clusters.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: dimensionality reduction, 2D/3D visualization, clustering preprocessing with HDBSCAN, supervised/parametric UMAP. These are concrete, well-defined capabilities. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific capabilities, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. Per rubric guidelines, missing 'Use when' caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'UMAP', 'dimensionality reduction', 'manifold learning', '2D/3D visualization', 'clustering', 'HDBSCAN', 'high-dimensional data', 'supervised', 'parametric'. Good coverage of terms a data scientist would use. | 3 / 3 |
Distinctiveness Conflict Risk | UMAP is a very specific algorithm/technique with distinct terminology (manifold learning, HDBSCAN, parametric UMAP). This is unlikely to conflict with other skills given its narrow, well-defined niche. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill with excellent executable code examples covering the full range of UMAP use cases. Its main weakness is verbosity — the parameter tuning section and conceptual explanations could be condensed significantly (e.g., into tables) since Claude doesn't need explanations of what 'local vs global structure' means or how neighborhood sizes work conceptually. Despite the length, the organization and progressive disclosure are strong.
Suggestions
Condense the parameter tuning section into a compact table format (parameter | values | effect | recommendation) instead of verbose prose explanations for each parameter.
Remove conceptual explanations Claude already knows, such as 'Controls the size of the local neighborhood UMAP examines when learning manifold structure' and the overview paragraph explaining what UMAP is.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some unnecessary explanations that Claude would already know (e.g., explaining what UMAP stands for, what dimensionality reduction is, how n_neighbors 'works' conceptually). The parameter tuning section is verbose with 'How it works' explanations that could be condensed into a table. The content could be significantly tightened while preserving all actionable information. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste ready code examples throughout — from basic usage to clustering workflows, ML pipeline integration, parametric UMAP, and inverse transforms. Specific parameter values are given with concrete use-case recommendations, and all code follows real library conventions. | 3 / 3 |
Workflow Clarity | Multi-step workflows are clearly numbered and sequenced (preprocessing → UMAP fitting → clustering → evaluation). The clustering workflow includes an evaluation step with metrics, and the ML pipeline section properly demonstrates train/test splitting with consistent preprocessing. The troubleshooting section provides clear problem→solution mappings for common failure modes. | 3 / 3 |
Progressive Disclosure | Content is well-structured with a clear progression from Quick Start → Parameter Tuning → Supervised/Semi-Supervised → Clustering → Advanced Features. The references section points to a single level of additional documentation (api_reference.md). Advanced topics like Parametric UMAP and AlignedUMAP are appropriately placed at the end. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
086de41
- 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.