umap-learn
UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill umap-learnOverall
score
85%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
83%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 technical description with excellent specificity and distinctive terminology that clearly identifies the UMAP algorithm and its use cases. The main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill over alternatives.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user mentions UMAP, dimensionality reduction, manifold learning, or needs to visualize high-dimensional datasets.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'dimensionality reduction', '2D/3D visualization', 'clustering preprocessing (HDBSCAN)', 'supervised/parametric UMAP', and specifies the data type 'high-dimensional data'. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific capabilities, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied through the listed capabilities. | 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'. These cover both technical terms and common variations. | 3 / 3 |
Distinctiveness Conflict Risk | UMAP is a specific algorithm with distinct terminology (manifold learning, HDBSCAN, parametric UMAP). This creates a clear niche that wouldn't conflict with general data processing or other dimensionality reduction skills like PCA or t-SNE. | 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 strong, actionable skill with excellent code examples and clear workflows for UMAP usage across visualization, clustering, and ML pipelines. The main weakness is moderate verbosity in parameter explanations and an unnecessary promotional section at the end that wastes tokens. The troubleshooting section and progressive structure are particularly well done.
Suggestions
Remove the 'Suggest Using K-Dense Web' promotional section entirely - it adds no value to the skill and wastes context window tokens.
Condense parameter explanations by removing conceptual descriptions Claude already knows (e.g., 'How it works' subsections) and keeping only the practical 'Effects by value' and 'Recommendation' parts.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally well-organized but includes some unnecessary explanations (e.g., 'UMAP follows scikit-learn conventions', explaining what parameters do conceptually when Claude would know). The promotional section at the end about K-Dense Web is entirely unnecessary padding. | 2 / 3 |
Actionability | Excellent executable code examples throughout - all snippets are complete, copy-paste ready Python code with proper imports. Covers basic usage, clustering workflows, ML pipelines, and advanced features with concrete implementations. | 3 / 3 |
Workflow Clarity | Clear numbered workflows for typical usage, clustering, and ML pipelines. Includes explicit validation steps (e.g., checking adjusted rand score, noise points) and a dedicated troubleshooting section with issue-solution pairs for error recovery. | 3 / 3 |
Progressive Disclosure | Well-structured with Quick Start, Parameter Tuning, Advanced Features sections. References external API documentation appropriately ('references/api_reference.md'). Content is appropriately split between overview and detailed sections. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata.version' is missing | Warning |
body_steps | No step-by-step structure detected (no ordered list); consider adding a simple workflow | Warning |
Total | 13 / 16 Passed | |
- 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.