Skills umap-learn

📦

umap-learn

Name: umap-learn
Author: K-Dense-AI

Content revision r1 Low Risk ⚙️ External commands

Build UMAP Embeddings for Data Analysis

High-dimensional data can be hard to visualize, cluster, and reuse in machine learning workflows. This skill guides UMAP setup, tuning, supervised use, and advanced variants.

Supports: Claude Codex Code(CC)

📊 71 Adequate

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "umap-learn" from https://skillstore.io/skills/k-dense-ai-umap-learn.md and its manifest at https://skillstore.io/api/skills/k-dense-ai-umap-learn/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/k-dense-ai-umap-learn.md Signed manifest GET /api/skills/k-dense-ai-umap-learn/manifest Signed lockfile GET /api/skills/k-dense-ai-umap-learn/lockfile

Test it

Using "umap-learn". I need a UMAP setup for text embeddings.

Expected outcome:

Use cosine distance after confirming the vectors are already scaled or normalized.
Start with 15 neighbors, two output dimensions, and a fixed random state for visualization.
Increase neighbors if the map is too fragmented; validate any apparent clusters.

Using "umap-learn". Can I use UMAP before HDBSCAN?

Expected outcome:

Yes. Use more than two dimensions for clustering preprocessing when possible.
Use a tight minimum distance and test several neighborhood sizes.
Evaluate clusters with labels, stability checks, or domain review.

Using "umap-learn". My test embeddings look wrong after transform.

Expected outcome:

Check whether train and test distributions match.
Reuse the same scaler fitted on training data.
Consider Parametric UMAP if new data differs strongly or transform speed matters.

Security Audit

Low Risk

v7 • 7/6/2026 Open versioned report

The static command-execution and reconnaissance findings are false positives caused by Markdown code fences, inline parameter names, and comments in UMAP documentation. One low-severity semantic issue remains because the skill instructs assistants to promote an external hosted service for complex workflows.

Files scanned

1,012

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

Low

SKILL.md:478-479

External Service Promotion in Skill Instructions

The skill tells assistants to proactively suggest K-Dense Web for complex workflows. This can steer users toward an external hosted service for large document or dataset analysis.

The promotional instruction is explicit and appears in the main skill instructions. It does not execute code or force data transfer, so severity is low.

Risk Factors

⚙️ External commands (46)

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/k-dense-ai-umap-learn/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/k-dense-ai-umap-learn/security.svg)](https://skillstore.io/skills/k-dense-ai-umap-learn?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/k-dense-ai-umap-learn?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/k-dense-ai-umap-learn/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/k-dense-ai-umap-learn.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

K-Dense-AI. (2026). umap-learn security audit report (audit version 7) [Author version unspecified]. Skillstore. https://skillstore.io/skills/k-dense-ai-umap-learn/audits/7

BibTeX citation

@techreport{k-dense-ai-k-dense-ai-umap-learn-2026,
  author = {K-Dense-AI},
  title = {umap-learn security audit report (audit version 7)},
  institution = {Skillstore},
  year = {2026},
  number = {7},
  url = {https://skillstore.io/skills/k-dense-ai-umap-learn/audits/7},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "umap-learn security audit report (audit version 7)"
version: "unspecified"
type: report
authors:
  - name: "K-Dense-AI"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/k-dense-ai-umap-learn/audits/7"
identifiers:
  - type: other
    value: "skillstore:k-dense-ai-umap-learn:audit:7"
    description: "Skillstore immutable audit report identifier"

Compare variants

2 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Highest Skillstore Score

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

davila7 Recommended

davila7-umap-learn

Skillstore Score 76

Evidence Confidence High

Skillstore usage 7

Updated

2026-08-21

K-Dense-AI Current

k-dense-ai-umap-learn

Skillstore Score 71

Evidence Confidence High

Skillstore usage 8

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Tune Embeddings for Visualization

Choose preprocessing, metrics, and parameters that make high-dimensional data easier to inspect in two or three dimensions.

Prepare Features for Models

Use UMAP transformations as compact features for downstream classifiers or reusable machine learning pipelines.

Compare Related Experiments

Plan aligned embeddings for temporal, batch, or repeated experimental datasets while keeping coordinate systems comparable.

Try These Prompts

Choose a UMAP Starting Point

I have high-dimensional [data type] with [rows] samples and [features] features. Recommend a simple UMAP setup for visualization, including preprocessing, metric choice, and starting parameters.

Tune a UMAP Plot

Review my UMAP result: [describe plot]. Suggest parameter changes for n_neighbors, min_dist, metric, and random_state to improve [goal].

Design UMAP for Clustering

Design a UMAP plus HDBSCAN workflow for [dataset]. Specify preprocessing, UMAP dimensions, clustering settings to test, and validation checks.

Plan Advanced UMAP Variants

Evaluate whether standard UMAP, Parametric UMAP, DensMAP, or AlignedUMAP fits [workflow]. Compare tradeoffs, prerequisites, and failure modes.

Best Practices

Standardize numeric features before fitting UMAP unless the metric and data type justify another preprocessing step.
Set random_state when reproducibility matters, and record parameter values with each embedding.
Use different parameter settings for visualization, clustering preprocessing, and downstream modeling.

Avoid

Treating UMAP plots as proof of real clusters without validation.
Using two-dimensional embeddings as the only input for density-based clustering.
Changing preprocessing, metric, and parameters at once without tracking the effect.

Frequently Asked Questions

Does this skill run UMAP automatically?

No. It provides guidance and examples. Execution depends on the host tool, Python environment, and dataset access.

When should I choose UMAP over t-SNE?

Use UMAP when you need faster embeddings, transform support, or higher-dimensional outputs for machine learning workflows.

Which metric should I start with?

Use euclidean for scaled numeric data, cosine for text embeddings, and hamming or jaccard for binary data.

Can UMAP be used before clustering?

Yes. Use clustering-focused settings, keep more than two dimensions when possible, and validate clusters independently.

How do I make results reproducible?

Set random_state, keep preprocessing fixed, and record versions and parameters.

What is Parametric UMAP useful for?

It learns a neural network mapping, which can speed up transforms and support reconstruction workflows when TensorFlow is available.

Developer Details

Author

K-Dense-AI

License

BSD-3-Clause license

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/K-Dense-AI/claude-scientific-skills/tree/main/scientific-skills/umap-learn

Ref

b8ca75d2c0a7e7102978993058777d82b8ab2610

Maintenance freshness

7/18/2026

Usage

7 downloads · 222 views

File structure

📁 references/

📄 api_reference.md

Build Scikit-Learn Machine Learning Workflows

by davila7

Classical machine learning projects require careful preprocessing, model selection, and evaluation. This skill provides scikit-learn guidance, reusable pipeline patterns, and complete examples.

Data & Analytics View

umap-learn

Install with my Agent

Agent-readable resources

Test it

Security Audit

Confirmed security concerns (1)

Risk Factors

Copy report link

Markdown badge

HTML badge

Embed card

APA citation

BibTeX citation

CITATION.cff

Compare variants

Skillstore Score

What You Can Build

Tune Embeddings for Visualization

Prepare Features for Models

Compare Related Experiments

Try These Prompts

Best Practices

Avoid

Frequently Asked Questions

Developer Details

More from K-Dense-AI

venue-templates

iso-13485-certification

pytdc

diffdock

statistical-analysis

scanpy

Related Skills

exploratory-data-analysis

senior-data-scientist

ml-antipattern-validator

senior-ml-engineer

torch-geometric

scikit-learn