umap-tsne-analysis

Use when performing sample-level dimensionality reduction and visualization on abundance or OTU-style matrices with a companion group file, generating UMAP and/or t-SNE coordinates and plots for group separation assessment. NOT for: differential expression testing, single-cell workflows requiring dedicated embeddings pipelines, or analyses without a sample grouping file.

Quality

73%

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 ./awesome-med-research-skills/Data Analysis/umap-tsne-analysis/SKILL.md

Quality

Content

60%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 well-structured and actionable with clear reference navigation, but it is padded with concept re-explanations, duplicated tables, and self-referential checklists, and it references several bundle paths that do not exist. Tightening and fixing the missing references would lift the score meaningfully.

Suggestions

Cut the Methods section's definitional prose about t-SNE/UMAP (Claude already knows these) and the duplicated Dependency Baseline table that already lives in cli-guide.md; keep only parameter interpretation.

Remove or condense the Implementation Checklist, which is build-process metadata rather than runtime guidance for Claude.

Fix broken references: either add tests/data/, tests/test_skill.R, and dependencies.lock.tsv to the bundle, or drop the references from the body.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: the Methods section re-explains what t-SNE/UMAP are (concepts Claude knows), the Dependency Baseline table duplicates references/cli-guide.md, the Implementation Checklist is self-referential metadata, and Examples restate the Usage block.	2 / 5
Actionability	Provides copy-paste-ready Rscript commands, a complete argument table, and executable examples, but references tests/data/, dependencies.lock.tsv, and tests/test_skill.R that do not exist in the bundle.	4 / 5
Workflow Clarity	Clear four-step Validate -> Prepare -> Run -> Visualize sequence with input validation in Step 1 and an error-handling table with a feedback loop to troubleshooting.md; minor gap is the lack of an explicit verify-output checkpoint in the agent-facing sequence.	4 / 5
Progressive Disclosure	The 'When to Read External Files' table clearly signals one-level-deep references to real files (algorithm.md, cli-guide.md, troubleshooting.md, main.R), but body references to tests/data/ and dependencies.lock.tsv are broken (files absent).	4 / 5
	Total	14 / 20 Passed

Description

87%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 strong: it states concrete capabilities, natural trigger terms, an explicit use-when clause, and clear negative boundaries that distinguish it from adjacent bioinformatics skills. Only minor specificity and keyword-synonym gaps keep it from being a top example.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('dimensionality reduction', 'visualization', 'generating UMAP and/or t-SNE coordinates and plots for group separation assessment') tied to a specific domain, but does not enumerate as many distinct actions as the 5-anchor example.	4 / 5
Completeness	Explicitly answers both 'what' ('performing... generating UMAP and/or t-SNE coordinates and plots') and 'when' ('Use when performing... with a companion group file') with concrete trigger phrases, plus an explicit 'NOT for' anti-trigger.	5 / 5
Trigger Term Quality	Strong natural user vocabulary ('UMAP', 't-SNE', 'dimensionality reduction', 'group separation', 'abundance or OTU-style matrices') with synonyms, though a few common phrasings are absent.	4 / 5
Distinctiveness Conflict Risk	The 'NOT for' clause excludes differential expression, single-cell, and groupless clustering, carving a clear niche with minimal conflict risk against neighboring 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: awesome-med-research-skills/Data Analysis/umap-tsne-analysis/SKILL.md
Commit: f5ef65b

Reviewed: ~9 hours 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.