tooluniverse-gene-enrichment

Gene-set enrichment analysis — GO (Biological Process, Molecular Function, Cellular Component), KEGG, Reactome pathway enrichment via clusterProfiler, gseapy, ORA, GSEA. Use for interpreting DEG lists, screen hit lists, or any gene-list-to-pathways query. Includes simplify-cutoff handling and union-vs-total denominator conventions for percent-DE questions.

Quality

89%

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

Quality

Content

78%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.

A high-actionability, well-sequenced operational skill whose scripts and decision tables are excellent, but it suffers from broken reference links (6 of 11 referenced files are missing) and moderate repetition of the simplify caveat. Fixing the dead links and consolidating the duplicate caveats would lift conciseness and progressive_disclosure.

Suggestions

Create or remove the six missing reference files the body links to (references/cross_validation.md, id_conversion.md, organism_support.md, common_patterns.md, multiple_testing.md, report_template.md) — every 'See references/...' pointer must resolve to a real file.

Consolidate the simplify-p.adjust denominator caveat, which is explained in PRIMARY SCRIPTS, the Analysis conventions section, and near Pattern 3b, into one authoritative location.

Tighten or remove the 'Input Parameters' table, which duplicates parameter behavior already expressed by the runnable scripts, to reclaim token budget.

Dimension	Reasoning	Score
Conciseness	Densely packed, assumes Claude's intelligence (no basic-concept filler), but the simplify-p.adjust caveat is restated in three places and the 'Input Parameters' table partially duplicates behavior already encoded in the scripts, so it could be trimmed further.	4 / 5
Actionability	Three fully-specified CLI scripts with copy-paste invocations and parseable output-line contracts ('# TOP_BY_ADJ_PVALUE', '# CANDIDATE_RANK'), plus a DEG-filter decision table mapping question phrasing to exact filters — fully executable and covers common cases.	5 / 5
Workflow Clarity	Clear sequencing (RULE ZERO → PRIMARY SCRIPTS → fallback) with validation checkpoints (tie-count warning, DEG cross-check, 'stop and reconsider' on over-filtering), but the verification guidance is advisory prose rather than a hard checklist with explicit pass/fail gates.	4 / 5
Progressive Disclosure	The body is an overview with one-level-deep, clearly signaled references to references/ and scripts/, but it links to 11 reference files while only 5 actually exist — six paths (cross_validation, id_conversion, organism_support, common_patterns, multiple_testing, report_template) are dead, breaking navigation.	3 / 5
	Total	16 / 20 Passed

Description

100%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.

An exemplary description: third-person, concrete, names tools and databases, answers both what and when with specific trigger phrases, and carves out a distinct niche. The only minor gap is the absence of WikiPathways/MSigDB terms, which does not lower any anchor.

Dimension	Reasoning	Score
Specificity	Names the domain and multiple concrete actions — GO/KEGG/Reactome enrichment via clusterProfiler and gseapy — plus specific behaviors like 'simplify-cutoff handling' and 'union-vs-total denominator conventions', giving comprehensive concrete coverage.	5 / 5
Completeness	Explicitly answers both 'what' (enrichment analysis across named databases via named tools) and 'when' ('Use for interpreting DEG lists, screen hit lists, or any gene-list-to-pathways query') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural terms a bioinformatics user would actually say: 'gene-set enrichment', 'GO', 'KEGG', 'Reactome', 'DEG lists', 'gene-list-to-pathways', 'GSEA', 'ORA', covering synonyms and canonical phrasing.	5 / 5
Distinctiveness Conflict Risk	A clear niche (pathway/enrichment analysis) with tool-specific triggers and explicit sibling-skill boundaries in the body, giving minimal conflict risk.	5 / 5
	Total	20 / 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
relative_links	Relative link issues: 4 suspicious	Warning
referenced_paths_exist	Referenced path issues: 8 missing	Warning

	Total	14 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-gene-enrichment/SKILL.md
Commit: 1b02920

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.