tooluniverse-gene-enrichment

Perform comprehensive gene enrichment and pathway analysis using gseapy (ORA and GSEA), PANTHER, STRING, Reactome, and 40+ ToolUniverse tools. Supports GO enrichment (BP, MF, CC), KEGG, Reactome, WikiPathways, MSigDB Hallmark, and 220+ Enrichr libraries. Handles multiple ID types (gene symbols, Ensembl, Entrez, UniProt), multiple organisms (human, mouse, rat, fly, worm, yeast), customizable backgrounds, and multiple testing correction (BH, Bonferroni). Use when users ask about gene enrichment, pathway analysis, GO term enrichment, KEGG pathway analysis, GSEA, over-representation analysis, functional annotation, or gene set analysis.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced body with explicit validation checkpoints and a closing checklist. Its main weaknesses are mild reference redundancy and a critical progressive-disclosure defect: all 14 referenced bundle files (references/*.md, scripts/*.py) are absent, so every "See references/..." link resolves to nothing.

Suggestions

Create the 14 referenced bundle files (references/ora_workflow.md, references/gsea_workflow.md, references/enrichr_guide.md, references/cross_validation.md, references/id_conversion.md, references/tool_parameters.md, references/organism_support.md, references/common_patterns.md, references/troubleshooting.md, references/multiple_testing.md, references/report_template.md, and scripts/format_enrichment_output.py, scripts/compare_enrichment_sources.py, scripts/filter_by_gene_set_size.py) so the deferred detailed content actually exists.

De-duplicate navigation: the "Detailed Documentation" section re-lists every reference already linked inline — keep one canonical index and remove the scattered duplicate "See:" links (or vice versa) to tighten conciseness.

Drop the bare comment-only code block in Step 1 (Create Report File) and show the actual header-writing call, or link to references/report_template.md once it exists, so every code block is executable.

Dimension	Reasoning	Score
Conciseness	Mostly efficient actionable reference material (tables, decision trees, code), but the ~400-line body carries redundancy — inline "See: references/..." links are re-listed wholesale in the "Detailed Documentation" section — and could be tightened; not a 1 because it avoids concept lectures, not a 3 because it is not lean.	2 / 3
Actionability	Provides fully executable, parameter-specific code (gseapy.enrichr/prerank with cutoffs, ToolUniverse calls with organism IDs and join formats) plus an input-parameter table with examples, matching the copy-paste-ready anchor; not a 2 because the examples are complete and concrete rather than pseudocode.	3 / 3
Workflow Clarity	The 5-step Quick Start has explicit checkpoints — "ID Conversion and Validation" gates enrichment, cross-validation is required, and a mandatory Completeness Checklist closes the flow — with a Troubleshooting section for error recovery; not a 2 because validation is explicit rather than merely listed.	3 / 3
Progressive Disclosure	The overview is well-signaled and one-level-deep, but it defers detail ("complete examples", "all 225+ libraries", "complete guide") to 14 referenced files in references/ and scripts/ that do not exist on disk, so the deferred content is absent and navigation is broken; not a 1 because the body is well-organized and not a deeply nested dead-end, not a 3 because the promised split-out material is missing.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that names concrete actions and tools, gives explicit "Use when" triggers with natural user terms, and carves out a distinct enrichment niche. "Comprehensive" is a mild buzzword but the surrounding specifics dominate.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and named tools — "Perform ... enrichment and pathway analysis using gseapy (ORA and GSEA), PANTHER, STRING, Reactome" plus enumerated databases (GO BP/MF/CC, KEGG, Reactome, WikiPathways, MSigDB) — matching the anchor for listing several specific concrete actions; not a 2 because it goes well beyond naming a domain and a couple of actions.	3 / 3
Completeness	Clearly answers both "what" (perform gene/pathway enrichment via named tools and databases) and "when" with an explicit "Use when users ask about ..." trigger clause, matching the anchor for explicit triggers on both sides; not a 2 because the "when" is explicit, not merely implied.	3 / 3
Trigger Term Quality	The "Use when users ask about gene enrichment, pathway analysis, GO term enrichment, KEGG pathway analysis, GSEA, over-representation analysis, functional annotation, or gene set analysis" clause gives good coverage of natural terms users would actually say; not a 2 because it covers common variations rather than missing them.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (gene/pathway enrichment) with domain-specific triggers and named tools (gseapy, PANTHER, STRING, Reactome), making it unlikely to fire for the wrong skill; not a 2 because the triggers are specific to enrichment rather than generically overlapping.	3 / 3
	Total	12 / 12 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: 27 missing	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/bio/tooluniverse-gene-enrichment/SKILL.md
Commit: df37802

Reviewed: 2 days 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.