tooluniverse-gwas-study-explorer

Compare GWAS studies, perform meta-analyses across cohorts, and assess signal replication. Uses GWAS Catalog metadata, study-level statistics, and cross-cohort comparison. Use for evaluating GWAS reproducibility for a trait, meta-analysis sample size and effect-size aggregation, and detecting study heterogeneity (population, design, ancestry).

Quality

67%

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

Fix and improve this skill with Tessl

tessl review fix ./plugin/skills/tooluniverse-gwas-study-explorer/SKILL.md

Quality

Content

42%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 contains valuable skill-specific guidance (honesty rule, tool inventory, compute-don't-describe) but is diluted by extensive textbook GWAS meta-analysis explanation, high-level rather than executable workflows, and a reference to a non-existent bundle file.

Suggestions

Move textbook material (I² formula, fixed/random-effects explanations, quality tiers, sources of heterogeneity) into a separate reference file and keep SKILL.md focused on skill-specific procedure and tool usage.

Replace the high-level workflow bullets with concrete, executable sequences that name the exact tool calls per step and show a short Python example for the meta-analysis computation.

Either add the referenced python_implementation.py to the scripts/ bundle or remove the inline reference to it, so referenced paths resolve to real files.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: large sections (Statistical Methods, Study Quality Assessment, Limitations) restate textbook GWAS concepts Claude already knows — I² formula, fixed/random effects, quality tiers, winner's curse, publication bias — adding significant padding.	2 / 5
Actionability	Concrete tool names (gwas_search_studies, gwas_get_associations_for_snp) and a "COMPUTE, DON'T DESCRIBE" directive help, but workflows are high-level bullets with no executable code, and the referenced python_implementation.py is described rather than shown.	3 / 5
Workflow Clarity	Use-case workflows list sequenced steps with stated outcomes, but validation checkpoints are implicit; only the honesty rule acts as a guardrail, and steps lack concrete tool calls per step.	3 / 5
Progressive Disclosure	Headers give reasonable structure, but the body inlines textbook material that belongs in reference files and references python_implementation.py, which is not present in the (empty) references/scripts/assets bundle.	3 / 5
	Total	11 / 20 Passed

Description

92%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.

A strong, specific description that names concrete actions, data sources, and explicit trigger conditions in third person. It clearly communicates both capability and invocation context with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Compare GWAS studies, perform meta-analyses across cohorts, and assess signal replication" — plus the specific data sources used, giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both what (compare/meta-analyze/assess replication using GWAS Catalog + Open Targets) and when ("Use for evaluating GWAS reproducibility..., meta-analysis sample size and effect-size aggregation, and detecting study heterogeneity").	5 / 5
Trigger Term Quality	Good keyword coverage with synonyms ("GWAS studies", "meta-analyses"/"meta-analysis", "signal replication"/"GWAS reproducibility", "study heterogeneity"), but a few natural phrasings a user might say are not exhaustively covered.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (cross-cohort GWAS comparison and meta-analysis) with distinct triggers, minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-gwas-study-explorer/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.