Name: tooluniverse-gwas-study-explorer
Rating: 55.2 (1 reviews)
Author: mims-harvard

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

61%

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 ./plugins/tooluniverse/skills/tooluniverse-gwas-study-explorer/SKILL.md

The canonical home for this skill is tooluniverse-gwas-study-explorer in mims-harvard/ToolUniverse

Quality

Content

35%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 covers the domain breadth and includes valuable honesty/lookup guardrails, but it is padded with concepts Claude already knows, lacks executable code despite instructing computation, and references a non-existent script. Weakest on conciseness and actionability.

Suggestions

Replace the textbook Statistical Methods, Quality Tiers, and Limitations sections with concise decision rules, and move detailed reference material into a references/ file linked from SKILL.md.

Add at least one concrete, copy-pasteable Python snippet (e.g., calling gwas_get_associations_for_study and computing inverse-variance pooled beta + I²) to satisfy the 'COMPUTE, DON'T DESCRIBE' directive.

Either create scripts/python_implementation.py as referenced by the honesty rule, or remove/fix the broken reference so progressive disclosure navigation is trustworthy.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: large sections restate textbook GWAS knowledge Claude already knows (fixed vs random effects, I² threshold interpretation, sources of heterogeneity, winner's curse, quality tiers) that could be trimmed without losing actionability.	2 / 5
Actionability	Despite the 'COMPUTE, DON'T DESCRIBE' directive, the body contains no executable code or commands; workflows are high-level bullet hints and the one referenced artifact (python_implementation.py) does not exist in the bundle.	2 / 5
Workflow Clarity	The four use cases provide rough step sequences, but validation checkpoints are mostly implicit; the honesty-rule blockquote is the only real feedback loop for a batch meta-analysis operation, which caps clarity at 3.	3 / 5
Progressive Disclosure	Section headers give reasonable structure, but everything is inlined into one file (statistical methods, quality tiers, tools list, glossary) and the sole referenced file (python_implementation.py) is missing, so references are not cleanly signaled.	3 / 5
	Total	10 / 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.

A strong, specific description that clearly states capabilities and explicit use-when triggers tied to a well-defined GWAS meta-analysis niche. Minor scope for adding a few more colloquial trigger phrasings.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Compare GWAS studies, perform meta-analyses across cohorts, and assess signal replication') plus secondary tasks like reproducibility evaluation and heterogeneity detection, with only minor gaps in coverage.	4 / 5
Completeness	Explicitly answers both what ('Compare GWAS studies, perform meta-analyses...') and when ('Use for evaluating GWAS reproducibility..., meta-analysis..., and detecting study heterogeneity...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good coverage of natural domain terms ('GWAS reproducibility', 'meta-analysis', 'study heterogeneity', 'cross-cohort comparison') with a clear 'Use for' trigger clause, though a few common phrasings a user might say are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (GWAS Catalog / Open Targets meta-analysis and replication assessment) with distinct triggers and minimal overlap risk against generic analysis skills.	5 / 5
	Total	18 / 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: plugins/tooluniverse/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.