tooluniverse-meta-analysis

Meta-analysis / evidence synthesis — pool effect sizes across studies (odds ratios, risk ratios, hazard ratios, mean differences, correlations, GWAS betas) with fixed- or random-effects models, quantify heterogeneity (Q, I², τ²), and build a forest plot. Use when you have results from MULTIPLE studies and need a single pooled estimate, or to synthesize evidence from a systematic review / multiple GWAS / replicated experiments. Handles the error-prone effect-size + standard-error preparation (converting OR/HR/CI, two-group means±SD, proportions, and correlations into the (effect, SE) the pooling step needs).

Quality

87%

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

82%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 well-structured, highly actionable body with executable commands, exact formulas, and a working script. It loses a little on conciseness (one run-on warning paragraph) and progressive disclosure (a dangling cross-skill reference path) and lacks an explicit error-recovery feedback loop.

Suggestions

Tighten the 'Scale foot-gun' callout (line 79) into a short checklist so it scans as fast as the rest of the body.

Clarify that references/cox_regression.md (line 113) belongs to the sibling tooluniverse-statistical-modeling skill, or remove the inline reference to avoid a dead-looking path in this skill's own bundle.

Add a brief validate→fix→retry note for when MetaAnalysis_run errors or the helper script rejects a row, to lift workflow_clarity to a full checkpoint loop.

Dimension	Reasoning	Score
Conciseness	Dense and information-rich with no padding of concepts Claude already knows (compact tables, exact formulas), but the run-on scale foot-gun paragraph (line 79) and some discursive 'Honest limitations' commentary could be tightened.	4 / 5
Actionability	Fully executable: a concrete `tu run MetaAnalysis_run '{...}'` command with real data, exact CSV column specs, exact conversion formulas, and a verified-working helper script (scripts/meta_analysis.py) — copy-paste ready and covers the common cases.	5 / 5
Workflow Clarity	A clear 5-step numbered sequence with the error-prone step flagged and decision rules at each stage (I² bands, ratio-scale warnings acting as checkpoints), but no explicit validate→fix→retry feedback loop is described, keeping it just short of 5.	4 / 5
Progressive Disclosure	Good structure with a clear overview and a one-level-deep, verified reference to the helper script, appropriately inlining the core conversion table; however a referenced path (references/cox_regression.md) does not exist in this skill's bundle and is not clearly signaled as belonging to a sibling skill.	4 / 5
	Total	17 / 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 clearly states what the skill does and when to use it, with comprehensive concrete actions and natural trigger terms. The only mild gap is trigger-term breadth, which is constrained by the domain lacking file-extension-style triggers.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions with comprehensive coverage — pooling via fixed/random-effects models, quantifying heterogeneity (Q, I², τ²), building a forest plot, and converting OR/HR/CI, two-group means±SD, proportions, and correlations into (effect, SE).	5 / 5
Completeness	Explicitly answers both what ('pool effect sizes… quantify heterogeneity… build a forest plot') and when ('Use when you have results from MULTIPLE studies and need a single pooled estimate, or to synthesize evidence from a systematic review…') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural phrases users would say ('systematic review', 'multiple studies', 'pooled estimate', 'forest plot', 'GWAS') with good synonym coverage; a few natural variations missing and the domain has no file-extension triggers to round it out to 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche (meta-analysis / evidence synthesis) with distinctive triggers ('MULTIPLE studies', 'pooled estimate'); the body explicitly routes single-study analysis and literature search to sibling skills, minimizing conflict risk.	5 / 5
	Total	19 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: plugins/tooluniverse/skills/tooluniverse-meta-analysis/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.