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

91%

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 strong, actionable body: concrete script and tool invocation, exact formulas, and a well-sequenced workflow with heterogeneity checkpoints. Minor conciseness trimming and a cleaner reference structure would lift it to top marks.

Suggestions

Tighten the 'Scale foot-gun' callout and 'Honest limitations' to the essential warning each — the log-transform rule is the core point and can lead the block.

Add an explicit validate→retry step (e.g., if a row fails effect-size conversion, fix the CSV row and re-run) to give the workflow a true feedback loop.

Clarify that references/cox_regression.md belongs to the tooluniverse-statistical-modeling skill, or link it with the skill prefix, to avoid a dangling cross-skill reference.

Dimension	Reasoning	Score
Conciseness	Efficient — dense tables and critical rules earn their place and it avoids explaining basics Claude knows — but the scale foot-gun block and some elaboration in 'Honest limitations' could be trimmed slightly. Not a 5 because a few sentences over-explain.	4 / 5
Actionability	Fully executable: a real script invocation with CSV column specs ('python …/meta_analysis.py --input studies.csv'), a concrete 'tu run MetaAnalysis_run' JSON example, and exact conversion formulas in the table. The helper script exists in the bundle and is copy-paste ready.	5 / 5
Workflow Clarity	Clear 5-step sequence (Extract → Pick model → Pool → Read heterogeneity → Forest plot) with decision checkpoints (fixed vs random on I², 'Don't over-pool' at I²>75%, retraction/publication-bias checks). Not a 5 because there is no explicit validate→fix→retry feedback loop.	4 / 5
Progressive Disclosure	Well-organized sections with the helper script referenced clearly one level deep and conversion logic appropriately split into the script. Not a 5 because the related-skills pointer to another skill's references/cox_regression.md is a mildly confusing cross-skill reference and conversion formulas are duplicated inline and in the script.	4 / 5
	Total	17 / 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.

A high-quality description: concrete actions, explicit 'Use when' trigger with synonyms, third-person voice, and a distinct niche. It earns top marks on every dimension without padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'pool effect sizes across studies', 'quantify heterogeneity (Q, I², τ²)', 'build a forest plot', and the conversion of 'OR/HR/CI, two-group means±SD, proportions, and correlations into the (effect, SE)' — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both — the 'what' (pool, quantify heterogeneity, forest plot, effect-size prep) and a concrete 'Use when you have results from MULTIPLE studies…' trigger clause.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage with synonyms: 'meta-analysis', 'evidence synthesis', 'systematic review', 'multiple GWAS', 'replicated experiments', plus the effect-size vocabularies users actually name.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (pooling across multiple studies) with distinct triggers that separate it from single-study regression/literature-search skills; minimal conflict risk.	5 / 5
	Total	20 / 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: plugin/skills/tooluniverse-meta-analysis/SKILL.md
Commit: 7a0ceb2

Reviewed: 3 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.