scientific-meta-analysis

Aggregate study effect sizes into pooled estimates with heterogeneity and bias metrics.

3|1|Updated Feb 11, 2026

Search Tags:#statistics #meta-analysis #heterogeneity #effect-size #random-effects #funnel-plot #forest-plot

Ready to run

npx skills add https://github.com/nahisaho/satori --skill scientific-meta-analysis

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: scientific-meta-analysis
Source: https://github.com/nahisaho/satori/tree/main/src/.github/skills/scientific-meta-analysis
Command: npx skills add https://github.com/nahisaho/satori --skill scientific-meta-analysis

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Multi-study data integration and effect-size synthesis can be time-consuming and prone to inconsistencies. This skill provides a reproducible pipeline for combining study results to obtain a pooled estimate, while evaluating heterogeneity and potential biases.

Core Features & Use Cases

Fixed or random-effects meta-analysis (DerSimonian-Laird) for combining effect sizes such as SMD, MD, OR, or RR.
Visualization and diagnostics including Forest plots, Funnel plots, I², Q, and τ² statistics.
Use Cases: evidence synthesis for systematic reviews, guideline development, and research programs across academia and industry.

Quick Start

Compute a random-effects meta-analysis for your set of studies using the provided effect sizes and variances to obtain a pooled estimate.

Frequently Asked Questions about scientific-meta-analysis

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I compute a pooled effect size from multiple independent studies?▼

To compute a pooled effect size from multiple independent studies, use a fixed or random-effects meta-analysis model like DerSimonian-Laird. This aggregates diverse outcome types such as SMD, MD, OR, or RR into a single reproducible pooled estimate.

What is heterogeneity assessment in meta-analysis and when do I need it?▼

Heterogeneity assessment in meta-analysis evaluates variation across combined studies using I², Q, and τ² statistics. You need it when synthesizing evidence from independent studies to ensure the pooled effect size is valid and not skewed by outliers.

Can I use random-effects meta-analysis for systematic reviews with diverse outcome types?▼

Yes, you can use random-effects meta-analysis for systematic reviews with diverse outcome types. It supports outcomes like SMD, MD, OR, or RR, and provides structured, reproducible reporting required for guideline development.

What's the best way to detect bias in multi-study data integration?▼

The best way to detect bias in multi-study data integration is by generating funnel plots. This diagnostic visualization helps identify potential publication biases during evidence synthesis, ensuring the pooled estimate is reliable.

How do I visualize effect sizes across studies for reproducible reporting?▼

To visualize effect sizes across studies for reproducible reporting, generate forest plots. This diagnostic display plots individual study effects and the pooled estimate, satisfying standard requirements for systematic reviews.

Why does my meta-analysis show high heterogeneity and how should I interpret it?▼

If your meta-analysis shows high heterogeneity, interpret it using the provided I², Q, and τ² statistics. High values indicate substantial variation across studies, suggesting the pooled effect size may not represent a uniform effect.