What is the Meta-Analysis skill for Claude Code?

It is a specialized capability that enables Claude to synthesize results across multiple studies using statistical models to derive a summary effect size and assess the consistency of findings.

Which statistical models does this skill support?

The skill supports both Fixed-effect models (assuming a single true effect) and Random-effects models (allowing for heterogeneity between studies).

How does the skill handle different types of research data?

It converts various metrics like Cohen's d, Odds Ratio (OR), and Relative Risk (RR) into a common metric and calculates standard errors for weighted synthesis.

Can this skill detect publication bias?

Yes, it includes specialized procedures for assessing publication bias, including Funnel plots, Egger's test, and the trim-and-fill method.

What are the requirements to run this skill?

The skill requires Read, Write, and Bash tool permissions within the Claude Code environment to process study data and execute analysis scripts.

Meta-Analysis Research Assistant

Name: Meta-Analysis Research Assistant
Author: astoreyai

byastoreyai

•

数据科学与机器学习

Conducts quantitative synthesis of research data by pooling effect sizes across multiple studies to derive summary conclusions.

关于

The Meta-Analysis skill empowers Claude to perform complex quantitative research synthesis by automating the extraction and conversion of effect sizes, choosing appropriate statistical models, and assessing study heterogeneity. It streamlines the systematic review process by calculating summary effects and confidence intervals while investigating publication bias through advanced tests like Egger’s and funnel plot analysis. This skill is an essential tool for evidence-based research, allowing users to move from a collection of raw study data to a rigorous, statistically-backed synthesis with professional reporting.

主要功能

Support for fixed-effect and random-effects statistical modeling
Deep data investigation via subgroup and sensitivity analysis
2 GitHub stars
Publication bias detection including Egger’s test and trim-and-fill methods
Automated effect size conversion and standard error calculation
Heterogeneity assessment using I² statistics and Cochran's Q tests

使用场景

Conducting systematic reviews for academic paper preparation and peer review
Synthesizing clinical trial results to determine overall treatment efficacy
Aggregating multiple market research datasets into a single evidence-based report

关于

主要功能

Support for fixed-effect and random-effects statistical modeling
Deep data investigation via subgroup and sensitivity analysis
2 GitHub stars
Publication bias detection including Egger’s test and trim-and-fill methods
Automated effect size conversion and standard error calculation
Heterogeneity assessment using I² statistics and Cochran's Q tests

使用场景

Conducting systematic reviews for academic paper preparation and peer review
Synthesizing clinical trial results to determine overall treatment efficacy
Aggregating multiple market research datasets into a single evidence-based report