Agent Skills
› aiming-lab/AutoResearchClaw
› meta-analysis
meta-analysis
GitHub提供跨研究或实验结果聚合的统计方法最佳实践，包括报告效应量、处理异质性、可视化森林图及评估发表偏倚等核心原则。
Trigger Scenarios
需要汇总多个独立研究或实验的结果
进行跨数据集或跨实验的对比分析
Install
npx skills add aiming-lab/AutoResearchClaw --skill meta-analysis -g -y
SKILL.md
Frontmatter
{
"name": "meta-analysis",
"metadata": {
"author": "researchclaw",
"version": "1.0",
"category": "experiment",
"priority": "5",
"references": "Borenstein et al., Introduction to Meta-Analysis, 2009",
"trigger-keywords": "meta-analysis,effect size,pooled,cross-study,aggregat",
"applicable-stages": "7,14"
},
"description": "Statistical methods for combining results across multiple studies. Use when aggregating cross-study or cross-experiment results."
}
Meta-Analysis Best Practice
When comparing results across studies or experiments:
- Report effect sizes, not just p-values
- Use standardized metrics for cross-study comparison
- Account for heterogeneity (different setups, datasets, seeds)
- Report confidence intervals alongside point estimates
- Use forest plots to visualize cross-study comparisons
- Identify and discuss outliers or inconsistent results
- Consider publication bias when interpreting aggregate results
Version History
- e2e23c9 Current 2026-07-25 07:48
