菜单
Run statistical meta-analysis in R with renv, generate effect estimates, heterogeneity, and publication bias diagnostics, and export figures and tables. Use when analyzing extracted study data.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
基于 SOC 职业分类
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/htlin222/lymphoma-TLS-outcome --skill ma-meta-analysis命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
Orchestrate agent team for meta-analysis pipeline. Creates team, spawns teammates, manages task list and handoffs between pipeline stages.
Define extraction schema, extract study data from full texts, and store it in a structured database for meta-analysis. Use when moving from full-text collection to statistical analysis.
End-to-end AI-assisted meta-analysis pipeline orchestration from TOPIC.txt to final manuscript and reviewer responses. Use when the user provides a topic and wants the full meta-analysis workflow, tracking, and final paper.
| name | ma-meta-analysis |
| description | Run statistical meta-analysis in R with renv, generate effect estimates, heterogeneity, and publication bias diagnostics, and export figures and tables. Use when analyzing extracted study data. |
Analyze extracted data using standard meta-analysis methods and produce validated outputs.
05_extraction/extraction.csv05_extraction/data-dictionary.md06_analysis/01_setup.R06_analysis/02_effect_sizes.R06_analysis/03_models.R06_analysis/04_subgroups_meta_regression.R06_analysis/05_plots.R06_analysis/06_tables.R06_analysis/07_sensitivity.R06_analysis/08_bias.R06_analysis/09_validation.R06_analysis/07_export_tables.R06_analysis/figures/ PNG files at 300 dpi06_analysis/tables/ PNG + HTML + DOCX + CSV tables (via gt + flextable)06_analysis/validation.md06_analysis/renv.lockAll models must use REML + Hartung-Knapp (Cochrane mandate, July 2025):
# meta: metagen(..., method.tau = "REML", hakn = TRUE)
# metafor: rma(..., method = "REML", test = "knha")
Run DerSimonian-Laird as sensitivity analysis for comparison, but REML + HKSJ is the primary result.
renv in 06_analysis/ and record package versions.
renv::init() in 06_analysis/06_analysis/renv.lockassets/r/ into 06_analysis/ and adapt them to the study schema.
assets/r/01_setup.R → 06_analysis/01_setup.Rmetafor::escalc for the outcome type.
06_analysis/02_effect_sizes.R (use metafor::escalc() function)meta and/or metafor with REML + Hartung-Knapp defaults.
06_analysis/03_models.R (L10-30: metagen(..., method.tau = "REML", hakn = TRUE))06_analysis/04_subgroups_meta_regression.R06_analysis/07_sensitivity.R06_analysis/08_bias.R06_analysis/05_plots.R06_analysis/figures/*.png (png(..., res=300, width=3000, height=2400))gtsummary to build manuscript-ready summary tables.
06_analysis/06_tables.R (use gtsummary::tbl_summary())gt + flextable for manuscript sync.
06_analysis/07_export_tables.R06_analysis/tables/*.png, 06_analysis/tables/*.html, 06_analysis/tables/*.docx06_analysis/validation.md.
06_analysis/validation.mdassets/r/ provides a scaffolded R workflow that maps to the standard steps.references/r-meta-roadmap.md summarizes the expected analysis tasks.| Step | Skill | Stage |
|---|---|---|
| Prev | /ma-data-extraction | 05 Data Extraction |
| Next | /ma-manuscript-quarto | 07 Manuscript Drafting |
| All | /ma-end-to-end | Full pipeline orchestration |