review-synthesis
Skill10 starsChanged 19 days agoLicence not identifiedView on GitHub
综述文章的证据综合（乔淼PhD · AI学术训练营 · AI学术工作流 · 综述文章工作台 阶段③）。把最终纳入的文献全文综合成 证据综合.md：按 综述选题.md 锚块的 review_type 三路分流——systematic 走 meta-analysis（效应量/异质性/敏感性/发表偏倚/偏倚风险/GRADE）或降级为 SWiM 定性系统综述；semi-systematic 走主题综合与 meta-narrative（RAMESES）；integrative 走概念整合出新框架（Torraco）。方法锚 Snyder (2019) + Cochrane Handbook + RAMESES + Torraco (2005)。**这是综述文章专用，不要用实证论文的 data-analysis-round / analyze-quantitative-data 代替**（那两个锚的是单研究数据分析，没有效应量合成）。Trigger on："综合我的综述语料库"、"做 meta-analysis"、"把纳入文献综合成研究发现"、"主题综合 / meta-narrative / 整合式综述的综合"、"synthesize my review corpus"、"run the synthesis for my systematic review"。
- Reads credentials
In this repository45 other files it gives its agents.
- academic-project-initSkill
- analyze-qualitative-dataSkill
- analyze-quantitative-dataSkill
- article-frameworkSkill
- cnkiSkill
- critical-paper-readingSkill
- data-analysis-roundSkill
- findings-synthesisSkill
- fulltext-draftSkill
- journal-rankSkill
- journal-requirements-checkSkill
- knowledge-module-genSkill
- knowledge-module-listSkill
- literature-analysisSkill
- literature-searchSkill
- lit-pdf-zoteroSkill
- lit-pyramidSkill
- lit-verifySkill
- manuscript-diagnosisSkill
- manuscript-revisionSkill
- methodology-draftSkill
- methods-mapSkill
- model-paper-deconstructSkill
- pxyv-searchSkill
- research-designSkill
- research-gap-scanSkill
- review-blueprintSkill
- review-draft-assemblySkill
- review-draftSkill
- review-response-planningSkill
- review-revision-responseSkill
- skill-forgeSkill
- skill-workshop-planSkill
- sr-search-recordSkill
- submission-package-preparationSkill
- submission-task-intakeSkill
- topic-concept-constructionSkill
- topic-hypothesis-testingSkill
- topic-method-drivenSkill
- topic-pxyv-parseSkill
- topic-review-integrativeSkill
- topic-review-semisystematicSkill
- topic-review-systematicSkill
- topic-theory-interpretationSkill
- topic-workbenchSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.