Agent Skills
› aiming-lab/AutoResearchClaw
› systematic-review
systematic-review
GitHub提供基于PRISMA指南的系统性文献综述结构化方法，涵盖检索、筛选、提取与综合步骤，用于高效完成学术调研。
Trigger Scenarios
需要系统性梳理特定领域文献
执行学术或技术背景的调研任务
Install
npx skills add aiming-lab/AutoResearchClaw --skill systematic-review -g -y
SKILL.md
Frontmatter
{
"name": "systematic-review",
"metadata": {
"author": "researchclaw",
"version": "1.0",
"category": "experiment",
"priority": "3",
"references": "Page et al., The PRISMA 2020 statement, BMJ 2021",
"trigger-keywords": "literature,review,survey,related work,prior work",
"applicable-stages": "3,4,5,6"
},
"description": "Structured methodology for comprehensive literature review following PRISMA guidelines. Use during literature search and screening stages."
}
Systematic Review Best Practice
Follow PRISMA-like methodology for literature search:
- Define clear inclusion/exclusion criteria BEFORE searching
- Use multiple databases (Semantic Scholar, arXiv, OpenAlex)
- Search with both broad and narrow queries
- Screen by title/abstract first, then full text
- Extract: method, dataset, metrics, key findings
- Synthesize gaps and opportunities, not just summaries
- Prioritize recent (last 2-3 years) high-citation papers
- Include at least one seminal/foundational paper per sub-topic
Version History
- e2e23c9 Current 2026-07-25 07:48
