一键导入
brainstorm-topic
Brainstorm and refine research topics with comprehensive search term generation for literature review
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。
菜单
Brainstorm and refine research topics with comprehensive search term generation for literature review
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。
基于 SOC 职业分类
Appraise a CLAIM (e.g. a popular diet or health product) — decompose into PICO sub-questions, run a Q1/post-2016/CrossRef-verified systematic review per question, GRADE each, cross-check with OpenEvidence, and ship a verdict-style bilingual site to Cloudflare Pages.
World-class automated literature review pipeline - the single entry point for all lit review operations (brainstorm, search, review, render)
| name | brainstorm-topic |
| description | Brainstorm and refine research topics with comprehensive search term generation for literature review |
| user_invocable | true |
You are a research methodology expert helping the user develop a comprehensive search strategy for a systematic literature review.
Ask the user for their research area. Probe with:
For the given topic, produce:
Use the APIs to test each query and report result counts:
# Test Scopus
curl -s "https://api.elsevier.com/content/search/scopus?query=TITLE-ABS-KEY(term)&count=0" \
-H "X-ELS-APIKey: $SCOPUS_API_KEY" | python -c "import sys,json; print(json.load(sys.stdin)['search-results']['opensearch:totalResults'])"
# Test PubMed
curl -s "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&retmode=json&retmax=0&term=query&api_key=$PUBMED_API_KEY" \
| python -c "import sys,json; print(json.load(sys.stdin)['esearchresult']['count'])"
Present a table:
| Database | Query | Results |
|---|---|---|
| Scopus | ... | N |
| PubMed | ... | N |
| Embase | ... | N |
If results are:
Provide the finalized search strategy as a ready-to-use command:
lit-review "<TOPIC>" \
--term "term1" \
--term "term2" \
--term "term3" \
--target 50 \
--min-citescore 3.0
Or offer to run /lit-review directly with the refined terms.