📚 智能文献综述生成器
/install literature-review-writing-assistant
Review Paper Writing Skill
Overview
This skill helps you write a thorough, well-structured literature review — from topic definition and systematic search to formatted citations and a polished markdown draft. It covers:
- Topic framing with PICO framework
- Search strategy (Boolean, MeSH, wildcards, proximity)
- Multi-source academic search (arXiv, Semantic Scholar, OpenAlex, CrossRef, PubMed)
- DOI / arXiv ID validation and conflict detection
- Citation formatting (APA, MLA, IEEE, BibTeX, RIS, Markdown)
- Auto-generated literature review in Markdown
Quick Start
1. Run a Search
python3 scripts/lit_search.py "large language model education" -n 20 --sources arxiv openalex
2. Validate DOIs
python3 scripts/lit_search.py "machine learning" --validate
3. Format Citations
python3 scripts/lit_search.py "BERT" -n 10 -f apa # APA 7th
python3 scripts/lit_search.py "transformer" -n 10 -f bibtex # BibTeX
python3 scripts lit_search.py "attention" -n 10 -f ris # RIS
4. Filter Results
| Flag | Effect |
|---|---|
--published-only |
Exclude arXiv preprints |
--preprint-only |
Only arXiv preprints |
--min-year 2020 |
Earliest publication year |
--min-citations 50 |
Minimum citation count |
--conflicts |
Detect cross-source metadata conflicts |
5. Batch Mode (from file)
Create papers.txt with one DOI/PMID/arXiv ID per line:
10.48550/arXiv.2303.08774
10.48550/arXiv.2205.11916
PMID: 34567890
Then:
python3 scripts/lit_search.py file://papers.txt -f bibtex
Search Strategy Framework
PICO Framework
Use PICO to structure your research question:
| Element | Meaning | Example |
|---|---|---|
| Population | Target group | high school students |
| Intervention | Treatment or method | motivational interviewing |
| Comparator | Control group | no intervention |
| Outcome | Measurable result | academic performance |
Convert to search terms:
P: student*
I: "motivational interviewing"
O: "academic achievement"
→ "motivational interviewing" AND student* AND "academic achievement"
Boolean Operators
# AND: all terms must appear
"cognitive behavioral therapy" AND adolescent*
# OR: any term may appear
depression OR anxiety OR "mental health"
# NOT: exclude terms
animal NOT pet
# Parentheses for grouping
("cognitive behavioral therapy" OR CBT) AND adolescent*
Wildcards & Truncation
student* → student, students, student's, students'
wom?n → woman, women
Proximity Search
behavior N/2 change # "behavior" within 2 words of "change"
"stress" ADJ3 "coping" # same sentence
MeSH (PubMed)
"Motor Activity"[Mesh]
"Depression"[Mesh] AND "Therapy"[Mesh:Subheading]
Database-Specific Syntax
# PubMed
"motivational interviewing"[Title/Abstract]
("Anxiety"[Mesh] OR "Anxiety Disorders"[Mesh]) AND 2020:2024[dp]
# PsycINFO (OVID)
exp Motivational Interviewing/
motivation interview*.tw
# Web of Science
TS=("motivational interviewing" AND school*)
PY=2020-2024
Source Comparison
| Source | Type | API Key | Best For |
|---|---|---|---|
| arXiv | Preprint | ❌ No | CS, ML, physics, stats |
| Semantic Scholar | Published + preprint | Optional | High-citation papers |
| OpenAlex | Published | ❌ No | Broad cross-disciplinary |
| CrossRef | Published | ❌ No | Authoritative DOI metadata |
| PubMed | Published (biomedical) | ❌ No | Medicine, health, biology |
Recommended combinations:
arxiv + semantic_scholar→ preprints + high-impact papersopenalex + pubmed→ comprehensive academic coveragearxiv + openalex + pubmed→ full-spectrum search
Quality Tags
| Source | Peer Reviewed | Tag |
|---|---|---|
| arXiv | ❌ No | [arXiv] |
| Journal / Conference | ✅ Yes | [Published] |
| PubMed | ✅ Yes | [PubMed] |
⚠️ arXiv papers are preprints — not peer-reviewed. Treat conclusions as provisional.
Citation Formats
| Format | Style |
|---|---|
apa |
APA 7th Edition |
mla |
MLA 9th Edition |
ieee |
IEEE |
bibtex |
BibTeX (for LaTeX) |
ris |
RIS (for EndNote/Zotero) |
markdown |
Markdown with source tags |
Search Workflow
1. Define topic → PICO framework
↓
2. Build search blocks → synonyms, MeSH terms, wildcards
↓
3. Run multi-source search (parallel API calls)
↓
4. Deduplicate by DOI / arXiv ID
↓
5. Validate IDs (HEAD request → doi.org)
↓
6. Detect cross-source conflicts (title, year, authors)
↓
7. Filter → year, citations, source type
↓
8. Format → APA / MLA / BibTeX / ...
↓
9. Generate literature review (timeline, keywords, summary)
Configuration
Edit scripts/lit_search.py to add your Semantic Scholar API key:
API_KEYS = {
"semantic_scholar": "your-api-key" # Get: https://www.semanticscholar.org/api-keys
}
Without a key, the free tier is used (1 req/sec). A key enables 1000 req/5 sec and avoids rate-limiting.
Output Examples
Markdown output (-f markdown):
[1] **Attention Is All You Need**
* Vaswani, A., Shazeer, N., Parmar, N., et al. (2017). *
arXiv: [1706.03762](https://arxiv.org/abs/1706.03762) [arXiv]
*Citations: 80000*
[2] **BERT: Pre-training of Deep Bidirectional Transformers**
* Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). NAACL-HLT 2019*
DOI: [10.48550/arXiv.1810.04805](https://doi.org/10.48550/arXiv.1810.04805) [Published]
*Citations: 70000*
Generated review section:
# Literature Review
## Statistics
- **Total Papers**: 20
- [arXiv]: 8
- [Published]: 10
- [PubMed]: 2
## Timeline
- 2024: 5 papers
- 2023: 8 papers
- 2022: 4 papers
- 2021: 3 papers
Troubleshooting
| Problem | Solution |
|---|---|
| "Rate limit" from Semantic Scholar | Add API key, or switch to OpenAlex |
| No results | Try fewer / broader search terms |
| Too many results | Narrow date range, add AND filters |
| Invalid DOI | Check format; try CrossRef validation |
| arXiv ID not found | Use format YYMM.NNNNN (e.g., 2303.08774) |
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install literature-review-writing-assistant - 安装完成后,直接呼叫该 Skill 的名称或使用
/literature-review-writing-assistant触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
📚 智能文献综述生成器 是什么?
Literature review paper writing assistant — guides you through the full lifecycle: (1) Systematic search using PICO/Boolean/MeSH frameworks across arXiv, Sem... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 13 次。
如何安装 📚 智能文献综述生成器?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install literature-review-writing-assistant」即可一键安装,无需额外配置。
📚 智能文献综述生成器 是免费的吗?
是的,📚 智能文献综述生成器 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
📚 智能文献综述生成器 支持哪些平台?
📚 智能文献综述生成器 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 📚 智能文献综述生成器?
由 sherry-zh0u(@sherry-zh0u)开发并维护,当前版本 v1.0.0。