← 返回 Skills 市场
sherry-zh0u

📚 智能文献综述生成器

作者 sherry-zh0u · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
13
总下载
1
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install literature-review-writing-assistant
功能描述
Literature review paper writing assistant — guides you through the full lifecycle: (1) Systematic search using PICO/Boolean/MeSH frameworks across arXiv, Sem...
使用说明 (SKILL.md)

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 papers
  • openalex + pubmed → comprehensive academic coverage
  • arxiv + 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)
安全使用建议
This result is low confidence because local artifact inspection failed; review should be rerun in an environment where metadata.json and artifact files are readable before relying on the verdict.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
No purpose or capability mismatch could be confirmed from artifact evidence because the artifact files were not accessible.
Instruction Scope
No overbroad or hidden instruction scope could be confirmed from artifact evidence.
Install Mechanism
No risky install behavior could be confirmed from artifact evidence.
Credentials
No disproportionate environment access could be confirmed from artifact evidence.
Persistence & Privilege
No persistence or privilege concern could be confirmed from artifact evidence.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install literature-review-writing-assistant
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /literature-review-writing-assistant 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release — literature review paper writing assistant. - Guides users through systematic literature search using PICO/Boolean/MeSH frameworks across major academic sources (arXiv, Semantic Scholar, OpenAlex, CrossRef, PubMed). - Supports DOI & arXiv ID validation with cross-source conflict detection. - Outputs citations in multiple formats: APA 7th, MLA 9th, IEEE, BibTeX, RIS, and Markdown. - Auto-generates structured literature reviews with timeline, keyword extraction, and source-quality tagging. - Provides filtering by publication type, citation count, year, and supports batch processing from file. - Includes a detailed usage guide, search strategies, and troubleshooting tips.
元数据
Slug literature-review-writing-assistant
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

📚 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。

💬 留言讨论