Nsfc Literature Agent Skill
NSFC申请书文献检索与引用生成。使用OpenAlex API免费搜索学术文献，使用wenxian生成标准引用格式。
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/njzjz/nsfc-agent-skills --skill nsfc-literatureThe instruction itself
5 sections, as written by the authorNSFC 申请书文献检索与引用生成
文献在申请书中的要求
- 参考文献约30条，以近5年为主
- CNS等权威期刊优先
- 国际文献为主 + 国内文献为辅 + 自己的工作（可高亮）
- 不要遗漏领域关键文献（评审人会注意）
- 格式必须统一规范
- 有当年文献加分
- 勿缺失关键参考文献
文献检索
OpenAlex API（免费，无需API key）
脚本：scripts/search_literature.py
基本用法：
# 搜索关键词，按引用数排序
uv run scripts/search_literature.py "machine learning potential" --limit 20 --sort cited_by_count
# 搜索近3年的文献
uv run scripts/search_literature.py "deep learning molecular dynamics" --year-from 2023
# 按发表日期排序（找最新文献）
uv run scripts/search_literature.py "neural network force field" --sort publication_date
# 紧凑输出（每篇一行）
uv run scripts/search_literature.py "density functional theory" --compact
返回信息：标题、作者、期刊、年份、DOI、引用数、摘要
搜索策略建议：
- 先用宽泛关键词搜索了解领域全貌
- 再用精确关键词搜索特定方向
- 关注高引论文（领域经典）和最新论文（前沿动态）
- 检查是否遗漏领域大牛的工作
- 搜索中文关键词时可能需要用英文替代
引用生成
wenxian
wenxian 是一个学术引用生成工具，支持从 DOI、PMID、arXiv ID 等标识符生成标准引用格式。
脚本：scripts/generate_references.py
用法：
# 从DOI列表文件生成BibTeX引用
uv run scripts/generate_references.py refs.txt --format bibtex
# 生成纯文本引用
uv run scripts/generate_references.py refs.txt --format text
# 输出到文件
uv run scripts/generate_references.py refs.txt --format bibtex --output refs.bib
refs.txt 格式（每行一个标识符）：
10.1103/PhysRevLett.120.143001
10.1038/s41586-020-2242-8
arXiv:2304.09423
NSFC引用格式
NSFC申请书通常使用编号引用格式 [1], [2], ...
格式示例：
[1] 作者1, 作者2, 等. 标题. 期刊, 卷(期): 起始页-结束页, 年份.
[2] Author1, Author2, et al. Title. Journal, Volume(Issue): Pages, Year.
注意：
- 所有文献格式必须统一（姓名顺序、期刊缩写等）
- 建议手动录入基金委成果系统保持格式一致
- 自己的文献可以加粗或用其他方式高亮
完整工作流程
1. 确定研究方向和关键词
↓
2. 用 search_literature.py 搜索相关文献
↓
3. 筛选 ~30 条最相关的文献
- 高引经典 + 近年前沿 + 自己的工作
↓
4. 收集所有 DOI，写入 refs.txt
↓
5. 用 generate_references.py 生成标准引用
↓
6. 检查格式统一性
↓
7. 确认没有遗漏关键文献
常见问题
搜索不到文献？
- 尝试不同的关键词组合
- 使用英文关键词
- 检查拼写
- OpenAlex覆盖面广但不是100%，可辅以Google Scholar
wenxian报错？
- 确认
uvx已安装（uv的一部分） - 确认DOI格式正确（如
10.1038/s41586-020-2242-8） - 部分API可能需要网络代理，请根据本地环境配置
格式不统一？
- 使用同一工具生成所有引用
- 手动检查并统一姓名顺序、期刊缩写
- 建议最后统一校对一遍
Other skills for the same job
different authors, same section of the catalogue
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.
Identifies high-quality leads for your product or service by analyzing your business, searching for target companies, and providing actionable contact strategies. Perfect for sales, business development, and marketing professionals.
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.
Efficient database search tool for bioRxiv preprint server. Use this skill when searching for life sciences preprints by keywords, authors, date ranges, or categories, retrieving paper metadata, downloading PDFs, or conducting literature reviews.
Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly works. Use for literature searches, research output analysis, citation analysis, and academic database queries.
Access USPTO APIs for patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, for IP analysis and prior art searches.
Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.
Automated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical data (e.g., deception detection, content analysis). Combines literature insights with data-driven hypothesis testing. For manual hypothesis formulation use hypothesis-generation; for creative ideation use scientific-brainstorming.
How to use it
Take njzjz/nsfc-literature from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.