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。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/lth0/codexSkill --skill nsfc-literature命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Multi-perspective academic paper review with dynamic reviewer personas. Simulates 5 independent reviewers (EIC + 3 peer reviewers + Devil's Advocate) with field-specific expertise. Supports full review, re-review (verification), quick assessment, methodology focus, Socratic guided, and calibration modes. Triggers on: review paper, peer review, manuscript review, referee report, review my paper, critique paper, simulate review, editorial review, calibrate reviewer, reviewer calibration, measure reviewer accuracy.
12-agent academic paper writing pipeline. 10 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-check/disclosure). 6 paper types, 5 citation formats, bilingual abstracts, LaTeX/DOCX-via-Pandoc/PDF output. Style Calibration + Writing Quality Check + Anti-Patterns with IRON RULE markers. Triggers: write paper, academic paper, guide my paper, parse reviews, AI disclosure, 寫論文, 學術論文, 引導我寫論文, 審查意見.
Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory integrity verification, two-stage peer review, and reproducible quality gates. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publication, complete paper workflow.
正在显示 SKILL.md
| name | nsfc-literature |
| description | 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。 |
| version | 0.1.0 |
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:
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:
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
uvx 已安装(uv 的一部分)10.1038/s41586-020-2242-8)