research-lab
Skill0 starsChanged 7 months agoMITView on GitHub
科研模式入口。当用户说"进入科研模式"、"开始做科研"、发论文链接、 提到研究课题/假设/实验/文献综述时激活。提供假设驱动循环、 PubMed文献检索、证据追踪、研究项目管理等科研能力。
3 other projects use a version of this.
Adopted by
Most recently taken up by
- ooooooooooooooooooop/agent-toolstheir own version, first seen Oct 22, 2026
- ooooooooooooooooooop/personal-aitheir own version, first seen Oct 22, 2026
- BigY0shi/super-skillstheir own version, first seen May 7, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- BigY0shi/super-skills★ 4same name
- ooooooooooooooooooop/agent-tools★ 4same name
- ooooooooooooooooooop/personal-ai★ 4same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
Files
🔬 Research Lab — 科研模式
触发词
"进入科研模式"、"开始做科研"、"research mode"、发论文链接(arxiv/doi)、 提到"假设"、"实验设计"、"文献综述"、"研究课题"
能力清单
1. 文献检索与阅读
- PubMed 搜索:
bash skills/research-lab/scripts/pubmed-search.mjs "关键词" [--max 10] - 论文阅读: 微信/网页论文自动提取+摘要+关键点提炼
- 文献管理: 录入飞书追踪表
2. 假设驱动循环（Hypothesis-Driven Loop）
Plan → Evidence → Review → Iterate- 假设提出: 结构化记录到
research/projects/{name}/hypotheses.md - 证据收集: 自动/手动收集支持/反驳证据
- 评估审查: 定期回顾假设状态
- 迭代: 根据证据调整假设
3. 研究项目管理
- 项目目录:
research/projects/{project-name}/ - 每个项目包含:
README.md— 项目概述hypotheses.md— 假设追踪evidence/— 证据文件notes/— 阅读笔记references.md— 参考文献列表progress.md— 进展日志
4. 知识整合
- 飞书文档: 研究笔记/论文草稿
- 飞书表格: 假设追踪表/文献管理表
- Memory: 长期研究记忆（自动更新 MEMORY.md）
使用方式
进入科研模式
用户说"进入科研模式"时:
- 确认当前研究项目（已有则加载，没有则创建）
- 展示项目状态（假设数、文献数、最近进展）
- 列出可用操作
日常操作
- "搜一下 XXX 的最新论文" → PubMed 搜索
- "读一下这篇论文 [链接]" → 提取+摘要+录入
- "提出一个假设：XXX" → 结构化记录
- "整理一下目前的证据" → 汇总分析
- "项目进展怎么样" → 状态报告
退出科研模式
"退出科研模式"或"回到正常模式" → 保存状态，恢复正常
工具依赖
- PubMed E-utilities API（免费，无需key）
- arXiv API（免费，无需key，支持短语匹配）
- Semantic Scholar API（免费，无需key，含引用统计/TLDR）
- 微信文章读取（已有 wechat-article-reader）
- 飞书文档/表格 API（已有）
搜索脚本速查
Node.js 脚本（代理支持好，推荐日常用）
| 脚本 | 覆盖领域 | 用法 |
arxiv-search.mjs | CS/AI/ML/数学/物理 | node arxiv-search.mjs "关键词" --max 10 --sort date |
pubmed-search.mjs | 生物医学/生命科学 | node pubmed-search.mjs "关键词" --max 10 --sort date |
s2-search.mjs | 综合学术（含引用数） | node s2-search.mjs "关键词" --max 10 --sort citationCount |
scholar-search.mjs | 三源合一 | node scholar-search.mjs "关键词" --sources all --max 5 |
Python 工具（paperscraper + semanticscholar）
| 命令 | 说明 |
python3.11 scholar.py search "关键词" --source all --max 5 | 统一搜索 |
python3.11 scholar.py search "关键词" --source s2 --json | 仅 Semantic Scholar（含引用/TLDR） |
python3.11 scholar.py search "关键词" --source pubmed | 仅 PubMed |
python3.11 scholar.py download DOI_OR_ARXIV_ID -o ./papers/ | 下载 PDF |
通用参数: --max N 数量 | --sort date|relevance|citationCount | --json JSON输出
scholar-search.mjs 额外参数: --sources all|arxiv|pubmed|s2
已安装 Python 包
paperscraper0.3.6 — PubMed/arXiv/bioRxiv/medRxiv/chemRxiv 搜索 + PDF 下载semanticscholar0.12.0 — Semantic Scholar API 客户端（引用图谱/推荐）
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.