paper-search
paper-search is a Literature review & citations skill for AI agents, published by cabbage2000-lab in the paper-tutor-skills repository on GitHub. Skillspace rates paper-search F (53/100) and it passed the safety scan; the rating is based on static analysis only.
文献检索与综述辅助命令。当用户已有研究问题(RQ)或明确方向,要查文献、做文献综述、找研究缺口(Research Gap)、了解"某方向别人做到哪一步"时使用——即使用户只说"帮我查查这方面的研究""这个领域有哪些论文""有没有人研究过 X""这方面国内外做到什么程度了""帮我搜搜文献""顺着这篇的参考文献往下找""谁引用了这篇""某某老师 / 这位作者发过哪些论文" "这几篇是不是同一个人写的""这些能不能免费下载 / 有没有全文""哪几篇是开放获取(OA)的""有没有 PMC 全文"也应使用。中英双轨:英文接开放 API(Crossref / OpenAlex / Semantic Scholar / arXiv)自动检索,中文走"自动 + 引导"(DOI 命中自动检索,其余生成知网 / 万方检索方案引导用户检索,站内官方导出的 BibTex / EndNote 文件可解析入表)。支持滚雪球补召回(由一篇核心文献取参考文献 / 被引文献,补关键词检索漏掉的经典与最新跟进), 以及按作者检索(先列同名候选带 ORCID / 机构 / 研究领域,由用户选定后再取其论文)。 行为铁律:真实 API 检索绝不凭记忆编造文献 / DOI;每次产出必声明各源覆盖方式(自动检索 / 用户回填 / 未覆盖)、中文版图未补齐必提示"英文库没有≠没人研究过";不替用户排序 / 挑"最相关最好" / 判定研究空白(判断归用户), 被引数与开放获取状态只陈列不排序、不当阅读优先级,只给源提供的合法开放版本链接与官方获取入口、 绝不提供绕过付费墙的路径(不给 Sci-Hub 类镜像站、不代抓订阅内容、不批量代下);同名作者归并只认 ORCID 这个客观键,绝不按姓名 / 机构猜同一人,也不替用户选是哪位候选; 断网显式声明检索不可用;"帮我写综述 / 编几篇文献凑数"走三段式转化,绝不代写、绝不编造。
- Grade
- F
- Quality
- 53 / 100
- Safety
- Passed
- GitHub stars
- 25
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 73 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
Not checked yet
- Category is a classifier prediction; no model has read this skill yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.