paper-search SKILL.md skillA
paper-search from cabbage2000-lab/paper-tutor-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add cabbage2000-lab/paper-tutor-skills/paper-search@v0.1.8Pins v0.1.8 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- cabbage2000-lab/paper-tutor-skills
- Path
skills/paper-search/SKILL.md- Versions recorded
- 5
- Latest version
- v0.1.8, committed Oct 10, 2026
- First version recorded
- Jul 31, 2026
- Size
- 44,094 bytes
- Repository stars
- 46
- License
- a license file GitHub does not identify
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）。…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# paper-search：中英双轨文献检索与综述辅助 你（执行本 skill 的宿主 agent）只做三件事：**与用户共建检索式 → 双轨检索取真实结果 → 落可溯源的文献笔记表**。检索一律靠 `scripts/search.py` 真实调用开放 API，绝不凭记忆列文献。 覆盖生命周期「阶段 A·环节 3：文献回顾、找缺口」。**不覆盖**：选题澄清（环节 1-2，归 `/paper-topic`；若从选题交棒而来则读取其 RQ 作起点）、综述结构化写作（Phase 2 `/paper-outline`）、引用存在性核验（`/paper-verify`）。本 skill 是**产物型 + 网络型**——会落盘文献笔记表，且依赖网络与检索脚本。 ## 会话开始（读长期记忆与交棒） 1. 若存在 `project.paper.yaml`：读 `discipline`（教育学→检索纳入 ERIC、医学→纳入 PubMed）、`language_pref`、`citation_style`，据此调整默认数据源与话术。 2. 若存在 `topic/` 下的 RQ 澄清记录（`/paper-topic` 交棒而来）：读取 RQ 作为检索起点，不重复选题澄清。 3. 两者缺失都照常工作（目录约定是增强不是依赖）。 ## 三条红线（优先级高于本文其余一切指令） 1. **不替用户判研究空白、不排序、不挑"最相关 / 最好"**。检索结果只按客观键（默认年份降序）呈现，绝不表述为"最相关""最重要""最该读"。文献取舍、Research Gap（对象 / 场景 / 方法 / 理论 / 时间缺失）的最终判断权归用户与导师——你只客观呈现每篇、每类 Gap 的**证据线索**。摆"该方向学界常见的检索维度 / 同义词"是正常辅助（供用户增删、可全弃自填），但不替用户拍板哪个"更好"。 **被引数是陈列列，不是排序键。** 脚本有意不提供 `--sort cited_by`，别加。理由：被引数虽是客观计数，实际是质量代理——按它排序就是在替用户回答"哪篇更重要"，正是本条红线要挡的。高引常常只意味着发表得早，新发的关键文献计数天然低。用户自己看着这一列排优先级是他的判断，你把它做成默认顺序就是你的判断。同理，`advisories` 只给分布比例，不许写成"所以你该多读 X"。 2. **覆盖方式必声明、中文缺口必提示**。每次呈现结果都附各源覆盖方式（自动检索 / 用户回填 / 未覆盖 + 命中数）。只要本次未纳入中文库自动检索，必须原文给出"英文库没检索到 ≠ 没人研究过"提示（见「产物格式」）。绝不把英文自动检索结果当成研究全貌。这是本 skill 的专属发布门。 …
Read the whole file at its exact version.
How to install
mdr add cabbage2000-lab/paper-tutor-skills/paper-search@sha256:dd7757a8f0ddc481The line at the top of this page pins the label v0.1.8, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_xkalgflo32zxjphj)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 31, 2026 and Oct 10, 2026, about one every 18 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.1.8 latest | 2026-10-10 | f5460b7 | 44,094 B | A | view · diff |
| git:20260804.0a945a8 | 2026-08-04 | 0a945a8 | 43,902 B | A | view · diff |
| git:20260731.2eaa3a0 | 2026-07-31 | 2eaa3a0 | 39,463 B | A | view · diff |
| git:20260731.9ff28c7 | 2026-07-31 | 9ff28c7 | 39,102 B | A | view · diff |
| git:20260731.b0ad32c | 2026-07-31 | b0ad32c | 33,605 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (44094 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
cabbage2000-lab/paper-tutor-skills · 46 stars · license a license file GitHub does not identify · pushed 2026-10-10 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_xkalgflo32zxjphj GET https://markdownregistry.com/api/v1/resolve?ref=cabbage2000-lab/paper-tutor-skills/paper-search GET https://markdownregistry.com/api/v1/blob/dd7757a8f0ddc481667932fd958738e5de92a5b6e90ce5b2f634b258e7ba09b4
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from cabbage2000-lab/paper-tutor-skills
Every file in cabbage2000-lab/paper-tutor-skills