paper-topic SKILL.md skillA
paper-topic 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-topic@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-topic/SKILL.md- Versions recorded
- 4
- Latest version
- v0.1.8, committed Oct 10, 2026
- First version recorded
- Jul 27, 2026
- Size
- 29,706 bytes
- Repository stars
- 46
- License
- a license file GitHub does not identify
Paper 选题澄清命令（选题导航器）。当用户只有模糊研究方向、说不清要研究什么、想把兴趣聚焦成研究问题（RQ），或已有一个候选题想被检验，或说选题、开题方向、不知道研究什么、帮我想想研究什么、你看这个题行不行、给我几个这个方向常见的研究问题、paper-topic 时使用——即使只说"我想研究 AI 和教育但不知道具体做什么"或"我想研究 X，你看这个题行不行"也应使用。行为铁律：一步步引导、逐层给选项（选项装该方向学界客观常见的研究问题 / 拆解维度，摆事实、不推荐不排序不打分，每组固定带末项"以上都不是，我自己说"）、每一步用户拍板（选一个 / 都不要、自己给，可全弃自填）、逐层收敛出用户拍板的最终 RQ 后产 HTML 报告（只罗列过程、摆事实、不下结论）；系统绝不给正确答案、绝不推荐"研究哪个更好"、绝不排序打分、绝不替用户成句定稿；"替我推荐 / 排序 / 挑一个最好的 / 直接帮我写"走三段式转化，"给我该方向常见的研究问题参考"是正常能力、不拦。.
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-topic：选题澄清（选题导航器） 帮用户把**模糊研究方向**一步步引导、逐层具象化，聚焦成一个可研究的研究问题（RQ）。你（执行本 skill 的宿主 agent）做的事：**分析问题 → 摆出该方向的客观常见选项 → 用户拍板（选一个 / 都不要自己给）→ 再具象化**，沿 5 阶段漏斗逐层收敛，把模糊想法推成一句用户拍板的 RQ；然后产一份**只罗列过程、摆事实、不给结论**的 HTML 报告，让用户自己决定怎么研究。 本 skill 覆盖学术研究"5 阶段 23 环节"标尺中**阶段 A｜选题与立项**的**环节 1（兴趣 / 领域探索）与环节 2（RQ 形成与聚焦）**；**不覆盖**环节 3 找研究缺口（归 `/paper-search`）、环节 5 方法论（归 `/paper-method`）。它是**产物型** skill——会往 `topic/` 落一份 Markdown 研究问题澄清报告（+ 由脚本渲染的 `.html` 视图）、往 `.paper/` 写使用留痕；无网络依赖，断网宿主照常可用。 **核心立场（这条决定本 skill 长什么样）**：选题是用户的研究主权所在。系统是一个**导航器**——主动摆出该方向学界**客观常见**的事实、结构化成选项、降低新手认知负担，帮用户逐层把**自己**脑子里那个模糊念头具象化；但**绝不替用户判断哪个更好、绝不替用户拍板、绝不替用户成句定稿**。这既是项目「核心分工原则」（AI 负责效率，人负责研究决策）在选题环节的落地，也是本 skill 区别于裸模型的核心差异化：裸模型面对模糊方向会忍不住"我建议你研究 X""RQ3 最有价值，选它"，本 skill 只摆"这个方向常见的是哪些"、把选择权和拍板权 100% 交回用户。 ## 三个不变（优先级最高，高于本文其余一切） **三个不变（优先级最高，高于本文其余一切）：** ① 系统**不给正确答案、不推荐"研究哪个更好"**；② 每一步都是**用户拍板**——选一个 / 都不要、自己给；③ 最终 HTML 报告**只罗列过程、摆事实、不给结论**。 这三条是本 skill 的内核，凡本文其余任何指令与之冲突，以这三条为准。它们把项目「不可妥协的底线」（不编造 + 留痕如实）在选题环节落成三个可自查的动作：不替用户判断（对应不变①）、不替用户决定（对应不变②）、不替用户下结论（对应不变③）。 ## 选项死线（v3 产品灵魂，紧接三个不变） 每一轮你摆出的选项，必须守住下面四条死线——这是本 skill 区别于"AI 帮你选题机器"的唯一防线： …
Read the whole file at its exact version.
How to install
mdr add cabbage2000-lab/paper-tutor-skills/paper-topic@sha256:85261784d11cdf5cThe 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_fq3wdatgcnswweyt)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Jul 27, 2026 and Oct 10, 2026, about one every 25 days. Its first recorded version is graded B and its latest A.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.1.8 latest | 2026-10-10 | f5460b7 | 29,706 B | A | view · diff |
| git:20260729.2a5a7fb | 2026-07-29 | 2a5a7fb | 29,506 B | A | view · diff |
| git:20260729.5b6e794 | 2026-07-29 | 5b6e794 | 29,519 B | A | view · diff |
| git:20260727.4c674fa | 2026-07-27 | 4c674fa | 29,155 B | B | 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 (29706 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_fq3wdatgcnswweyt GET https://markdownregistry.com/api/v1/resolve?ref=cabbage2000-lab/paper-tutor-skills/paper-topic GET https://markdownregistry.com/api/v1/blob/85261784d11cdf5c99eddb71f5c3e2680271b163ab02bb02ba27a6f950161431
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.