topic-workbench SKILL.md skillA
topic-workbench from qiaomiaojoe/ai-academic-workflow is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add qiaomiaojoe/ai-academic-workflow/topic-workbench@git:20260717.59c14bfPins git:20260717.59c14bf in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- qiaomiaojoe/ai-academic-workflow
- Path
skills/topic-workbench/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260717.59c14bf, committed Jul 17, 2026
- First version recorded
- Jul 3, 2026
- Size
- 3,708 bytes
- Repository stars
- 10
- License
- a license file GitHub does not identify
「AI学术训练营」选题工作流总入口（乔淼PhD · AI学术工作流）。当用户想选题但没说用哪种模式时，先分诊：先判大类（研究性文章 / 综述性文章），再判最贴近的模式——研究性 ①理论诠释 ②假设检验 ③概念建构 ④方法驱动；综述性 系统 / 半系统 / 整合式（Snyder 三型）——然后转入对应的独立 skill 执行；用户已有现成选题只需结构化时转 topic-pxyv-parse。Trigger on："帮我选题"、"选题工作流"、"我想做一个关于…的研究，帮我把选题磨出来"、"help me develop a research topic"、"topic coaching"。.
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
# Topic Workbench · 选题分诊入口 用户想选题但没指定模式时，从这里进。本 skill 只做两件事：**判型 → 转对应 skill**。 ## 第一步 · 判大类 先确认用户要写的是哪一类论文（说不清就用一句话问）： - **研究性文章**（做原创研究：实证 / 理论）→ 走下面「研究性 4 模式」。 - **综述性文章**（综合一片文献，不做原创数据）→ 走下面「综述性 3 模式（Snyder 三型）」。 ## 研究性 4 模式 根据用户输入（研究方向 / 问题描述 / 方法取向）判断最贴近的模式，给出判断 + 一句话理由，向用户确认（可改选）： | 模式 | 适用信号 | 转入 skill | |------|---------|-----------| | ① 理论诠释 | 想用某个理论视角诠释一个现象；定性 / 批判取向 | `topic-theory-interpretation` | | ② 假设检验 | 关心 X 对 Y 的影响、中介 / 调节；定量取向 | `topic-hypothesis-testing` | | ③ 概念建构 | 现象是新的，现有理论命名不了，需要造概念 | `topic-concept-construction` | | ④ 方法驱动 | 手里有方法 / 数据，想解决领域已知局限 | `topic-method-driven` | ## 综述性 3 模式（Snyder 2019 三型） **2 问判型**（判完给判断 + 理由，向用户确认）： - Q1｜综述问题是"窄而具体"还是"宽而发散"？窄、具体（某因素效应 / 两变量关系 / 某干预有没有用）→ 系统综述；宽、发散 → 看 Q2。 - Q2｜主要想"理清现状 + 给议程"还是"批判并造一个新框架 / 理论"？理清、给议程 → 半系统；造新框架 / 概念 → 整合式。 | 模式 | 适用信号 | 转入 skill | |------|---------|-----------| | 综述① 系统综述 | 窄问题 · 要证据说话 · 有一批可比实证（要量化合成 → +meta-analysis） | `topic-review-systematic` | | 综述② 半系统 / 叙事 | 宽而跨学科的主题 · 想理清脉络 / 主题 · 给研究议程 | `topic-review-semisystematic` | | 综述③ 整合式 | 想批判性整合、造一个新框架 / 概念 / 类型学 | `topic-review-integrative` | ## 特殊入口 - 用户**已有现成选题 / 研究计划**，只需要结构化成 PXYV（好接文献搜索等下游）→ 转 `topic-pxyv-parse`，不必重跑三阶段。 …
Read the whole file at its exact version.
How to install
mdr add qiaomiaojoe/ai-academic-workflow/topic-workbench@sha256:d1be4eaed57fc7caThe line at the top of this page pins the label git:20260717.59c14bf, 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_j3fpwx3qcz7rkdox)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Jul 3, 2026 and Jul 17, 2026, about one every 7 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260717.59c14bf latest | 2026-07-17 | 59c14bf | 3,708 B | A | view · diff |
| git:20260704.8f9ae45 | 2026-07-04 | 8f9ae45 | 2,206 B | A | view · diff |
| git:20260703.eabb41d | 2026-07-03 | eabb41d | 8,251 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 (3708 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
qiaomiaojoe/ai-academic-workflow · 10 stars · license a license file GitHub does not identify · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_j3fpwx3qcz7rkdox GET https://markdownregistry.com/api/v1/resolve?ref=qiaomiaojoe/ai-academic-workflow/topic-workbench GET https://markdownregistry.com/api/v1/blob/d1be4eaed57fc7ca2276b838e033a0142f3c57b6ff37db7e9ec39f09cc16e3a3
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.