topic-pxyv-parse SKILL.md skillA
topic-pxyv-parse 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-pxyv-parse@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-pxyv-parse/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260717.59c14bf, committed Jul 17, 2026
- First version recorded
- Jul 4, 2026
- Size
- 3,582 bytes
- Repository stars
- 10
- License
- a license file GitHub does not identify
已有选题的 PXYV 四维拆分（乔淼PhD · AI学术训练营 · AI学术工作流）。用户已有现成的选题 / 研究计划 / 摘要 / RP，不需要重跑选题三阶段，只需要把它结构化成 PXYV（P 理论视角 / X 现象 / Y 语境 / V 贡献）+ RQ + workbench 锚块，好直接接文献搜索、研究设计等下游步骤；同时诊断四维的缺口与弱点。Trigger on："把我的选题拆成 PXYV"、"我已经有选题了，帮我结构化"、"给我的研究计划做 PXYV 拆分"、"parse my topic into PXYV"、"structure my existing research idea"。.
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 PXYV Parse · 已有选题 → PXYV 四维拆分 不是选题教练，不重跑三阶段——把用户**已有的**选题结构化成 PXYV，并诊断缺口。 ## 调用约定（独立运行） - 输入：用户粘贴的选题描述 / 研究计划 / 摘要 / RP 段落，或一个文件路径。都没有 → 请用户用几句话说清「想研究什么、用什么视角、在什么语境、图什么贡献」。 - 落盘：`选题.md`（顶部含锚块，与选题工作流产出格式一致，下游无感），默认当前工作目录；用户只要会话内结果就不落盘。 - 产出语言：项目 CLAUDE.md 有设定则从之，否则跟随用户。 ## 协议 **1 · 判型**：先判断这个选题最贴近哪种模式（①理论诠释 ②假设检验 ③概念建构 ④方法驱动），一句话理由，写入锚块 mode 字段。 **2 · 四维拆分**（每一维给出拆分 + 依据原文的哪句话；拆不出来就标 [缺失]，不要硬编）： - **P 理论视角**：用的什么理论 / 范式 / 方法范式？提醒：P 不是访谈 / 田野等数据方法。 - **X 现象**：研究对象是什么？学界可能的标准术语是什么（给 1-2 个候选）？ - **Y 语境**：时空 / 人群 / 行业 / 制度语境。 - **V 贡献**：这个研究图什么？按贡献阶梯初步定级（L1 语境扩展 / L2 机制条件 / L3 构念方法 / L4 假设挑战），并给 so-what 双句草案（① 理论/领域增量句 ② 现实利害句——具体人群/机构，不接受"全社会"）。 **3 · RQ / 标志产出提取**：从原文提取（或按 mode 体例草拟 2-3 版让用户选）：mode ① RQ/Thesis；mode ② H 假设链方向；mode ③ 原创概念 + 开放 RQ；mode ④ Aims/直接陈述。 **4 · 缺口诊断**（一张表）：`| 维度 | 拆分结果 | 强/弱/缺失 | 建议 |`——弱或缺失的维度给具体建议：P 弱 → 建议跑对应 mode 选题 skill 的 A.3；V 没校准 → 建议跑阶段 B 校准（B.4 V 空白检验 + B.5 近邻对位）；近邻空缺 → 建议用 `lit-verify` + 检索补 5 近邻。**不替用户补编内容，只指路。** **5 · 产出锚块 + 正文**： ``` <!-- workbench mode: [1-4] title: [一句话标题] P: … | X: … | Y: … | V: … V-level: [L1-L4 · 初判，未经 B 校准的标注 (未校准)] SW: [so-what 双句压缩成一句] journal: [有则填，无则 TBD] RQ: [研究问题一句话] neighbors: [有则填；无则留 TBD——未经近邻对位] …
Read the whole file at its exact version.
How to install
mdr add qiaomiaojoe/ai-academic-workflow/topic-pxyv-parse@sha256:78e56cc019c7568bThe 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_fwbelkkinnxusnt6)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Jul 4, 2026 and Jul 17, 2026, about one every 13 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260717.59c14bf latest | 2026-07-17 | 59c14bf | 3,582 B | A | view · diff |
| git:20260704.8f9ae45 | 2026-07-04 | 8f9ae45 | 3,609 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 (3582 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_fwbelkkinnxusnt6 GET https://markdownregistry.com/api/v1/resolve?ref=qiaomiaojoe/ai-academic-workflow/topic-pxyv-parse GET https://markdownregistry.com/api/v1/blob/78e56cc019c7568bdb7e1beea9189b7664da2a8064860398434cbdd725d72c37
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.