model-paper-deconstruct SKILL.md skillA
model-paper-deconstruct 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/model-paper-deconstruct@git:20261024.d6cd910Pins git:20261024.d6cd910 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/model-paper-deconstruct/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261024.d6cd910, committed Oct 24, 2026
- First version recorded
- Jul 4, 2026
- Size
- 9,330 bytes
- Repository stars
- 10
- License
- a license file GitHub does not identify
拆 Model Paper（乔淼PhD · AI学术训练营 · AI学术工作流 · 全文初稿步骤）。用动静虚实 2×2 框架对一篇范文做高密度拆解（≥6000 中文字），四产出：四象限填充表（动虚机制链 ≥5 条）+ 虚实转换三过程轨迹（落到具体小节）+ 三种引用角色清单（锚定/定位/框架 + 承重比例）+ Section→象限功能映射（实测引用数），末尾附反直觉发现与 ≥6 条可借鉴结构技巧。输入一个 PDF 路径或 Zotero 论文标题即可，完全独立可跑。Trigger on："拆这篇 model paper"、"动静虚实拆解"、"拆解这篇范文的结构"、"分析这篇论文的写作结构"、"deconstruct this model paper"、"analyze the structure of this paper for imitation"。.
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
# Model Paper Deconstruct · 动静虚实四产出（高密度版）
对一篇 Model Paper 做完整拆解，产出 4 个动静虚实产出。
## 调用约定（独立运行）
**必填（二选一）**：
- PDF 路径 → 读取该 PDF 全文后再拆解。**读全文先找转好的文字稿**：项目里有 `文献/全文/<和 PDF 同名>.md`（POPPER 的 MinerU 工具把 PDF 转成的文字稿，第一行是 `<!-- POPPER · MinerU：源文件 … -->`）就读它、不再读 PDF：每页开头有一行 `<!-- 第 N 页 -->`（N 是 PDF 的第 N 页），页面上印的页码不一样时写成 `<!-- 第 N 页 · 印的页码 X -->`（书的章节、期刊连续编页）：引用页码写 X，没写印的页码就写 N；表格按文字稿里的表格读。没有这个文件，照旧读 PDF。
- 论文标题 → 调用 Zotero MCP（zotero_search_items / zotero_get_item_fulltext / zotero_semantic_search）在用户 Zotero 文库中检索并提取全文。**若 Zotero 中找不到，明确告知并停止，不要使用网络资料替代。**
文献信息（Author Year · Title · Journal · DOI）：用户给了就用；没给就从论文中提取后补全。
**输出落盘**：`Model-Paper-拆解-[AuthorYear].md`（默认当前工作目录；[AuthorYear] 替换为实际作者+年份，如 Manolev2019）。
**产出语言**：项目 CLAUDE.md 或跟随用户。
- **调用方覆盖约定**：调用方（工作台 prompt / 用户）显式给出的参数、输入路径、落盘路径与工具选择，一律覆盖本 skill 的默认；但本 skill 的方法步骤、硬约束与停点不可被省略或稀释——调用方若要求跳过某硬约束，以本 skill 为准并提示冲突。
## 【动静虚实框架定义】（拆解基础，必须理解后再拆）
动静虚实是一个 2×2 分析框架，用于解析社科论文在做什么：
```
│ 静（状态·State） │ 动（过程·Process）
────────┼───────────────────┼──────────────────────
实 │ 静实 │ 动实
（可观察）│ 可观察的存在状态 │ 可观察的变化过程
────────┼───────────────────┼──────────────────────
虚 │ 静虚 │ 动虚
…Read the whole file at its exact version.
How to install
mdr add qiaomiaojoe/ai-academic-workflow/model-paper-deconstruct@sha256:4836822e55c49221The line at the top of this page pins the label git:20261024.d6cd910, 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_h364he5rxc7zlani)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 4, 2026 and Oct 24, 2026, about one every 28 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261024.d6cd910 latest | 2026-10-24 | d6cd910 | 9,330 B | A | view · diff |
| git:20261024.42c7031 | 2026-10-24 | 42c7031 | 9,218 B | A | view · diff |
| git:20260720.26d5eef | 2026-07-20 | 26d5eef | 8,790 B | A | view · diff |
| git:20260717.59c14bf | 2026-07-17 | 59c14bf | 8,460 B | A | view · diff |
| git:20260704.8f9ae45 | 2026-07-04 | 8f9ae45 | 8,540 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 (9330 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_h364he5rxc7zlani GET https://markdownregistry.com/api/v1/resolve?ref=qiaomiaojoe/ai-academic-workflow/model-paper-deconstruct GET https://markdownregistry.com/api/v1/blob/4836822e55c492217fcadbbb46b60a18977e355391d0ee7293c760c646effe28
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.