review-draft-assembly SKILL.md skillA
review-draft-assembly 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/review-draft-assembly@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/review-draft-assembly/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261024.d6cd910, committed Oct 24, 2026
- First version recorded
- Jul 20, 2026
- Size
- 5,806 bytes
- Repository stars
- 10
- License
- a license file GitHub does not identify
综述初稿组装（乔淼PhD · AI学术训练营 · AI学术工作流 · 文献分析步骤）。按综述蓝图把知识模块组装成综述初稿：三 Section 组装规则 + 深读张力句并入 + 逐条引用核验（对照 Zotero/清单出独立报告）+ 参考文献表 + 反 AI 味写作要求 + 初稿纯净交付（零模块编号零 Zotero key）+ 转 docx。Trigger on："组装综述初稿"、"把模块拼成综述"、"综述成稿"、"assemble my literature review draft"。.
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
# Review Draft Assembly · 综述初稿组装 ## 调用约定（独立运行） - 输入：综述蓝图（`综述蓝图.md`，必需）+ 模块产出（`知识模块/M*.md`，旧项目 `模块/M*.md`，必需）+ 可选深读产物（`深读-*.md`，在蓝图同文件夹或旧项目的 `深读/` 里）。缺必需项 → 指路先跑 `review-blueprint` / `knowledge-module-gen`。 - 参数：总字数目标（可选）、引用格式（默认 APA 7th）、输出语言（项目 CLAUDE.md 或用户指定；中英双语 = 先英文 draft 再中文译稿，两稿都要 inline citation）。 - 落盘（默认当前工作目录）：`综述初稿.md`（+ 双语 `-zh.md`）+ 同名 .docx + `引用核验报告.md`。 - **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。 前置： - 综述蓝图.md（必需 · 含框架 + 模块映射 + Section 3 gap） - 知识模块/M1.md … M_n.md（旧项目 模块/；必需） - 深读-*.md（可选，蓝图同文件夹或旧项目的 深读/；若存在自动并入 Section 2） 按「综述蓝图.md」指定的逻辑结构组装综述初稿。 ## 【字数分配】 - 用户给了总字数目标 → 按 Section 1 ~40% · Section 2 ~40% · Section 3 ~20% 分配（可微调）。 - 未给 → Section 1 ≈ 200-400 字 · Section 2 ≈ 200-400 字 · Section 3 ≈ 100-200 字。 - 字数是目标上限，证据不足时宁缺毋滥，不灌水。 ## 【Section 1 · XY 经验段】 - 按蓝图 Section 1 的模块出场顺序整合 - 开头：用蓝图 Section 1 核心 argument 引入 - 主体：依次穿插各模块 output 的核心 finding（含 inline citation） - 张力：模块间的分歧或竞争立场 - 收尾：1 句连接到 Section 2 ## 【Section 2 · PV 理论段】 - 按蓝图 Section 2 的模块论证顺序组装 - 开头：蓝图 Section 2 核心 argument - 主体：理论谱系 + 框架继承/冲突 - 若存在「深读-*.md」：把深读关键论点作为张力句嵌入主体 - 收尾：1 句指向 Section 3 的 gap …
Read the whole file at its exact version.
How to install
mdr add qiaomiaojoe/ai-academic-workflow/review-draft-assembly@sha256:e90e823cfc96340cThe 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_6mjf3h5xf3oyptc6)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 20, 2026 and Oct 24, 2026, about one every 24 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261024.d6cd910 latest | 2026-10-24 | d6cd910 | 5,806 B | A | view · diff |
| git:20261024.42c7031 | 2026-10-24 | 42c7031 | 5,694 B | A | view · diff |
| git:20261014.5e2faed | 2026-10-14 | 5e2faed | 5,221 B | A | view · diff |
| git:20261014.31e7871 | 2026-10-14 | 31e7871 | 5,079 B | A | view · diff |
| git:20260720.26d5eef | 2026-07-20 | 26d5eef | 4,749 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 (5806 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_6mjf3h5xf3oyptc6 GET https://markdownregistry.com/api/v1/resolve?ref=qiaomiaojoe/ai-academic-workflow/review-draft-assembly GET https://markdownregistry.com/api/v1/blob/e90e823cfc96340c5f636b9aba560b5ace48dc39c0b017e1fa18936e69a06335
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.