review-draft SKILL.md skillA
review-draft 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@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/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261024.d6cd910, committed Oct 24, 2026
- First version recorded
- Oct 14, 2026
- Size
- 14,576 bytes
- Repository stars
- 10
- License
- a license file GitHub does not identify
综述文章初稿扩写（乔淼PhD · AI学术训练营 · AI学术工作流 · 综述文章工作台 · 管线终点）。把一篇**综述文章**（review 本身即整篇论文，贡献是综合/框架/议程）按其报告规范（系统→PRISMA / 半系统→RAMESES / 整合→Torraco 2005）扩写成综述初稿：读 综述选题.md 机器锚块定型定规范 + 证据综合.md 写综合/结果节（缺则占位，绝不编造数据/引语）+ 语料库 PRISMA 筛选记录写方法节 + 逐条引用核验出独立报告 + 参考文献表 + 反 AI 味 + 初稿纯净 + 转 docx。区别于 `review-draft-assembly`（那是给**实证论文**写文献综述**节**）。方法锚 Snyder (2019)。Trigger on："写综述文章初稿"、"把综述扩写成初稿"、"按 PRISMA/RAMESES/Torraco 成文"、"draft my review article"、"write up my literature review paper"。.
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 · 综述文章初稿扩写（综述文章工作台 · 管线终点）
把一篇**综述文章**扩写成可打磨的全文段落初稿。综述文章的 review 本身就是整篇论文——不是实证论文里的文献综述节（那用 `review-draft-assembly`）。成文结构由**报告规范**决定：系统综述→PRISMA、半系统/叙事→RAMESES、整合式→Torraco (2005)。
方法锚：Snyder, H. (2019). Literature review as a research methodology: An overview and guidelines. *Journal of Business Research*, 104, 333-339.
## 调用约定（独立运行）
- 输入按"用户直给 > 项目文件 > 降级"解析：
1. **综述选题.md（必需）**：读**文件最顶部的机器锚块**，取 `review_type`（systematic / semi-systematic / integrative）与 `report_standard`（PRISMA / RAMESES / Torraco (2005)）**定成文结构**；读锚块下方【综述规格块】（RQ / 纳入排除 / 组织框架 / 预期贡献）+【PXYV 派生投影】+ 近邻综述表作为写作依据。缺 → 指路先去「综述文章工作台」阶段① 用 `topic-review-*` 产出综述选题.md。
2. **证据综合.md（③ 综合结果）**：存在 → **综合 / 结果节**据其逐子问题结论 + 证据整合撰写（meta-analysis 报效应量与 CI、定性报主题与脉络、整合式报新框架）；不存在 → 退回逐轮原始产出（`综合-*` / 分析日志.md）归并；两者皆无 → 综合/结果节只留骨架（一行"此节占位 · 待③综合落地后撰写"），**不凭空编造效应量、主题或引语**。
3. **语料库 + 筛选记录（`文献/检索筛选/`：检索记录.md / 纳入排除标准.md / 选择流程.md（旧项目为 PRISMA流量.md）/ 筛选决定.csv）**：存在 → **方法节**的检索策略 / 纳入排除 / 数量流（识别→去重→**未进入筛选**→摘要筛→纳入）+ 流程图据其撰写；缺 → 方法节按综述选题.md 的检索协议种子写，并在交付说明标注"检索执行记录待补"。
⚠️ **上游是摘要层定稿模式**（`sr-search-record`）：筛选只在题名/摘要层完成，**没有全文合格性评估层**。方法节的数量流因此**没有"全文筛"这一段**，不得凭骨架补一个。这条与「未进入筛选（相关性排序预算外）」一起，都是必须如实写出的流程事实。
…Read the whole file at its exact version.
How to install
mdr add qiaomiaojoe/ai-academic-workflow/review-draft@sha256:4d00a58b521abcd1The 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_d2r7q42fwh7r2amc)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Oct 14, 2026 and Oct 24, 2026, about one every 3 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261024.d6cd910 latest | 2026-10-24 | d6cd910 | 14,576 B | A | view · diff |
| git:20261024.42c7031 | 2026-10-24 | 42c7031 | 14,464 B | A | view · diff |
| git:20261015.26ae0d2 | 2026-10-15 | 26ae0d2 | 13,991 B | A | view · diff |
| git:20261015.61b50d3 | 2026-10-15 | 61b50d3 | 12,068 B | A | view · diff |
| git:20261014.31e7871 | 2026-10-14 | 31e7871 | 11,899 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 (14576 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_d2r7q42fwh7r2amc GET https://markdownregistry.com/api/v1/resolve?ref=qiaomiaojoe/ai-academic-workflow/review-draft GET https://markdownregistry.com/api/v1/blob/4d00a58b521abcd1926b2f3fe8cb6bd56fd3a2ad430c1b9612fb0ddaa5652122
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.