fulltext-draft SKILL.md skillA
fulltext-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/fulltext-draft@git:20260720.26d5eefPins git:20260720.26d5eef 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/fulltext-draft/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260720.26d5eef, committed Jul 20, 2026
- First version recorded
- Jul 3, 2026
- Size
- 3,365 bytes
- Repository stars
- 10
- License
- a license file GitHub does not identify
全文初稿扩写（乔淼PhD · AI学术训练营 · AI学术工作流 · 全文初稿步骤 · 管线终点）。把 文章框架.md 的段落骨架扩写成可打磨的全文段落初稿：正文语言最高优先级规则、方法论节直接采用研究设计初稿、结果节据 研究发现.md 撰写（缺则占位，绝不编造数据/引语）、每段紧扣骨架功能与引用角色、文末撰写说明。Trigger on："扩写全文初稿"、"把框架写成全文"、"写全文初稿"、"expand my framework into a full draft"、"draft my full 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
# Fulltext Draft · 全文初稿扩写（管线终点） 把文章框架的 Part 2 段落骨架扩写为可读的段落文字初稿，整合全部可用产出。 ## 调用约定（独立运行） - 输入按"用户直给 > 项目文件 > 降级"解析： 1. **文章框架（必需）**：`文章框架.md`（article-framework 的产出）或用户给的框架文件。没有 → 先跑 `article-framework`。 2. **研究设计初稿（可选）**：`研究设计初稿.md` 存在 → 方法论节直接采用其 Sec 4 draft，不另起炉灶。 3. **数据分析产出（可选）**：优先 `研究发现.md`（已按 RQ 整合的综合发现）作为 Results/Findings 节权威依据；不存在 → 退回逐轮原始产出（quant-* / qual-* / 分析日志.md）归并；两者皆无 → 本节只留骨架（一行"此节占位 · 待数据落地后撰写"），**不凭空编造数据或访谈引语**。 4. 综述初稿 / 选题（引用候选与改写素材）：有则用，没有则按框架里的引用候选与 [TBD-citation] 处理。 - 落盘：`全文初稿.md`（默认当前工作目录）。 - **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。 ## 强制要求 - 🌐【正文语言 · 最高优先级】正文必须严格使用指定输出语言撰写，不得默认或回退到中文：英文项目 → 正文全英文；中英双语 → 指定语种正文 + 必要处中文对照/教学点；中文项目才用中文。任何"字数/词数"说明都只是长度参考，不决定语言，更不得把正文改写成中文。 - 结果/发现节：按 研究发现.md 的逐子问题/假设结论 + 证据整合 + 方法间一致性组织，引用真实数值/引语。 - 其余各节都必须生成对应的段落文字初稿。 - 每个段落：紧扣骨架"功能"字段；按"引用角色"嵌入相应文献（锚定/定位/框架）；长度参考（英文每段约 150-300 词 / 中文每段约 250-500 字，按实际撰写语言取区间）；不要写成提纲，要写成可直接打磨的段落散文；引用就地标 [Author Year]，参考文献列表附文末。 - 保留框架的节序号和段序号，与骨架一一对应；各节起始加一句"本节功能（一行）"。 - 全文末尾追加"撰写说明"：哪些段落基于综述初稿改写、哪些基于 Model Paper 仿写、哪些基于研究设计初稿（方法论）、哪些基于数据分析产出（结果/发现）、哪些需要补充文献后再扩写。
Read the whole file at its exact version.
How to install
mdr add qiaomiaojoe/ai-academic-workflow/fulltext-draft@sha256:e63f2fbc119d240bThe line at the top of this page pins the label git:20260720.26d5eef, 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_pvnwwfilglurp4i4)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Jul 3, 2026 and Jul 20, 2026, about one every 6 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260720.26d5eef latest | 2026-07-20 | 26d5eef | 3,365 B | A | view · diff |
| git:20260717.59c14bf | 2026-07-17 | 59c14bf | 3,036 B | A | view · diff |
| git:20260704.8f9ae45 | 2026-07-04 | 8f9ae45 | 3,070 B | A | view · diff |
| git:20260703.eabb41d | 2026-07-03 | eabb41d | 9,629 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 (3365 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_pvnwwfilglurp4i4 GET https://markdownregistry.com/api/v1/resolve?ref=qiaomiaojoe/ai-academic-workflow/fulltext-draft GET https://markdownregistry.com/api/v1/blob/e63f2fbc119d240be1dc074e321ed2fe15168a772de681c85adcb8e0a418d2da
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.