methodology-draft SKILL.md skillA
methodology-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/methodology-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/methodology-draft/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260720.26d5eef, committed Jul 20, 2026
- First version recorded
- Jul 4, 2026
- Size
- 4,766 bytes
- Repository stars
- 10
- License
- a license file GitHub does not identify
研究设计初稿（乔淼PhD · AI学术训练营 · AI学术工作流 · 研究设计步骤）。把选定的研究设计方案展开为完整研究设计：B1 全局方法决策 → B2 方法论段骨架（6 维度表）→ B3 可执行设计清单（抽样矩阵/访谈提纲或问卷/编码书或统计链/信效度伦理/时间线）→ B4 合成干净版 Sec 4 方法论 draft，落两份分离文件（初稿 + 设计说明）。Trigger on："展开研究设计初稿"、"写方法论初稿"、"把选定方案变成研究设计"、"draft my methodology section"。.
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
# Methodology Draft · 研究设计初稿（B1-B4） 把用户**选定的方案**展开为完整研究设计与干净的 Sec 4 方法论 draft。 ## 调用约定（独立运行） - 输入：① 选定的研究设计方案（来自 `methods-map` 的 A4，或用户直接口述：路径/方法链/对标文献）② 方法地图 + methodology_plugin（`方法地图.md`，methods-map 的产出；**没有时降级**：请用户给出主流方法与排除项的判断依据，或先跑 `methods-map`，所有"外挂对照"字段改标 [无外挂·用户口径]）③ RQ 与引用候选来源（`选题.md` + `综述初稿.md`，或用户口头给）④ 用户偏好（样本规模/时间线/软件，可选）。 - 落盘（两份文件分离 · 文件名固定，不改名 / 不加日期后缀——下游 `article-framework` / `fulltext-draft` 按文件名读）：`研究设计初稿.md` + `研究设计-设计说明.md`（默认当前工作目录）。 - 产出语言：项目 CLAUDE.md 或用户指定（英文/双语时 B4 用学术语体，正文约 1200-1500 词）。 - **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。 ## B1 · 全局方法决策 路径 / 结构形式 / 对标 exemplar（承接选定方案，补全理由）。 ## B2 · 方法论段骨架（5-7 段），每段输出 6 维度表 `| 功能（Rationale/Context/Sampling/Collection/Variable/Analysis/Ethics/Limit） | 方法决策（选什么 · 从 mainstream_methods 里排除什么 · 为什么 trade-off） | 外挂对照（methodology_plugin 路径 · 主流/小众/新趋势/gap） | 统计决策（定量段才填：测量层级 → 合法工具链） | 引用候选（来自综述初稿 + 5 近邻，不自造） | 要写什么（3-5 句段落 outline） |` ## B3 · 研究设计清单（把决策变可执行） 1. 抽样设计：抽样矩阵（维度 × 标准 × 目标 N）+ 纳入/排除标准 + 招募路径 + 饱和判定（定性）/ 样本量合规（定量） 2. 数据收集工具：定性 → 访谈提纲（4-5 个 block，每 block 3-5 问）；定量 → 问卷结构（按 section）；录音 / 转录 / 软件细节 …
Read the whole file at its exact version.
How to install
mdr add qiaomiaojoe/ai-academic-workflow/methodology-draft@sha256:f2aa430f67cdd611The 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_5pzcurfyfcsk4agc)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Jul 4, 2026 and Jul 20, 2026, about one every 8 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260720.26d5eef latest | 2026-07-20 | 26d5eef | 4,766 B | A | view · diff |
| git:20260717.59c14bf | 2026-07-17 | 59c14bf | 4,437 B | A | view · diff |
| git:20260704.8f9ae45 | 2026-07-04 | 8f9ae45 | 4,500 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 (4766 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_5pzcurfyfcsk4agc GET https://markdownregistry.com/api/v1/resolve?ref=qiaomiaojoe/ai-academic-workflow/methodology-draft GET https://markdownregistry.com/api/v1/blob/f2aa430f67cdd611e002ba4ccf4593de0ef6498a7ed7beb988f1ddb15ba96344
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.