skill-workshop-plan SKILL.md skillA
skill-workshop-plan 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/skill-workshop-plan@git:20261014.1ae645bPins git:20261014.1ae645b 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/skill-workshop-plan/SKILL.md- Versions recorded
- 4
- Latest version
- git:20261014.1ae645b, committed Oct 14, 2026
- First version recorded
- Jul 4, 2026
- Size
- 4,316 bytes
- Repository stars
- 10
- License
- a license file GitHub does not identify
数据 Skill 工坊 · 规划 + 找料（乔淼PhD · AI学术训练营 · AI学术工作流）。诊断现成分析 skills（analyze-quantitative-data / analyze-qualitative-data）够不够、要不要造新 skill、造哪几个（带停点等确认）；确认后检索权威方法学源材料（教科书章节 / 方法学经典 / 官方手册）下载到源材料文件夹并写 源材料清单.md。造 skill 本身用 skill-forge。Trigger on："规划要造哪些数据分析 skill"、"我这个方法现成 skill 够不够"、"帮我找造 skill 的方法学材料"、"plan and source materials for a new analysis skill"。.
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
# Skill Workshop Plan · 规划 + 找料 到"下料齐 + 写清单"为止，不直接造 skill（造 skill 用 `skill-forge`）。 ## 调用约定（独立运行） - 方法需求按优先级：用户直接说的方法链（如"我要跑 HLM"）> `研究设计初稿.md` + `研究设计-设计说明.md`（B3 分析框架）+ 备用 `选题.md` > 都没有 → 问用户手动给方法关键词，**不凭空假设方法**。 - 落盘：源材料与清单进 `skill源材料/`（用户指定或当前工作目录）。 - **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。 ## 阶段 1 · 诊断要不要造、造哪几个 1. 从方法需求抽出实际要用的分析方法链（具体到统计模型 / 编码流派 / 特定流程，不要泛泛说"做回归"）。 2. 对照现成 skills 判断覆盖度： - `analyze-quantitative-data`（Neuman 7e Ch12：codebook→cleaning→univariate→bivariate→elaboration→regression→inferential） - `analyze-qualitative-data`（Neuman 7e Ch14：开放/轴心/选择性编码 + analytic memo + outcropping + 理想型 + Mill 比较） 3. 诊断结论：**现成够用** → 指明用哪个 + 从哪步起 + 为什么够用，结束（不必造，不必下料）；**需要新建** → 逐个列：skill 主题 + 建议名（小写连字符 + 方法论锚，如 analyze-hlm-by-raudenbush）+ 一句话定位 + 现成 skill 缺在哪。 →【停】把诊断结论给用户确认：用现成的还是造新的？造哪几个？确认后再进阶段 2。 ## 阶段 2 · 找料 + 下载（确认要造之后才做） 对每个确认要造的 skill，找**权威方法学源材料**（教科书章节 / 方法学经典论文 / 官方手册）： 1. 先列候选清单给用户点头：标题 / 作者·年 / 类型 / 为什么权威（领域公认度）/ 拟用章节。**不要先下载**。 …
Read the whole file at its exact version.
How to install
mdr add qiaomiaojoe/ai-academic-workflow/skill-workshop-plan@sha256:df5b584a7d9084d8The line at the top of this page pins the label git:20261014.1ae645b, 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_oeegfdx7mm24gotr)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Jul 4, 2026 and Oct 14, 2026, about one every 34 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261014.1ae645b latest | 2026-10-14 | 1ae645b | 4,316 B | A | view · diff |
| git:20260720.26d5eef | 2026-07-20 | 26d5eef | 3,497 B | A | view · diff |
| git:20260717.59c14bf | 2026-07-17 | 59c14bf | 3,168 B | A | view · diff |
| git:20260704.8f9ae45 | 2026-07-04 | 8f9ae45 | 3,215 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 (4316 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_oeegfdx7mm24gotr GET https://markdownregistry.com/api/v1/resolve?ref=qiaomiaojoe/ai-academic-workflow/skill-workshop-plan GET https://markdownregistry.com/api/v1/blob/df5b584a7d9084d83351f34d627fb06797adf35e2aeabac20329c9dab23aa801
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.