data-analysis-round SKILL.md skillA
data-analysis-round 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/data-analysis-round@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/data-analysis-round/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260720.26d5eef, committed Jul 20, 2026
- First version recorded
- Jul 3, 2026
- Size
- 5,893 bytes
- Repository stars
- 10
- License
- a license file GitHub does not identify
数据分析 · 跑一轮（乔淼PhD · AI学术训练营 · AI学术工作流）。三种分支：定量（调 analyze-quantitative-data，Neuman Ch12）/ 定性（调 analyze-qualitative-data，Neuman Ch14）/ 自定义 skill（完全按该 skill 自身规则执行，不稀释硬约束）。支持多轮多 skill 分析：每轮产出带前缀不覆盖（-R2/-R3）+ 分析日志.md 逐轮记账。RQ/变量/颗粒度可由用户直接给，不依赖研究设计文件。Trigger on："跑一轮定量/定性分析"、"用 XX skill 分析这份数据"、"数据分析工作流"、"分析这份问卷/访谈"、"run a quantitative/qualitative analysis round"、"analyze my data with skill X"。.
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
# Data Analysis Round · 跑一轮（定量 / 定性 / 自定义 skill） 每次调用 = 跑**一轮**分析（多轮/多 skill 不覆盖、有记账）。三个分支：quant（`analyze-quantitative-data`）/ qual（`analyze-qualitative-data`）/ custom（任意用户指定 skill）。 ## 调用约定（独立运行） **必填**：数据/材料文件路径（用户给；没有就先要，不开工）。custom 分支还需 skill 名。 **分析设定（RQ / DV / IV / 度量层级 / 编码方案 / 颗粒度 / 抽样加权）**按优先级解析： 1. 用户在会话里直接给的（或「额外指令/备注」写明的）→ 最高优先。 2. 研究设计产出：`研究设计初稿.md`（RQ/假设/变量定义）+ `研究设计-设计说明.md`（B3 分析框架：抽样/加权/方法链/度量层级/编码方案/颗粒度）+ 备用 `选题.md`；从中提取设定并与研究设计敲定的方案保持一致。 3. 都没有 → 问用户最小设定：本轮 RQ 一句话 +（定量）DV/IV 与度量层级 或（定性）编码取向；答不上就由所调 skill 的默认流程从头带（如 quant 从 codebook 步开始）。**不要因缺文件拒跑，也不要凭空假设。** **额外指令/备注**（可选，一个通用入口）：本轮针对哪个子问题/假设、RQ 侧重、从哪步起、临时调整、注意点。留空 = 按设定 + skill 默认流程跑，由 skill 自行决定起步。备注优先于默认流程。 **输出落盘**：产出写当前工作目录（建议 `./数据分析产出/`），记账写 `分析日志.md`（多轮不覆盖 · 逐轮记账）。 - **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。 ## 分支 · 定量（quant） 用 `analyze-quantitative-data` skill，按 Neuman 7e Ch 12 步骤：Q1 codebook → Q2 cleaning → Q3 univariate → Q4 bivariate → Q5 elaboration → Q6 regression → Q7 inferential。 硬约束（skill 自动强制）： - 度量层级正确（nominal × interval → ANOVA + eta²，拒绝 Pearson r） - WVS / CGSS / GSS 负值 = missing，默认过滤 …
Read the whole file at its exact version.
How to install
mdr add qiaomiaojoe/ai-academic-workflow/data-analysis-round@sha256:5b837cb195531612The 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_flaws3kqtxptd6si)
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 | 5,893 B | A | view · diff |
| git:20260717.59c14bf | 2026-07-17 | 59c14bf | 5,563 B | A | view · diff |
| git:20260704.8f9ae45 | 2026-07-04 | 8f9ae45 | 5,651 B | A | view · diff |
| git:20260703.eabb41d | 2026-07-03 | eabb41d | 5,674 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 (5893 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_flaws3kqtxptd6si GET https://markdownregistry.com/api/v1/resolve?ref=qiaomiaojoe/ai-academic-workflow/data-analysis-round GET https://markdownregistry.com/api/v1/blob/5b837cb1955316127165a92284aefa2fedfe6ee74c0b5adf9a57e1beae94cabc
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.