thesis-analyze SKILL.md skillA
thesis-analyze from gxgeek-n/wenqu-mem is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add gxgeek-n/wenqu-mem/thesis-analyze@git:20260726.6740b43Pins git:20260726.6740b43 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- gxgeek-n/wenqu-mem
- Path
skills/thesis-analyze/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260726.6740b43, committed Jul 26, 2026
- First version recorded
- Jul 4, 2026
- Size
- 3,756 bytes
- Repository stars
- 4
- License
- a license file GitHub does not identify
ZJU MEM学位论文数据分析入口。涵盖数据生成机制审计、数据处理（采集→清洗→统计→建模）和专业图表生成 （Mermaid/PlantUML/Python matplotlib），输出可直接嵌入论文的代码和图表。 【改道声明】画图/图表/可视化/出成品图/改图/重渲图类请求，一律路由到 thesis-figures （本项目画图统一入口）；本skill只管数据处理、统计分析与探索性草图，不产出论文成品图。 含 t检验、ANOVA、回归、聚类、卡方、相关性、信度效度、描述性统计等具体统计方法（读 CSV→出结果）。 触发词：数据生成机制、数据如何产生、数据分析、数据处理、数据清洗、统计分析、建模、data analysis、 t检验、方差分析、ANOVA、回归分析、相关分析、聚类分析、卡方检验、显著性检验、 描述性统计、信度效度、Cronbach、KMO、Cohen's d、假设检验。.
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
# ZJU MEM 学位论文数据分析 两步工作流。先处理数据，再生成图表。输出均为可执行的代码和可直接嵌入论文的图表。 ## Step 1: 数据处理 - 在选择统计方法前完成数据生成机制审计，先解释业务事件如何变成分析变量、 样本如何进入数据以及干预如何实际发生。涉及前后对比、因果措辞、企业日志 或口径变化时，必须读取 `references/data-generating-process-audit.md`。 - 数据采集：调研问卷、企业日志、AI系统日志、质量指标等真实来源。 - 数据清洗：缺失值处理（均值/中位数/删除）、异常值检测（IQR/Z-score）、归一化（MinMax/StandardScaler）。 - 统计方法：描述统计（均值/标准差/分布）、假设检验（t检验/卡方/ANOVA）、回归分析（线性/逻辑回归）、AI模型评价指标（准确率/召回率/F1）。 - 方法选择：内部对比后推荐最适合的一种（DMAIC/PDCA/六西格玛等）。 - 输出可执行Python代码模板（numpy/pandas/statsmodels）。 - 现成骨架（data-free，读你自己的 CSV，`--demo` 看用法）：`scripts/inferential.py`（Welch t+Cohen's d / ANOVA+Tukey，**仅抽样 Likert**）、`scripts/regression.py`（OLS+VIF+标准化 β，派生值可喂 fig_coef_ci.R）、`scripts/reliability.py`（Cronbach α+KMO）。详见 `scripts/README.md`。 - 详细指南见 `references/analysis-guide.md`。 ## Step 2: 专业图表生成 > **改道声明**：论文成品图（新建/修改/重渲）一律走 `thesis-figures`（本项目画图统一入口，R/ggplot2 + TikZ + 可编辑改造三路线，含 FIGURES.md 登记与验收闭环）。本节仅用于数据探索性草图。 - 支持Mermaid（架构图/流程图/时序图/甘特图）、PlantUML、Python matplotlib/seaborn。 - 严格遵循ZJU图表自明性：图题下置、表题上置、三线表、分章编号。 - 学术配色方案：避免过于鲜艳，优先灰度友好配色。 - 输出图编号+图题+可执行代码+自明性检查清单。 - 详细规范见 `references/visualization.md`。 ## 输出内容 每步输出： 1. 分步操作指南 2. 可直接执行的Python/Mermaid代码 3. 图表自明性检查清单 4. 下一步技能推荐 …
Read the whole file at its exact version.
How to install
mdr add gxgeek-n/wenqu-mem/thesis-analyze@sha256:e0ed995fd9dd5197The line at the top of this page pins the label git:20260726.6740b43, 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_j2v6d4gwufj2l22f)
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 Jul 26, 2026, about one every 8 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260726.6740b43 latest | 2026-07-26 | 6740b43 | 3,756 B | A | view · diff |
| git:20260726.ce7a2e7 | 2026-07-26 | ce7a2e7 | 3,541 B | A | view · diff |
| git:20260704.eb9bb8b | 2026-07-04 | eb9bb8b | 3,267 B | A | view · diff |
| git:20260704.d00de62 | 2026-07-04 | d00de62 | 2,390 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 (3756 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
gxgeek-n/wenqu-mem · 4 stars · license a license file GitHub does not identify · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_j2v6d4gwufj2l22f GET https://markdownregistry.com/api/v1/resolve?ref=gxgeek-n/wenqu-mem/thesis-analyze GET https://markdownregistry.com/api/v1/blob/e0ed995fd9dd51976a37354d008b0736f1593337f33e4edb784abbd6bf906e19
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.