thesis-figures SKILL.md skillA
thesis-figures 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-figures@git:20260704.c14667bPins git:20260704.c14667b 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-figures/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260704.c14667b, committed Jul 4, 2026
- First version recorded
- Jul 4, 2026
- Size
- 18,178 bytes
- Repository stars
- 4
- License
- a license file GitHub does not identify
本论文统一画图入口 skill——收编本论文 CLAUDE.md "数据可视化配图规范"全部铁律， 并吸收 scipilot-figure-skill 与既有画图实践的方法论精华。定位是"可视化顾问 + 路由器"：先判断该不该画、画什么图、 走哪条技术路线（R/ggplot2 数据图 | TikZ 流程架构图 | mac-editable 可编辑改造），再执行 并强制走"真实数据核对 → 黑白灰度优先 → 双格式导出 → FIGURES.md 登记 → 目视 PNG 验收" 闭环。触发词：画图、配图、出图、论文图表、可视化、帕累托、鱼骨图、雷达图、甘特图、 流程图、架构图、技术路线图、TikZ、ggplot、图转SVG、可编辑图、重渲图、改图、figure。 只可视化论文已有表格的真实数据，严禁编造任何统计量/坐标。.
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
# thesis-figures — 本论文统一画图入口 > **定位**：本论文统一画图入口，thesis-analyze / thesis-defense 等图表需求均路由到此。 > **适用范围**：本 MEM 论文（浙大 zjuthesis，黑白打印送审）的全部插图工作——新建、修改、重渲、改造为可编辑格式。 > **既有基础设施（必须复用，不另起炉灶）**：`zjuthesis/figures/FIGURES.md`（图↔源↔数据对照清单）、`figures/rebuild_all.sh`（一键重建）、`figures/src/`（全部图源）、`figures/src/crop.py`（TikZ 裁切）。 --- ## 0. 第一问：这张图要论证什么？（吸收自 scipilot 第 0 步） **任何画图请求，先回答两个问题再动手**： 1. **这张图要支撑正文哪个结论？** 同一批数据，论点不同图型就不同（对比改进前后→斜率图/成对柱；占比结构→帕累托/横向柱；趋势→折线；权重结构→雷达/树）。用户没说清就问一句，或从章节上下文推断并明确说出你的假设。 2. **数据在正文哪张表？** 本论文铁律：**只可视化论文已有表格的真实数据**。没有对应表格/正文数字的图一律不画；聚类没有原始点坐标就不画散点。这一条同时替代了 scipilot 的 `profile_data.py` 数据剖析步——本论文的"数据剖析"就是**打开对应正文表格逐个核对数字**，并查 `FIGURES.md` 确认依赖关系。 **一图一论点**（scipilot P12）：一张图塞不下就拆图，不硬塞。 --- ## 1. 适用判断树（三条技术路线） ``` 用户要画/改一张图 │ ├─ ① 数据图表（柱/折线/散点/帕累托/雷达/甘特/回归系数CI/LDA占比…） │ → R/ggplot2 路线（§2）。执行后端 = 全局 nature-figure skill │ (~/ai-skills/nature-skills/skills/nature-figure/，选 backend=r)， │ 本 skill 提供论文级约束与验收闭环。**若未装 nature-figure**，直接用本 skill 附带 │ scripts/templates/*.R 骨架(自带黑白主题+跨平台中文字体+双导出，零外部依赖)。 │ 现有实例：fig_pareto / fig_kano / fig_regression / fig_perf_progress / │ fig_gantt / fig_lda / fig_scheme（源在 figures/src/*.R） │ …
Read the whole file at its exact version.
How to install
mdr add gxgeek-n/wenqu-mem/thesis-figures@sha256:4cea739dd4ec9d16The line at the top of this page pins the label git:20260704.c14667b, 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_36ffk7n4aymrasp7)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, all committed on Jul 4, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260704.c14667b latest | 2026-07-04 | c14667b | 18,178 B | A | view · diff |
| git:20260704.1ab6c99 | 2026-07-04 | 1ab6c99 | 17,263 B | A | view · diff |
| git:20260704.eb9bb8b | 2026-07-04 | eb9bb8b | 17,366 B | A | view · diff |
| git:20260704.d00de62 | 2026-07-04 | d00de62 | 17,006 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 (18178 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_36ffk7n4aymrasp7 GET https://markdownregistry.com/api/v1/resolve?ref=gxgeek-n/wenqu-mem/thesis-figures GET https://markdownregistry.com/api/v1/blob/4cea739dd4ec9d1627856236f9f3eab4095762deedbb3dcebb8f6ce1b1fd314f
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.