drawio-diagram
Skill14 starsChanged 12 days agoApache-2.0View on GitHub
本 Skill 指导 Agent 生成*标准的 Draw.io 格式图表(.drawio 文件),支持两种模式:从零生成(模型架构、算法流程等)与风格迁移*(参考图 + 内容 → 按参考图风格生成新图)。 contest-orchestrator 只在用户明确要求 Draw.io 时调用本技能;默认的流程图和技术路线图走 tech-route-maker,数据图走 modelviz,机制/几何图走 tikz-scientific-figures。输入以项目工作区的任务卡、问题图、模型契约、符号表和来源证据为边界。 从零生成: - 用户需要为深度学习模型(如 Transformer、CNN、RNN 等)生成架构图 - 用户需要绘制算法流程图、数据流图、系统架构图 - 用户需要可视化特定概念(如感受野、注意力机制、特征提取过程等) - 用户提到「画个图」「生成架构图」「可视化模型结构」「绘制流程图」等需求 风格迁移: - 用户提供参考图,希望「按这个风格画」「照着这个排版/配色画」
7 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- hua695/MathModeling-Skills-Arsenalword for word, first seen Oct 25, 2026
- Immortalqx/my_codex_skillstheir own version, first seen Jun 10, 2026
- dev-vpandey/vpandey-skillstheir own version, first seen May 23, 2026
- b1mango/Agent-Skillstheir own version, first seen Apr 26, 2026
- LaoK2017/Agent-Skillstheir own version, first seen Mar 10, 2026
- xstongxue/best-skillsedited, first seen Mar 5, 2026
Used with
Projects with it also use codegen-diagram, codegen-doc and 5 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
xstongxueSkillcodegen-diagram
基于当前项目/代码生成 Draw.io 图表,支持技术栈图、系统架构图、数据结构图、E-R 图四种类型。输出符合 Draw.io 语法的 .drawio 文件(mxGraph XML),可直接导入 Draw.io 编辑。当用户提到技术栈、系统架构、数据结构、E-R 图时使用。
Also in 3 projects that use this
xstongxueSkillcodegen-doc
基于当前项目/代码生成各类文档,支持论文章节、项目梳理、重点问题、简历项目描述四种类型。当用户提到生成论文章节、项目梳理、技术难点、简历项目描述时使用。要给新同事看的上手文档(新人文档、架构文档、代码导读、onboarding)用 project-docs。
Also in 3 projects that use this
garfield-bbSkillwechat-article-writer
公众号文章自动化写作流程。支持资料搜索、文章撰写、爆款标题生成、排版优化。当用户提到写公众号、微信文章、自媒体写作、爆款文章、内容创作时使用此 skill。
Also in 3 projects that use this
BlockSkillfrontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Also in 3 projects that use this
- +3 more from xstongxue
Other versions7 projects use a version of this.
Word for word · 1
- hua695/MathModeling-Skills-Arsenal★ 12100% same
Edited · 1
- xstongxue/best-skills★ 2.9k97% same
Wrote their own version · 5
- Immortalqx/my_codex_skills★ 54same name
- b1mango/Agent-Skills★ 4same name
- dev-vpandey/vpandey-skills★ 4same name
- catsonkeyboard/skills★ 0same name
- LaoK2017/Agent-Skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository39 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/01-core/contest-orchestrator/AGENTS.mdAGENTS.md
- skills/04-figures/tech-route-maker/AGENTS.mdAGENTS.md
- skills/03-writing/bzd-review-paper/CLAUDE.mdCLAUDE.md
- skills/04-figures/tech-route-maker/CLAUDE.mdCLAUDE.md
- contest-orchestratorSkill
- data-science-stackSkill
- heuristic-algorithmsSkill
- math-model-selectorSkill
- pyomoSkill
- academic-writingSkill
- bzd-review-paperSkill
- mathmodel-latex-skillSkill
- 论文辅助Skill
- figure-generationSkill
- fireworks-tech-graphSkill
- modelviz-skillSkill
- scipilot-figure-skillSkill
- tech-route-makerSkill
- tikz-scientific-figuresSkill
- browser-cdpSkill
- humanizer-zhSkill
- markitdown-skillSkill
- web-accessSkill
- darwin-skillSkill
- self-improvementSkill
- skill-audit-cleanupSkill
- story-coverSkill
- story-deslopSkill
- story-importSkill
- story-long-analyzeSkill
- story-long-scanSkill
- story-long-writeSkill
- story-reviewSkill
- story-setupSkill
- story-short-analyzeSkill
- story-short-scanSkill
- story-short-writeSkill
- storySkill
The file
Files
Draw.io 图表
本 Skill 指导 Agent 生成标准的 Draw.io 格式图表(.drawio 文件),支持两种模式:从零生成(模型架构、算法流程等)与风格迁移(参考图 + 内容 → 按参考图风格生成新图)。
Contest-Orchestrator Adapter
contest-orchestrator 只在用户明确要求 Draw.io 时调用本技能;默认的流程图和技术路线图走 tech-route-maker,数据图走 modelviz,机制/几何图走 tikz-scientific-figures。输入以项目工作区的任务卡、问题图、模型契约、符号表和来源证据为边界。
- 每个可见节点、连线、变量、标签和结论绑定来源定位;不得从参考图或对话中补造模型、结果、单位或引用。
- 返回
status、active_mode、task_card、artifacts、evidence、checks、blockers、next_node节点包,.drawio、说明和检查报告只写项目工作区。 - XML 结构、来源、文字和编号检查必须执行;截图、渲染复核和 AI 视觉检查默认开启,检查间距、对齐、裁切、遮挡、层级、文字可读性和整体整洁度,用户肉眼检查作为最终补充。
- 图表、说明和节点包不得包含元话语、内部交流、调试、失败过程、旧版本或其他负回响。
Step 0:任务识别
| 条件 | 执行 |
| 用户提供参考图,且希望「按这张图的风格」画新图 | 执行 reference/style-migration.md |
| 其他情况(从零生成) | 执行 reference/generation.md |
使用时机
从零生成:
- 用户需要为深度学习模型(如 Transformer、CNN、RNN 等)生成架构图
- 用户需要绘制算法流程图、数据流图、系统架构图
- 用户需要可视化特定概念(如感受野、注意力机制、特征提取过程等)
- 用户提到「画个图」「生成架构图」「可视化模型结构」「绘制流程图」等需求
风格迁移:
- 用户提供参考图,希望「按这个风格画」「照着这个排版/配色画」
通用规范(两种模式共用)
1. XML 格式严格性
- ✅ 所有标签必须正确闭合:
<mxCell>对应</mxCell>,绝不能写成</mCell> - ✅ 使用
vertex="1"标记节点,edge="1"标记连线 - ✅ 每个元素必须有唯一
id,从 0 开始递增 - ✅ 特殊字符必须转义:
&→&,<→<,>→>
2. 标准文件结构
<mxfile host="app.diagrams.net">
<diagram name="图表名称" id="图表id">
<mxGraphModel dx="1200" dy="800" grid="1" gridSize="10" guides="1" tooltips="1" connect="1" arrows="1" fold="1" page="1" pageScale="1" pageWidth="宽度" pageHeight="高度" background="#F5F5DC">
<root>
<mxCell id="0"/>
<mxCell id="1" parent="0"/>
<!-- 所有图形元素从 id="2" 开始 -->
</root>
</mxGraphModel>
</diagram>
</mxfile>3. 常用样式
- 2D 节点:
rounded=1;whiteSpace=wrap;html=1;fillColor=#颜色;strokeColor=#333333;strokeWidth=1;fontSize=11 - 3D 节点(推荐用于神经网络层):
shape=cube;whiteSpace=wrap;html=1;boundedLbl=1;backgroundOutline=1;darkOpacity=0.05;darkOpacity2=0.1;size=20;fillColor=#颜色;strokeColor=#333333;strokeWidth=1.5 - 连线:
edgeStyle=orthogonalEdgeStyle;rounded=0;html=1;strokeColor=#000000;strokeWidth=2;endArrow=classic - 虚线(残差):
dashed=1
4. 输出要求
- 图表说明(2-3 行)
- 使用指南:Draw.io 打开、导出 PNG/SVG(PDF 不进入论文图表交付流程)、图题与论文引用示例
参考资源
- Draw.io:https://app.diagrams.net/
- 官方文档:https://www.drawio.com/doc/
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

