Vivid Architecture Diagram Skill logo

Vivid Architecture Diagram Skill

Community
yjz211
vivid-architecture-diagram-skill

制作与修改模型、系统和方案架构图,以 SVG 资产保留设计风格并适配当前语义;文件型任务支持 A/B 候选、用户选择及原生可编辑 PPTX/SVG/PDF 交付,也按需路由 Draw.io、TikZ、HTML 和 Mermaid 技术图。

Overview

Publisheryjz211
Repositoryvivid-illustration-skill
Skill namevivid-architecture-diagram-skill
Stars
524
Forks
31
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by yjz211 on GitHub. Read the source before you install it.

Installation

Install the Vivid Architecture Diagram Skill AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/yjz211/vivid-illustration-skill/tree/main/channels/vivid-architecture-diagram-skill
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/yjz211/vivid-illustration-skill.git /tmp/vivid-illustration-skill
mkdir -p .claude/skills
cp -r /tmp/vivid-illustration-skill/channels/vivid-architecture-diagram-skill .claude/skills/vivid-architecture-diagram-skill
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Vivid Architecture Diagram Skill in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Vivid Architecture Diagram Skill on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Vivid Architecture Diagram Skill is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Vivid Architecture Diagram Skill · 架构图

这是 Vivid 整包内的架构通道,可直接读取本文件开始任务;共享资产和脚本仍位于包根目录,不单独复制一套。仅加载本次路线所需文档,不加载数据图选型、配色或执行规则。

<SKILL> 始终指本文件所在目录向上两级的 Vivid 包根目录,即 ../../,不是 channels/vivid-architecture-diagram-skill/;<RES> 为 <SKILL>/original/resources。工作流中的资源脚本路径相对于 <RES>,图件与 .vivid/ 则相对于用户任务工作区。

新图图内文字默认中文;用户或当前项目明确要求英文时统一使用英文。保留必要的专业缩写、单位、公式和专有名称,不改动真实对象身份。已有作品未要求改语言时保留当前文字。

选择当前路线

  • 文件型新建 SVG 架构图:读取 A/B 工作流,按下节生成双候选。196 套资源均以 SVG 工作副本适配,历史 Python 生成器仅作旧工程兼容。
  • 已有图件、已选候选、改字换色或单纯导出:读取 共同制作与验收,从用户当前 SVG 与源码继续,仅做所请修改及必要修复;不重新选择模板或启动 A/B。需要 PPTX 时读取 导出说明。
  • 当前网页工作台:读取 网页 Agent 边界 和 共同制作与验收。网页目前一次保存一个候选,按宿主的当前版本与保存流程执行;不启动文件型 A/B 调度,也不声称网页已经支持双候选。手动编辑使用 模块编辑器。
  • 用户指定其他技术图格式或任务需要精确几何:按下方替代路线执行,不强制改用 SVG 资产。

文件型新图:A/B 到交付

此节只适用于可保存独立图件目录的文件型任务,详细操作以 WORKFLOW.md 为准。

  1. 按当前对象、层次、连接与反馈关系检索 资产目录,查看真实预览和所选 TEMPLATE.md。确定一个共同主资产,保存事实、语言和同宽展示要求;资产中的示例标签、曲线和拓扑不是当前任务事实。
  2. 默认独立生成 A:保留构图 与 B:重组构图。有子代理时使用新上下文,只分发各自的路径文件、共同简报及必要输入,模型设置遵从当前用户要求;两路不互看成图或评价。协调者按工作流分发 A 路径 / B 路径,每个生成者只读自己的路径与其引用文档。
  3. 两路按 COMMON.md 实际看图、自主修正,再交回可复现源码、SVG/PDF/PNG 和真实矢量部件;不设置固定自改轮数。检查通过即停止,真实缺失输入或环境限制则说明未完成项。用户明确只要单候选时遵从其要求。
  4. 展示原图与 A/B 的等宽对照,让用户实际选择;不由协调者代选,也不提前为未选候选批量导出 PPTX。
  5. 用户选择即启动最终交付;若有修改,先只改所选版本,再按 PPTX.md 直接交付同版的 原生可编辑 PPTX、SVG、PDF 和字体包,不再询问格式或确认。用户明确另有交付要求时从其要求。PPTX 必须含可编辑文字和矢量对象,不能以整图图片或整图 SVG 置入冒充;实际核验可编辑性和视觉结果,如实说明未完成的 Office 验证。

制作时保住的设计

COMMON.md 是 SVG 制作与验收的共同规则。每次制作或修改都读取它;以下约束同时适用于 A、B、单候选和网页任务:

  • 复用仍适用的真实 SVG 图形和细节。原图有图标、对象轮廓或结构示意时,保留其表达作用;语义改变就自行绘制符合当前对象的可编辑 SVG 图案并编排,不能为省事删成标签或普通文本框。无当前依据的内容不照搬,也不虚构数据或结构。
  • 保留字体角色、真实字重、倾斜与字号层次;在相同展示宽度下检查实际文字大小和模块比例。长标签先精简、换行和调整局部布局,不默认缩字,也不靠扩宽画布把主体整体缩小。缺字时按原字体角色选择覆盖所需文字的字体,不改成英文规避。
  • 颜色跟随对象身份与状态。保持原有语义配色;用户选择顶层色板时才按 语义配色 映射角色,不直接套数据图的默认色序。
  • 结构、连线端点、对象键、部件归属和当前语义同步。自动检查只是证据,仍需实际查看整图及主要部件;留白、文字层次和图案表达也属于验收。续改的保真基线是当前已接受版本,不回退历史模板。

执行与替代路线

SVG 准备、渲染和导出命令见上述工作流。只需安装 架构依赖,首次渲染安装 Chromium:

text
python -m pip install -r "<SKILL>/requirements-architecture.txt"
python -m playwright install chromium

可编辑 PPT 的模块移动不会自动重接箭头,PPT 人工修改也不自动回写 SVG。来源与字体许可随交付保留,见 资产来源。资源齐全不代表所有新场景均已通过视觉验证。

以下路线仅在当前任务需要时加载。其资源和脚本共用 <RES>;先读 绘图入口 的分类、初始化和对账要求,再仅执行所选路线,已有 SVG 资产任务无需另行初始化它们:

已属于完整图集时保留上游 FIGURE_MANIFEST 的类别、事实来源、用途和输出路径。SVG 架构项按 图集架构执行 对账,A/B 合计一个图项,等待用户选择时仍未完成。单张架构图不因此扩展成整套数据图任务。

Frequently asked questions

What does the Vivid Architecture Diagram Skill AI skill do?

制作与修改模型、系统和方案架构图,以 SVG 资产保留设计风格并适配当前语义;文件型任务支持 A/B 候选、用户选择及原生可编辑 PPTX/SVG/PDF 交付,也按需路由 Draw.io、TikZ、HTML 和 Mermaid 技术图。

Why use Vivid Architecture Diagram Skill on TypingMind?

Because you install it once and use it with any model. Vivid Architecture Diagram Skill is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Vivid Architecture Diagram Skill in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/yjz211/vivid-illustration-skill/tree/main/channels/vivid-architecture-diagram-skill. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Vivid Architecture Diagram Skill?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Vivid Architecture Diagram Skill?

As many as you like. As long as a model supports skills, you can use Vivid Architecture Diagram Skill with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Vivid Architecture Diagram Skill AI skill free?

It is published on GitHub by yjz211. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇