dsh-diagram
Skill79 starsChanged 14 days agoMITView on GitHub
将代码项目、系统架构、业务逻辑画成高颜值、直观可视化的现代架构图。优先在当前聊天窗口内原生渲染(Mermaid / 内联 SVG),极致体验,绝不强迫用户跳出浏览器。
In this repository26 other files it gives its agents.
- doc-tidySkill
- dsh-backupSkill
- dsh-claude-styleSkill
- dsh-code-craftSkill
- dsh-crewSkill
- dsh-data-craftSkill
- dsh-deep-researchSkill
- dsh-doc-publisherSkill
- dsh-doc-searchSkill
- dsh-doc-tidySkill
- dsh-excel-copilotSkill
- dsh-flashgouSkill
- dsh-lifeSkill
- dsh-mail-craftSkill
- dsh-meeting-copilotSkill
- dsh-memory-syncSkill
- dsh-mobileSkill
- dsh-reviewSkill
- dsh-scrum-masterSkill
- dsh-slidesSkill
- dsh-storyboardSkill
- dsh-tierSkill
- dsh-videoSkill
- dsh-voiceSkill
- dsh-web-crawlerSkill
- dsh-write-craftSkill
The file
Files
现代高颜值架构图技能 (archify)
一句话:当前聊天窗口内原生内联呈现是第一公民!绝不让用户多走一步跳到外部浏览器。
🎯 核心体验准则
- 零跳转交付(顶级产品体验):
- 首选方式:直接在回答中使用标准
mermaid代码块 渲染高颜值图表(流光配色、清晰层级、模块分组)。 - 辅助方式:若需要更细腻的毛玻璃视觉,直接内联输出 SVG 矢量卡片。
- 禁止行为:禁止让用户复制本地链接去外部浏览器打开,除非用户主动明确要求导出独立文件。
- 首选方式:直接在回答中使用标准
- 架构图结构化规范:
- 自顶向下 / 业务流向清晰:接入层 (UI/Client) ➔ 核心层 (Engine/Core) ➔ 工具与能力层 (Tools/Bridges) ➔ 基础设施与存储 (Storage/Network)。
- 模块高亮配色:
- 📱 交互/客户端层:天蓝 / 灰蓝 (
#58a6ff) - 🧠 核心引擎/中枢:深蓝 / 核心紫 (
#388bfd/#bc8cff) - ⚙️ 工具与执行层:翠绿 (
#3fb950) - 💾 存储与记忆层:深紫 / 琥珀 (
#d29922)
- 📱 交互/客户端层:天蓝 / 灰蓝 (
🛠️ 标准输出范式(Mermaid 示例)
flowchart TD
classDef client fill:#21262d,stroke:#58a6ff,stroke-width:2px,color:#f0f6fc;
classDef core fill:#161b22,stroke:#bc8cff,stroke-width:2px,color:#f0f6fc;
classDef tool fill:#161b22,stroke:#3fb950,stroke-width:2px,color:#f0f6fc;
classDef data fill:#161b22,stroke:#d29922,stroke-width:2px,color:#f0f6fc;
subgraph 📱 接入层
App["Web GUI / 手机交互"]:::client
end
subgraph 🧠 核心层
Agent["DSH 智能调度中枢"]:::core
end
subgraph ⚙️ 能力与存储
Ops["安卓自动化工具链"]:::tool
DB["mem.db 记忆中枢"]:::data
end
App ==> Agent
Agent --> Ops
Agent <--> DBDoes 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.

