Architecture Design

Organization

devcodex-labs

architecture-design

架构设计文档编排 Owner — 当用户要求架构设计、系统设计、技术架构或可指导开发、Review 与任务拆分的完整方案时使用；要求从业务流程反推节点、状态、数据、一致性、异常补偿、ADR 与实施任务。

Overview

Publisher	devcodex-labs
Repository	`devcodex`
Skill name	`architecture-design`
Stars	433
Forks	44
Bundled files	1
License	AGPL-3.0
Links	Skill source Repository Homepage

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.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by devcodex-labs on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/devcodex-labs/devcodex/tree/main/content/skills/architecture-design
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.

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/devcodex-labs/devcodex.git /tmp/devcodex
mkdir -p .claude/skills
cp -r /tmp/devcodex/content/skills/architecture-design .claude/skills/architecture-design

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Architecture Design 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 Architecture Design 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 Architecture Design 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.

Architecture Design Skill

定位

本 Skill 负责完整架构设计文档的编排 Owner 视角。它把需求、业务流程、模块边界、数据模型、API 契约、一致性、异常补偿、ADR、验证与任务拆分组织成可直接指导开发、Review 和排期的设计产物。

本 Skill 不替代领域架构 Skill 的专业判断。它负责结构、顺序、追踪关系和交付物完整性；领域细节由后端、前端、数据、API、分布式、集成、平台、AI Agent、隐私合规、设计系统、DX 等 Skill 提供判断。

触发条件

场景	是否触发
用户要求架构设计、系统设计、技术架构、概要设计、详细设计或可指导开发/Review/任务拆分的方案	必须
需求从 0 到 1、跨模块、跨角色、跨状态、跨数据流或跨外部系统	必须
方案需要主流程、子流程、节点设计、状态机、数据流、时序、ADR、风险和实施拆分	必须
已有代码小修、单点 bug 修复、纯审计结论或只要求某一领域专家判断	N/A + skipReason

与领域架构 Skill 的关系

领域	主要协作 Skill	本 Skill 的编排责任
业务与产品取舍	`product-strategy`	把业务目标、角色、对象和成功标准转成架构输入
后端领域与流程	`backend-domain-architecture`	确保业务不变量、权限、事务和幂等映射到节点设计
API 与公开契约	`api-contract-architecture`	确保 API 由流程和消费者反推，避免先写接口后补业务
数据模型与迁移	`data-architecture`	确保模型、查询、索引、生命周期和消费者闭环
前端体验	`frontend-architecture`、`ux-interaction-architecture`	确保状态、错误、加载、权限和交互与主流程一致
分布式与外部系统	`distributed-systems-architecture`、`external-integration-architecture`	确保失败、重试、补偿、超时和一致性边界可验证
平台、AI、合规与 DX	`platform-ecosystem-architecture`、`ai-agent-system-architecture`、`privacy-compliance-architecture`、`developer-experience-architecture`	确保平台扩展、Agent 合同、合规边界和开发体验进入设计

核心门禁

Gate	要求	证据
`ArchitectureDesignIntentGate`	先结构化需求目标、业务场景、角色、业务对象、边界和非目标	requirementMatrix、boundary
`BusinessFlowFirstGate`	先写主业务流程，再进入模块、类、表、API 或缓存	mainFlow
`FlowDecompositionGate`	复杂主流程节点必须拆成子流程，并说明触发、输入、输出和终止条件	subFlows
`NodeImplementationGate`	关键节点必须写职责、前置条件、读写数据、状态变化、依赖、成功/失败和幂等	nodeDesign
`StateMachineGate`	有状态对象必须写状态、事件、转移条件、终态和非法转移	stateMachine
`DataFlowSequenceGate`	数据流和时序必须说明谁产生、谁消费、何时持久化、何时可见	dataFlow、sequence
`ModuleBoundaryGate`	模块职责、依赖方向、共享契约和禁止跨层访问必须清楚	moduleMap
`DataModelConsistencyGate`	数据模型、唯一键、索引、事务、一致性、缓存和生命周期必须闭环	dataModel、consistency
`ApiContractMappingGate`	API/CLI/事件/Hook/MCP 契约必须由流程节点和消费者反推	contractMatrix
`FailureCompensationGate`	重试、超时、重复提交、部分成功、外部失败和人工修复路径必须定义	failureMatrix
`ArchitectureDecisionGate`	关键决策必须写问题、方案、理由、备选项、拒绝原因和代价	ADR
`DevelopmentTaskSplitGate`	最终任务拆分必须能映射回流程节点、模块、契约和验证项	taskBreakdown
`ArchitectureReviewChecklistGate`	Review 清单必须覆盖流程、状态、数据、契约、一致性、异常、可运维性和风险	checklist

执行流程

结构化意图：提取目标、用户价值、业务角色、核心对象、范围、非目标、约束和待确认项。
建立主流程：用业务语言描述从触发到终态的主路径，先不落实现类名和数据库表。
拆分子流程：对复杂节点补子流程，明确入口、出口、失败分支和可恢复路径。
设计节点：逐个关键节点写职责、输入、输出、前置条件、状态变化、数据读写、外部依赖、成功/失败和幂等策略。
路由领域 Skill：按实际问题调用相关领域架构 Skill，引用其判断而不是重复发明领域规则。
建模与契约：在流程和节点稳定后，定义模块、数据模型、API/事件/CLI/Hook/MCP 契约和兼容策略。
写 ADR：记录会影响扩展性、复杂度、成本、风险或长期维护的关键决策。
完成落地：输出验证策略、风险、待确认项、任务拆分和 Architecture Review Checklist。

输出结构

架构设计文档必须包含 ## 目录导航。若某节不适用，保留标题并写明 N/A + skipReason；不要删除结构导致 Review 无法定位缺口。

markdown
## 目录导航
## 1. 架构目标与成功标准
## 2. 需求理解与业务场景
## 3. 角色、权限与核心业务对象
## 4. 系统边界与非目标
## 5. 当前上下文与约束
## 6. 整体架构图
## 7. 系统主流程
## 8. 子流程设计
## 9. 核心节点详细设计
## 10. 状态机设计
## 11. 数据流设计
## 12. 时序设计
## 13. 模块架构与依赖方向
## 14. 数据模型、索引与生命周期
## 15. API、事件、CLI、Hook 或 MCP 契约
## 16. 一致性、事务、缓存与幂等
## 17. 异常、重试、补偿与人工修复
## 18. 权限、安全、隐私与审计
## 19. 性能、容量与可扩展性
## 20. 可观测性与运维策略
## 21. ADR 决策记录
## 22. 风险、取舍与待确认项
## 23. 开发任务拆分与里程碑
## 24. Architecture Review Checklist

图表要求

主流程优先使用 Mermaid flowchart TD，节点名称使用业务动作。
有状态对象时使用 stateDiagram-v2 或状态转移表，必须包含非法转移处理。
跨系统调用、异步事件、补偿和回调使用 sequenceDiagram 或时序表。
图表必须和正文节点编号互相引用；不要为了形式完整添加无信息量图表。

反模式

反模式	修正
从需求直接跳到 controller/service/repository/table/API	先补主流程、子流程和节点设计
只说“使用 Redis/MQ/定时任务/缓存”但不说明业务触发与失败恢复	补 ADR、数据可见性、一致性和补偿策略
流程图只有大框，没有关键节点的输入、输出、状态和数据读写	补 `NodeImplementationGate`
API 先行，业务流程和消费者后补	用 `ApiContractMappingGate` 反推契约
写“根据实际情况处理异常”	明确失败矩阵、重试边界、人工修复和告警
为了显得完整引入不必要的分布式组件	写取舍，证明必要性或删除该复杂度

完成判定

完成的架构设计必须回答：做什么、为什么做、谁参与、主流程怎么走、关键节点怎么实现、状态如何变化、数据如何流动、契约如何消费、失败如何恢复、一致性如何保证、替代方案为何不选、开发任务如何拆分、Review 如何验收。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

intent.json1 KB

Frequently asked questions

What does the Architecture Design AI skill do?

Why use Architecture Design on TypingMind?

Because you install it once and use it with any model. Architecture Design 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 Architecture Design in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/devcodex-labs/devcodex/tree/main/content/skills/architecture-design. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Architecture Design?

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 Architecture Design?

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

Is the Architecture Design AI skill free?

Yes. It is published on GitHub by devcodex-labs under the AGPL-3.0 license. 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

Improve Codebase Architecture

mattpocock

CommunityPopular

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Grilling

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

Teach

Teach the user a new skill or concept, within this workspace.

Api Design

Patrones de diseño REST API incluyendo nomenclatura de recursos, códigos de estado, paginación, filtrado, respuestas de error, versionado y rate limiting para APIs de producción.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Architecture Design Skill

目录导航

定位

触发条件

与领域架构 Skill 的关系

核心门禁

执行流程

输出结构

图表要求

反模式

完成判定

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now