architecture — community architecture, community, ide skills, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Ideal for AI Agents like Claude Code, AutoGPT, and LangChain requiring comprehensive architecture design and development methodologies. 🎭 cc-best: Turn Claude Code into a full dev team — PM→Lead→Dev→QA autonomous workflow. 40 commands · 17 skills · 8 agents · 33 rules · 21 hooks · auto-learning pipeline. | 一个插件,完整开发团队。

xiaobei930 xiaobei930
[0]
[0]
Updated: 3/5/2026

Agent Capability Analysis

The architecture skill by xiaobei930 is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance.

Ideal Agent Persona

Ideal for AI Agents like Claude Code, AutoGPT, and LangChain requiring comprehensive architecture design and development methodologies.

Core Value

Empowers agents to create autonomous workflows by providing a full dev team setup, including ADR records, design checklists, scalability assessments, and architecture pattern references, utilizing skills like lead methodology, PM methodology, and auto-learning pipelines.

Capabilities Granted for architecture

Automating architecture decision-making with ADR templates
Generating scalable system designs using best practices
Creating autonomous dev teams with PM and Lead methodologies

! Prerequisites & Limits

  • Requires integration with existing development pipelines
  • Limited to software architecture design
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

architecture

Install architecture, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

架构设计技能

本技能提供架构设计的完整指南,包括 ADR 记录、设计检查清单、可扩展性评估、架构模式速查等最佳实践。

子文件

架构决策记录 (ADR)

对于重要的架构决策,创建 ADR 记录:

ADR 模板 (docs/decisions/ADR-XXX.md)

markdown
1# ADR-XXX: [决策标题] 2 3## 状态 4 5Proposed | Accepted | Deprecated | Superseded by ADR-YYY 6 7## 上下文 8 9[描述导致这个决策的背景、问题或需求] 10 11## 决策 12 13[明确说明做出的决策] 14 15## 理由 16 17[解释为什么选择这个方案] 18 19## 备选方案 20 21### 方案 A: [名称] 22 23- 优点: ... 24- 缺点: ... 25 26### 方案 B: [名称] 27 28- 优点: ... 29- 缺点: ... 30 31## 后果 32 33### 正面 34 35- [好处1] 36- [好处2] 37 38### 负面 39 40- [代价1] 41- [代价2] 42 43### 风险 44 45- [风险1] → 缓解: [措施] 46 47## 相关决策 48 49- ADR-XXX: [相关决策] 50 51## 日期 52 53YYYY-MM-DD

何时创建 ADR

场景是否需要 ADR
选择主要技术栈(框架、数据库)✅ 必须
定义核心架构模式✅ 必须
引入新的外部依赖⚠️ 视影响范围
API 设计重大变更✅ 必须
简单的实现细节❌ 不需要

系统设计检查清单

设计方案前,检查以下维度:

功能性需求

  • 用户故事是否清晰完整
  • API 契约是否定义明确
  • 数据模型是否满足需求
  • 边界条件是否考虑

非功能性需求

  • 性能: 响应时间目标?吞吐量要求?
  • 可扩展性: 预期用户量?数据增长?
  • 可用性: 可接受的停机时间?
  • 安全性: 认证授权?数据保护?

技术设计

  • 架构图是否清晰
  • 组件职责是否明确
  • 数据流是否完整
  • 错误处理策略是否定义
  • 测试策略是否规划

运维考虑

  • 部署策略是否明确
  • 监控告警是否规划
  • 日志策略是否定义
  • 回滚方案是否准备

可扩展性评估

扩展阶段规划

阶段用户量架构要求
MVP<1K单体应用足够
成长期1K-10K优化数据库查询,添加缓存
扩展期10K-100K服务拆分,读写分离
规模化>100K微服务,分布式缓存,多区域

常见瓶颈与解决方案

瓶颈解决方案
数据库读取慢索引优化 → 读写分离 → 缓存层
API 响应慢异步处理 → 消息队列 → CDN
内存不足分页加载 → 流式处理 → 扩容
并发冲突乐观锁 → 分布式锁 → 事件溯源

架构模式速查

后端模式

模式适用场景复杂度
分层架构大多数 CRUD 应用
六边形架构需要高可测试性
CQRS读写负载差异大
事件溯源需要完整审计轨迹
微服务团队多、规模大

前端模式

模式适用场景
组件组合构建复杂 UI
状态提升组件间共享状态
Context + Reducer全局状态管理
自定义 Hooks复用有状态逻辑
渲染属性灵活的组件复用

数据访问模式

模式说明
Repository抽象数据访问层
Unit of Work事务管理
DAO数据访问对象
Active Record模型直接操作数据库

架构评审清单

在提交设计方案前:

  • 是否遵循现有架构模式
  • 是否考虑了向后兼容性
  • 是否有明确的错误处理策略
  • 是否考虑了监控和可观测性
  • 是否有性能基准和目标
  • 是否考虑了安全性
  • 是否有回滚方案

与 /cc-best:lead 角色的配合

/cc-best:lead 技术设计
    ↓
  需要架构决策?
    ├─ 是 → 创建 ADR 记录
    └─ 否 → 继续设计
    ↓
  设计检查清单
    ↓
  任务分解
    ↓
  /cc-best:dev 开始实现

记住: 架构决策要记录理由——ADR 不是文档负担,而是未来自己和团队的决策参考。

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is architecture?

Ideal for AI Agents like Claude Code, AutoGPT, and LangChain requiring comprehensive architecture design and development methodologies. 🎭 cc-best: Turn Claude Code into a full dev team — PM→Lead→Dev→QA autonomous workflow. 40 commands · 17 skills · 8 agents · 33 rules · 21 hooks · auto-learning pipeline. | 一个插件,完整开发团队。

How do I install architecture?

Run the command: npx killer-skills add xiaobei930/cc-best/architecture. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for architecture?

Key use cases include: Automating architecture decision-making with ADR templates, Generating scalable system designs using best practices, Creating autonomous dev teams with PM and Lead methodologies.

Which IDEs are compatible with architecture?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for architecture?

Requires integration with existing development pipelines. Limited to software architecture design.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add xiaobei930/cc-best/architecture. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use architecture immediately in the current project.

Related Skills

Looking for an alternative to architecture or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI