Back to Details

anthropic-architect

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Anthropic Architect

Anthropic架构师

Expert architectural guidance for Anthropic-based projects. Analyze your requirements and receive tailored recommendations on the optimal architecture using Skills, Agents, Subagents, Prompts, and SDK primitives.
为基于Anthropic的项目提供专业的架构指导。分析你的需求，并获取关于使用Skills、Agents、Subagents、Prompts和SDK原语的最佳架构的定制化建议。

What This Skill Does

该Skill的功能

Helps you design the right Anthropic architecture for your project by:
  • Analyzing project requirements - Understanding complexity, scope, and constraints
  • Recommending architectures - Skills vs Agents vs Prompts vs SDK primitives
  • Applying decision rubrics - Data-driven architectural choices
  • Following best practices - 2025 Anthropic patterns and principles
  • Progressive disclosure design - Efficient context management
  • Security considerations - Safe, controllable AI systems
帮助你为项目设计合适的Anthropic架构，具体包括：
  • 分析项目需求 - 理解复杂度、范围和约束条件
  • 推荐架构方案 - 对比Skills、Agents、Prompts和SDK原语的适用场景
  • 应用决策准则 - 基于数据驱动的架构选择
  • 遵循最佳实践 - 2025年Anthropic架构模式与原则
  • 渐进式披露设计 - 高效的上下文管理
  • 安全考量 - 构建安全、可控的AI系统

Why Architecture Matters

架构设计的重要性

Without proper architecture:
  • Inefficient context usage and high costs
  • Poor performance and slow responses
  • Security vulnerabilities and risks
  • Difficult to maintain and scale
  • Agents reading entire skill contexts unnecessarily
  • Mixed concerns and unclear boundaries
With engineered architecture:
  • Optimal context utilization
  • Fast, focused responses
  • Secure, controlled operations
  • Easy to maintain and extend
  • Progressive disclosure of information
  • Clear separation of concerns
  • Scalable and reusable components
缺乏合适架构的问题：
  • 上下文使用效率低，成本高昂
  • 性能不佳，响应缓慢
  • 存在安全漏洞与风险
  • 难以维护和扩展
  • Agents不必要地读取整个Skill上下文
  • 关注点混杂，边界不清晰
采用精心设计的架构的优势：
  • 优化上下文利用率
  • 快速、聚焦的响应
  • 安全、可控的操作
  • 易于维护和扩展
  • 信息的渐进式披露
  • 清晰的关注点分离
  • 可扩展、可复用的组件

Quick Start

快速开始

Analyze Your Project

分析你的项目

Using the anthropic-architect skill, help me determine the best
architecture for: [describe your project]

Requirements:
- [List your key requirements]
- [Complexity level]
- [Reusability needs]
- [Security constraints]
Using the anthropic-architect skill, help me determine the best
architecture for: [describe your project]

Requirements:
- [List your key requirements]
- [Complexity level]
- [Reusability needs]
- [Security constraints]

Get Architecture Recommendation

获取架构建议

The skill will provide:
  1. Recommended architecture - Specific primitives to use
  2. Decision reasoning - Why this architecture fits
  3. Implementation guidance - How to build it
  4. Best practices - What to follow
  5. Example patterns - Similar successful architectures
该Skill将提供：
  1. 推荐架构 - 具体的原语使用方案
  2. 决策依据 - 该架构适配的原因
  3. 实施指导 - 如何构建该架构
  4. 最佳实践 - 需要遵循的准则
  5. 示例模式 - 类似的成功架构案例

The Four Anthropic Primitives

四种Anthropic原语

1. Skills (Prompt-Based Meta-Tools)

1. Skills（基于Prompt的元工具）

What: Organized folders of instructions, scripts, and resources that agents can discover and load dynamically.
When to use:
  • ✅ Specialized domain knowledge needed
  • ✅ Reusable across multiple projects
  • ✅ Complex, multi-step workflows
  • ✅ Reference materials required
  • ✅ Progressive disclosure beneficial
When NOT to use:
  • ❌ Simple, one-off tasks
  • ❌ Project-specific logic only
  • ❌ No need for reusability
Example use cases:
  • Prompt engineering expertise
  • Design system generation
  • Code review guidelines
  • Domain-specific knowledge (finance, medical, legal)
定义： 由指令、脚本和资源组成的有组织的文件夹，Agents可以动态发现和加载。
适用场景：
  • ✅ 需要专业领域知识
  • ✅ 可在多个项目中复用
  • ✅ 复杂的多步骤工作流
  • ✅ 需要参考资料
  • ✅ 渐进式披露能带来价值
不适用场景：
  • ❌ 简单的一次性任务
  • ❌ 仅针对特定项目的逻辑
  • ❌ 无需复用
示例用例：
  • Prompt工程专业知识
  • 设计系统生成
  • 代码评审指南
  • 特定领域知识（金融、医疗、法律）

2. Agents/Subagents (Autonomous Task Handlers)

2. Agents/Subagents（自主任务处理程序）

What: Specialized agents with independent system prompts, dedicated context windows, and specific tool permissions.
When to use:
  • ✅ Complex, multi-step autonomous tasks
  • ✅ Need for isolated context
  • ✅ Different tool permissions required
  • ✅ Parallel task execution
  • ✅ Specialized expertise per task type
When NOT to use:
  • ❌ Simple queries or lookups
  • ❌ Shared context required
  • ❌ Sequential dependencies
  • ❌ Resource-constrained environments
Example use cases:
  • Code exploration and analysis
  • Test generation and execution
  • Documentation generation
  • Security audits
  • Performance optimization
定义： 具有独立系统Prompt、专用上下文窗口和特定工具权限的专业化Agents。
适用场景：
  • ✅ 复杂的多步骤自主工作流
  • ✅ 需要隔离的上下文
  • ✅ 需要不同的工具权限
  • ✅ 并行任务执行
  • ✅ 针对不同任务类型的专业知识
不适用场景：
  • ❌ 简单查询或查找
  • ❌ 需要共享上下文
  • ❌ 存在顺序依赖
  • ❌ 资源受限的环境
示例用例：
  • 代码探索与分析
  • 测试生成与执行
  • 文档生成
  • 安全审计
  • 性能优化

3. Direct Prompts (Simple Instructions)

3. Direct Prompts（简单指令）

What: Clear, explicit instructions passed directly to Claude without additional structure.
When to use:
  • ✅ Simple, straightforward tasks
  • ✅ One-time operations
  • ✅ Quick questions or clarifications
  • ✅ No need for specialization
  • ✅ Minimal context required
When NOT to use:
  • ❌ Complex, multi-step processes
  • ❌ Need for reusability
  • ❌ Requires domain expertise
  • ❌ Multiple related operations
Example use cases:
  • Code explanations
  • Quick refactoring
  • Simple bug fixes
  • Documentation updates
  • Direct questions
定义： 直接传递给Claude的清晰、明确的指令，无额外结构。
适用场景：
  • ✅ 简单、直接的任务
  • ✅ 一次性操作
  • ✅ 快速提问或澄清
  • ✅ 无需专业化
  • ✅ 仅需极少上下文
不适用场景：
  • ❌ 复杂的多步骤流程
  • ❌ 需要复用
  • ❌ 需要领域专业知识
  • ❌ 多个相关操作
示例用例：
  • 代码解释
  • 快速重构
  • 简单bug修复
  • 文档更新
  • 直接提问

4. SDK Primitives (Custom Workflows)

4. SDK Primitives（自定义工作流）

What: Low-level building blocks from the Claude Agent SDK to create custom agent workflows.
When to use:
  • ✅ Unique workflow requirements
  • ✅ Custom tool integration needed
  • ✅ Specific feedback loops required
  • ✅ Integration with existing systems
  • ✅ Fine-grained control needed
When NOT to use:
  • ❌ Standard use cases covered by Skills/Agents
  • ❌ Limited development resources
  • ❌ Maintenance burden concern
  • ❌ Faster time-to-market priority
Example use cases:
  • Custom CI/CD integration
  • Specialized code analysis pipelines
  • Domain-specific automation
  • Integration with proprietary systems
定义： 来自Claude Agent SDK的底层构建块，用于创建自定义Agent工作流。
适用场景：
  • ✅ 独特的工作流需求
  • ✅ 需要自定义工具集成
  • ✅ 需要特定的反馈循环
  • ✅ 与现有系统集成
  • ✅ 需要细粒度控制
不适用场景：
  • ❌ 标准用例可由Skills/Agents覆盖
  • ❌ 开发资源有限
  • ❌ 担心维护负担
  • ❌ 优先考虑更快的上市时间
示例用例：
  • 自定义CI/CD集成
  • 专业化代码分析流水线
  • 特定领域自动化
  • 与专有系统集成

Decision Rubric

决策准则

Use this rubric to determine the right architecture:
使用以下准则确定合适的架构：

Task Complexity Analysis

任务复杂度分析

Low Complexity → Direct Prompts
  • Single operation
  • Clear input/output
  • No dependencies
  • < 5 steps
Medium Complexity → Skills
  • Multiple related operations
  • Reusable patterns
  • Reference materials helpful
  • 5-20 steps
High Complexity → Agents/Subagents
  • Multi-step autonomous workflow
  • Needs isolated context
  • Different tool permissions
  • 20 steps or parallel tasks
Custom Complexity → SDK Primitives
  • Unique workflows
  • System integration required
  • Custom tools needed
  • Specific feedback loops
低复杂度 → Direct Prompts
  • 单一操作
  • 清晰的输入/输出
  • 无依赖
  • 少于5个步骤
中复杂度 → Skills
  • 多个相关操作
  • 可复用模式
  • 参考资料有帮助
  • 5-20个步骤
高复杂度 → Agents/Subagents
  • 多步骤自主工作流
  • 需要隔离的上下文
  • 不同的工具权限
  • 超过20个步骤或并行任务
自定义复杂度 → SDK Primitives
  • 独特的工作流
  • 需要系统集成
  • 需要自定义工具
  • 特定的反馈循环

Reusability Assessment

可复用性评估

Single Use → Direct Prompts
  • One-time task
  • Project-specific
  • No future reuse
Team Reuse → Skills
  • Multiple team members benefit
  • Common workflows
  • Shareable knowledge
Organization Reuse → Skills + Marketplace
  • Cross-team benefit
  • Standard patterns
  • Company-wide knowledge
Product Feature → SDK Primitives
  • End-user facing
  • Production deployment
  • Custom integration
单次使用 → Direct Prompts
  • 一次性任务
  • 特定项目专用
  • 未来无需复用
团队复用 → Skills
  • 多个团队成员受益
  • 通用工作流
  • 可共享的知识
组织级复用 → Skills + 市场
  • 跨团队受益
  • 标准模式
  • 全公司范围的知识
产品功能 → SDK Primitives
  • 面向终端用户
  • 生产环境部署
  • 自定义集成

Context Management Needs

上下文管理需求

Minimal Context → Direct Prompts
  • Self-contained task
  • No external references
  • Simple instructions
Structured Context → Skills
  • Progressive disclosure needed
  • Reference materials required
  • Organized information
Isolated Context → Agents/Subagents
  • Separate concerns
  • Avoid context pollution
  • Parallel execution
Custom Context → SDK Primitives
  • Specific context handling
  • Integration requirements
  • Fine-grained control
极少上下文 → Direct Prompts
  • 自包含任务
  • 无外部引用
  • 简单指令
结构化上下文 → Skills
  • 需要渐进式披露
  • 需要参考资料
  • 有组织的信息
隔离上下文 → Agents/Subagents
  • 关注点分离
  • 避免上下文污染
  • 并行执行
自定义上下文 → SDK Primitives
  • 特定的上下文处理
  • 集成需求
  • 细粒度控制

Security & Control Requirements

安全与控制要求

Basic Safety → Direct Prompts + Skills
  • Standard guardrails
  • No sensitive operations
  • Read-only or low-risk
Controlled Access → Agents with Tool Restrictions
  • Specific tool permissions
  • Allowlist approach
  • Confirmation required
High Security → SDK Primitives + Custom Controls
  • Deny-all default
  • Explicit confirmations
  • Audit logging
  • Custom security layers
基础安全 → Direct Prompts + Skills
  • 标准防护措施
  • 无敏感操作
  • 只读或低风险
受控访问 → 带工具限制的Agents
  • 特定的工具权限
  • 白名单方式
  • 需要确认
高安全级别 → SDK Primitives + 自定义控制
  • 默认拒绝所有
  • 明确的确认
  • 审计日志
  • 自定义安全层

Architecture Patterns

架构模式

Pattern 1: Skills-First Architecture

模式1：Skills优先架构

Use when: Building reusable expertise and workflows
Structure:
Project
├── skills/
│   ├── domain-expert/
│   │   ├── SKILL.md
│   │   └── references/
│   │       ├── patterns.md
│   │       ├── best_practices.md
│   │       └── examples.md
│   └── workflow-automation/
│       ├── SKILL.md
│       └── scripts/
│           └── automate.sh
└── .claude/
    └── config
Benefits:
  • Reusable across projects
  • Progressive disclosure
  • Easy to share and maintain
  • Clear documentation
适用场景： 构建可复用的专业知识和工作流
结构：
Project
├── skills/
│   ├── domain-expert/
│   │   ├── SKILL.md
│   │   └── references/
│   │       ├── patterns.md
│   │       ├── best_practices.md
│   │       └── examples.md
│   └── workflow-automation/
│       ├── SKILL.md
│       └── scripts/
│           └── automate.sh
└── .claude/
    └── config
优势：
  • 可跨项目复用
  • 渐进式披露
  • 易于共享和维护
  • 清晰的文档

Pattern 2: Agent-Based Architecture

模式2：基于Agent的架构

Use when: Complex autonomous tasks with isolated concerns
Structure:
Main Agent (orchestrator)
├── Explore Agent (codebase analysis)
├── Plan Agent (task planning)
├── Code Agent (implementation)
└── Review Agent (validation)
Benefits:
  • Parallel execution
  • Isolated contexts
  • Specialized expertise
  • Clear responsibilities
适用场景： 具有隔离关注点的复杂自主任务
结构：
Main Agent (orchestrator)
├── Explore Agent (codebase analysis)
├── Plan Agent (task planning)
├── Code Agent (implementation)
└── Review Agent (validation)
优势：
  • 并行执行
  • 隔离的上下文
  • 专业化的专业知识
  • 清晰的职责划分

Pattern 3: Hybrid Architecture

模式3：混合架构

Use when: Complex projects with varied requirements
Structure:
Main Conversation
├── Direct Prompts (simple tasks)
├── Skills (reusable expertise)
│   ├── code-review-skill
│   └── testing-skill
└── Subagents (complex workflows)
    ├── Explore Agent
    └── Plan Agent
Benefits:
  • Right tool for each task
  • Optimal resource usage
  • Flexible and scalable
  • Best of all approaches
适用场景： 需求多样的复杂项目
结构：
Main Conversation
├── Direct Prompts (simple tasks)
├── Skills (reusable expertise)
│   ├── code-review-skill
│   └── testing-skill
└── Subagents (complex workflows)
    ├── Explore Agent
    └── Plan Agent
优势：
  • 为每个任务选择合适的工具
  • 优化资源使用
  • 灵活且可扩展
  • 融合所有方法的优势

Pattern 4: SDK Custom Architecture

模式4：SDK自定义架构

Use when: Unique requirements or product features
Structure:
Custom Agent SDK Implementation
├── Custom Tools
├── Specialized Feedback Loops
├── System Integrations
└── Domain-Specific Workflows
Benefits:
  • Full control
  • Custom integration
  • Unique workflows
  • Production-ready
适用场景： 独特需求或产品功能
结构：
Custom Agent SDK Implementation
├── Custom Tools
├── Specialized Feedback Loops
├── System Integrations
└── Domain-Specific Workflows
优势：
  • 完全控制
  • 自定义集成
  • 独特的工作流
  • 可用于生产环境

Key Principles (2025)

核心原则（2025年）

1. Progressive Disclosure

1. 渐进式披露

What: Show only what's needed, when it's needed.
Why: Avoids context limits, reduces costs, improves performance.
How: Organize skills with task-based navigation, provide query tools, structure information hierarchically.
定义： 仅在需要时展示必要的信息。
原因： 避免上下文限制，降低成本，提升性能。
实现方式： 按任务导航组织Skills，提供查询工具，按层次结构组织信息。

2. Context as Resource

2. 上下文作为资源

What: Treat context window as precious, limited resource.
Why: Every token counts toward limits and costs.
How: Use progressive disclosure, prefer retrieval over dumping, compress aggressively, reset periodically.
定义： 将上下文窗口视为宝贵的有限资源。
原因： 每个token都影响限制和成本。
实现方式： 使用渐进式披露，优先检索而非直接导入，积极压缩，定期重置。

3. Clear Instructions

3. 清晰的指令

What: Explicit, unambiguous directions.
Why: Claude 4.x responds best to clarity.
How: Be specific, define output format, provide examples, avoid vagueness.
定义： 明确、无歧义的指示。
原因： Claude 4.x对清晰性的响应最佳。
实现方式： 具体化，定义输出格式，提供示例，避免模糊表述。

4. Security by Design

4. 设计时考虑安全

What: Deny-all default, allowlist approach.
Why: Safe, controlled AI systems.
How: Limit tool access, require confirmations, audit operations, block dangerous commands.
定义： 默认拒绝所有，采用白名单方式。
原因： 构建安全、可控的AI系统。
实现方式： 限制工具访问，要求确认，审计操作，阻止危险命令。

5. Thinking Capabilities

5. 思考能力

What: Leverage Claude's extended thinking mode.
Why: Better results for complex reasoning.
How: Request step-by-step thinking, allow reflection after tool use, guide initial thinking.
定义： 利用Claude的扩展思考模式。
原因： 复杂推理任务能获得更好的结果。
实现方式： 请求分步思考，允许工具使用后的反思，引导初始思考。

6. Two-Message Pattern

6. 双消息模式

What: Use meta messages for context without UI clutter.
Why: Clean UX while providing necessary context.
How: Set isMeta: true for system messages, use for skill loading, keep UI focused.
定义： 使用元消息提供上下文，避免UI混乱。
原因： 在提供必要上下文的同时保持简洁的用户体验。
实现方式： 为系统消息设置isMeta: true，用于Skill加载，保持UI聚焦。

Reference Materials

参考资料

All architectural patterns, decision frameworks, and examples are in the 
references/
directory:
  • decision_rubric.md - Comprehensive decision framework
  • architectural_patterns.md - Detailed pattern catalog
  • best_practices.md - 2025 Anthropic best practices
  • use_case_examples.md - Real-world architecture examples
所有架构模式、决策框架和示例都位于
references/
目录中：
  • decision_rubric.md - 全面的决策框架
  • architectural_patterns.md - 详细的模式目录
  • best_practices.md - 2025年Anthropic最佳实践
  • use_case_examples.md - 真实世界的架构示例

Usage Examples

使用示例

Example 1: Determining Architecture for Content Generation

示例1：内容生成系统的架构确定

Input:
Using anthropic-architect, I need to build a system that:
- Generates blog posts from product features
- Ensures brand voice consistency
- Includes SEO optimization
- Reusable across marketing team
Analysis:
  • Medium complexity (structured workflow)
  • High reusability (team-wide)
  • Domain expertise needed (content, SEO, brand)
  • Progressive disclosure beneficial
Recommendation: Skills-First Architecture
  • Create 
    content-generator
    skill
  • Include brand voice references
  • SEO guidelines in references
  • Example templates
  • Progressive disclosure for different content types
输入：
Using anthropic-architect, I need to build a system that:
- Generates blog posts from product features
- Ensures brand voice consistency
- Includes SEO optimization
- Reusable across marketing team
分析：
  • 中等复杂度（结构化工作流）
  • 高可复用性（团队范围）
  • 需要领域专业知识（内容、SEO、品牌）
  • 渐进式披露有益
建议： Skills优先架构
  • 创建
    content-generator
    Skill
  • 包含品牌语调参考资料
  • SEO指南放入参考资料
  • 示例模板
  • 针对不同内容类型的渐进式披露

Example 2: Code Refactoring Tool

示例2：代码重构工具

Input:
Using anthropic-architect, I want to:
- Analyze codebase for refactoring opportunities
- Generate refactoring plan
- Execute refactoring with tests
- Review and validate changes
Analysis:
  • High complexity (multi-step, autonomous)
  • Different contexts needed (explore, plan, code, review)
  • Parallel execution beneficial
  • Tool permissions vary by stage
Recommendation: Agent-Based Architecture
  • Main orchestrator agent
  • Explore subagent (read-only, codebase analysis)
  • Plan subagent (planning, no execution)
  • Code subagent (write permissions)
  • Review subagent (validation, test execution)
输入：
Using anthropic-architect, I want to:
- Analyze codebase for refactoring opportunities
- Generate refactoring plan
- Execute refactoring with tests
- Review and validate changes
分析：
  • 高复杂度（多步骤、自主）
  • 需要不同的上下文（探索、规划、编码、评审）
  • 并行执行有益
  • 各阶段工具权限不同
建议： 基于Agent的架构
  • 主编排Agent
  • Explore子Agent（只读，代码库分析）
  • Plan子Agent（规划，无执行权限）
  • Code子Agent（写入权限）
  • Review子Agent（验证，测试执行）

Example 3: Simple Code Review

示例3：简单代码评审

Input:
Using anthropic-architect, I need to:
- Review this PR for bugs
- Check code style
- Suggest improvements
Analysis:
  • Low complexity (single operation)
  • One-time task
  • No reusability needed
  • Minimal context
Recommendation: Direct Prompt
  • Simple, clear instructions
  • No skill/agent overhead
  • Fast execution
  • Sufficient for task
输入：
Using anthropic-architect, I need to:
- Review this PR for bugs
- Check code style
- Suggest improvements
分析：
  • 低复杂度（单一操作）
  • 一次性任务
  • 无需复用
  • 极少上下文
建议： Direct Prompts
  • 简单、清晰的指令
  • 无Skill/Agent开销
  • 执行快速
  • 足以完成任务

Example 4: Custom CI/CD Integration

示例4：自定义CI/CD集成

Input:
Using anthropic-architect, I want to:
- Integrate Claude into CI pipeline
- Custom tool for deployment validation
- Specific workflow for our stack
- Production feature
Analysis:
  • Custom complexity
  • System integration required
  • Production deployment
  • Unique workflows
Recommendation: SDK Primitives
  • Build custom agent with SDK
  • Implement custom tools
  • Create specialized feedback loops
  • Integration with CI system
输入：
Using anthropic-architect, I want to:
- Integrate Claude into CI pipeline
- Custom tool for deployment validation
- Specific workflow for our stack
- Production feature
分析：
  • 自定义复杂度
  • 需要系统集成
  • 生产环境部署
  • 独特的工作流
建议： SDK Primitives
  • 使用SDK构建自定义Agent
  • 实现自定义工具
  • 创建专业化的反馈循环
  • 与CI系统集成

Best Practices Checklist

最佳实践检查清单

When designing your architecture:
  • Analyzed task complexity accurately
  • Considered reusability requirements
  • Evaluated context management needs
  • Assessed security requirements
  • Applied progressive disclosure where beneficial
  • Chose simplest solution that works
  • Documented architectural decisions
  • Planned for maintenance and updates
  • Considered cost implications
  • Validated with prototype/POC
设计架构时：
  • 准确分析任务复杂度
  • 考虑可复用性要求
  • 评估上下文管理需求
  • 评估安全要求
  • 在有益的地方应用渐进式披露
  • 选择最简单的可行方案
  • 记录架构决策
  • 规划维护和更新
  • 考虑成本影响
  • 通过原型/POC验证

Common Anti-Patterns

常见反模式

Anti-Pattern 1: Over-Engineering

反模式1：过度设计

Problem: Using Agents/SDK for simple tasks
Solution: Start simple, scale complexity as needed
问题： 对简单任务使用Agents/SDK
解决方案： 从简单开始，根据需要提升复杂度

Anti-Pattern 2: Context Dumping

反模式2：上下文导入

Problem: Loading entire skills into context
Solution: Use progressive disclosure, query tools
问题： 将整个Skills加载到上下文中
解决方案： 使用渐进式披露、查询工具

Anti-Pattern 3: Mixed Concerns

反模式3：关注点混杂

Problem: Single skill/agent doing too much
Solution: Separate concerns, use subagents or multiple skills
问题： 单个Skill/Agent承担过多职责
解决方案： 分离关注点，使用子Agent或多个Skills

Anti-Pattern 4: No Security Boundaries

反模式4：无安全边界

Problem: Full tool access for all agents
Solution: Allowlist approach, minimal permissions
问题： 所有Agent拥有完整的工具访问权限
解决方案： 白名单方式，最小权限原则

Anti-Pattern 5: Ignoring Reusability

反模式5：忽略可复用性

Problem: Recreating same prompts repeatedly
Solution: Extract to skills, share across projects
问题： 重复创建相同的Prompts
解决方案： 提取为Skills，跨项目共享

Getting Started

开始使用

Step 1: Describe Your Project

步骤1：描述你的项目

Provide clear requirements, complexity level, and constraints.
提供清晰的需求、复杂度级别和约束条件。

Step 2: Receive Recommendation

步骤2：接收建议

Get tailored architecture with reasoning.
获取带决策依据的定制化架构建议。

Step 3: Review Patterns

步骤3：查看模式

Explore similar successful architectures.
探索类似的成功架构案例。

Step 4: Implement

步骤4：实施

Follow implementation guidance.
遵循实施指导进行构建。

Step 5: Iterate

步骤5：迭代

Refine based on results and feedback.
根据结果和反馈进行优化。

Summary

总结

The Anthropic Architect skill helps you:
  • Choose the right primitives for your needs
  • Design scalable, maintainable architectures
  • Follow 2025 best practices
  • Avoid common pitfalls
  • Optimize for performance and cost
Key Primitives:
  • Skills - Reusable domain expertise
  • Agents - Autonomous complex workflows
  • Prompts - Simple direct tasks
  • SDK - Custom integrations
Core Principles:
  • Progressive disclosure
  • Context as resource
  • Security by design
  • Clear instructions
  • Right tool for the job
"The best architecture is the simplest one that meets your requirements."
Anthropic架构师Skill可以帮助你：
  • 选择符合需求的原语
  • 设计可扩展、可维护的架构
  • 遵循2025年最佳实践
  • 避免常见陷阱
  • 优化性能和成本
核心原语：
  • Skills - 可复用的领域专业知识
  • Agents - 自主复杂工作流
  • Prompts - 简单直接任务
  • SDK - 自定义集成
核心原则：
  • 渐进式披露
  • 上下文作为资源
  • 设计时考虑安全
  • 清晰的指令
  • 选用合适的工具
“最佳架构是满足你需求的最简单方案。”