Determine the best Anthropic architecture for your project by analyzing requirements and recommending the optimal combination of Skills, Agents, Prompts, and SDK primitives.
npxskills add zircote/.claude--skill anthropic-architectLoading…
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.
Helps you design the right Anthropic architecture for your project by:
Without proper architecture:
With engineered architecture:
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]
The skill will provide:
What: Organized folders of instructions, scripts, and resources that agents can discover and load dynamically.
When to use:
When NOT to use:
Example use cases:
What: Specialized agents with independent system prompts, dedicated context windows, and specific tool permissions.
When to use:
When NOT to use:
Example use cases:
What: Clear, explicit instructions passed directly to Claude without additional structure.
When to use:
When NOT to use:
Example use cases:
What: Low-level building blocks from the Claude Agent SDK to create custom agent workflows.
When to use:
When NOT to use:
Example use cases:
Use this rubric to determine the right architecture:
Low Complexity → Direct Prompts
Medium Complexity → Skills
High Complexity → Agents/Subagents
20 steps or parallel tasks
Custom Complexity → SDK Primitives
Single Use → Direct Prompts
Team Reuse → Skills
Organization Reuse → Skills + Marketplace
Product Feature → SDK Primitives
Minimal Context → Direct Prompts
Structured Context → Skills
Isolated Context → Agents/Subagents
Custom Context → SDK Primitives
Basic Safety → Direct Prompts + Skills
Controlled Access → Agents with Tool Restrictions
High Security → SDK Primitives + Custom Controls
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:
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:
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:
Use when: Unique requirements or product features
Structure:
Custom Agent SDK Implementation
├── Custom Tools
├── Specialized Feedback Loops
├── System Integrations
└── Domain-Specific Workflows
Benefits:
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.
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.
What: Explicit, unambiguous directions.
Why: Claude 4.x responds best to clarity.
How: Be specific, define output format, provide examples, avoid vagueness.
What: Deny-all default, allowlist approach.
Why: Safe, controlled AI systems.
How: Limit tool access, require confirmations, audit operations, block dangerous commands.
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.
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.
All architectural patterns, decision frameworks, and examples are in the references/ directory:
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:
Recommendation: Skills-First Architecture
content-generator skillInput:
Using anthropic-architect, I want to:
- Analyze codebase for refactoring opportunities
- Generate refactoring plan
- Execute refactoring with tests
- Review and validate changes
Analysis:
Recommendation: Agent-Based Architecture
Input:
Using anthropic-architect, I need to:
- Review this PR for bugs
- Check code style
- Suggest improvements
Analysis:
Recommendation: Direct Prompt
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:
Recommendation: SDK Primitives
When designing your architecture:
Problem: Using Agents/SDK for simple tasks
Solution: Start simple, scale complexity as needed
Problem: Loading entire skills into context
Solution: Use progressive disclosure, query tools
Problem: Single skill/agent doing too much
Solution: Separate concerns, use subagents or multiple skills
Problem: Full tool access for all agents
Solution: Allowlist approach, minimal permissions
Problem: Recreating same prompts repeatedly
Solution: Extract to skills, share across projects
Provide clear requirements, complexity level, and constraints.
Get tailored architecture with reasoning.
Explore similar successful architectures.
Follow implementation guidance.
Refine based on results and feedback.
The Anthropic Architect skill helps you:
Key Primitives:
Core Principles:
"The best architecture is the simplest one that meets your requirements."
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).