Design cloud-native architectures with service selection and cost optimization
Generates cloud-native architectures with service selection and cost optimization. Use when users request infrastructure designs for AWS, Azure, or GCP workloads.
/plugin marketplace add pluginagentmarketplace/custom-plugin-software-architect/plugin install software-architect-assistant@pluginagentmarketplace-software-architectThis skill inherits all available tools. When active, it can use any tool Claude has access to.
assets/config.yamlassets/schema.jsonreferences/GUIDE.mdreferences/PATTERNS.mdscripts/validate.pyDesign cloud infrastructure architectures with appropriate service selection, cost optimization, and deployment strategies across AWS, Azure, and GCP.
| Parameter | Type | Required | Validation | Default |
|---|---|---|---|---|
workload | string | ✅ | min: 30 chars | - |
provider | enum | ⚪ | aws|azure|gcp|multi | aws |
requirements | object | ⚪ | valid JSON | {} |
budget_tier | enum | ⚪ | startup|growth|enterprise | growth |
architecture_type | enum | ⚪ | serverless|containers|vms|hybrid | containers |
Requirements Schema:
{
"availability": "99.9%",
"latency_ms": 100,
"monthly_budget_usd": 5000
}
┌──────────────────────────────────────────────────────────┐
│ 1. VALIDATE: Check workload and requirements │
│ 2. ANALYZE: Workload characteristics │
│ 3. SELECT: Cloud services for each component │
│ 4. DESIGN: Architecture diagram │
│ 5. ESTIMATE: Cost projection │
│ 6. OPTIMIZE: Apply cost/performance optimizations │
│ 7. DOCUMENT: Return architecture with IaC snippets │
└──────────────────────────────────────────────────────────┘
| Error | Retry | Backoff | Max Attempts |
|---|---|---|---|
PROVIDER_ERROR | Yes | 2s, 4s | 3 |
COST_CALC_ERROR | Yes | 1s | 2 |
VALIDATION_ERROR | No | - | 1 |
log_points:
- event: design_started
level: info
data: [provider, architecture_type]
- event: cost_estimate_complete
level: info
data: [monthly_estimate_usd, services_count]
- event: optimization_applied
level: info
data: [optimization_type, savings_percent]
metrics:
- name: architectures_designed
type: counter
labels: [provider]
- name: design_time_ms
type: histogram
- name: estimated_monthly_cost
type: gauge
| Error Code | Description | Recovery |
|---|---|---|
E201 | Invalid provider | Show supported providers |
E202 | Budget exceeded | Suggest lower-cost alternatives |
E203 | Conflicting requirements | Highlight trade-offs |
E204 | Service not available in region | Suggest alternatives |
test_cases:
- name: "Web app on AWS"
input:
workload: "E-commerce web application with 10K daily users"
provider: "aws"
architecture_type: "containers"
expected:
has_services: true
has_diagram: true
has_cost_estimate: true
services_include: ["ECS", "RDS", "CloudFront"]
- name: "Serverless API"
input:
workload: "RESTful API with variable traffic"
provider: "aws"
architecture_type: "serverless"
expected:
services_include: ["Lambda", "API Gateway", "DynamoDB"]
- name: "Budget exceeded"
input:
workload: "Enterprise data warehouse"
requirements: { "monthly_budget_usd": 100 }
expected:
warning: "budget_exceeded"
has_alternatives: true
| Symptom | Root Cause | Resolution |
|---|---|---|
| High cost estimate | Wrong service tier | Right-size, use reserved |
| Single point of failure | Missing HA design | Add multi-AZ, redundancy |
| Vendor lock-in warning | Proprietary services | Use portable alternatives |
□ Is provider selection appropriate?
□ Are availability requirements met?
□ Is cost within budget?
□ Are all components connected?
□ Is IaC syntax valid?
| Component | AWS | Azure | GCP |
|---|---|---|---|
| Compute | ECS/Lambda | AKS/Functions | GKE/Cloud Functions |
| Database | RDS/Aurora | SQL Database | Cloud SQL |
| Storage | S3 | Blob Storage | Cloud Storage |
| Cache | ElastiCache | Cache for Redis | Memorystore |
| Component | Trigger | Data Flow |
|---|---|---|
| Agent 04 | Design request | Receives workload, returns architecture |
| Agent 05 | Security review | Provides security requirements |
| Version | Date | Changes |
|---|---|---|
| 2.0.0 | 2025-01 | Production-grade: multi-cloud, cost estimation, IaC |
| 1.0.0 | 2024-12 | Initial release |
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.