How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

aws-solution-architect - Skill

Name: aws-solution-architect
Author: borghei

Imported from borghei/claude-skills (engineering/aws-solution-architect/SKILL.md). Install upstream with npx skills add borghei/claude-skills --skill aws-solution-architect. Copyright stays with the author (MIT + Commons Clause).

AWS Solution Architect

Design scalable, cost-effective AWS architectures for startups with infrastructure-as-code templates — recommend the right pattern, generate CloudFormation/CDK/Terraform, and optimize spend.

Core Capabilities

Architecture design — recommend serverless, three-tier, microservices, data-pipeline, GraphQL, IoT, or multi-region patterns from app type, scale, budget, and compliance needs.
IaC generation — produce production-ready CloudFormation (SAM), CDK (TypeScript), and Terraform (HCL) with API Gateway, Lambda, DynamoDB, Cognito, IAM least-privilege, and CloudWatch.
Cost optimization — analyze inventory for idle resources, right-sizing, Savings Plans, storage tiering, and NAT Gateway alternatives with prioritized savings.
Service selection — decision matrices for compute, database, storage, networking, and security.
Operational excellence — monitoring, alarming, disaster recovery (RTO/RPO), and security hardening.

When to Use

Designing serverless / three-tier / microservices / data-pipeline / multi-region AWS architecture.
Writing or generating CloudFormation, CDK, or Terraform infrastructure-as-code.
Reducing AWS costs, right-sizing, or evaluating Savings Plans / Reserved capacity.
Selecting AWS services (Lambda, API Gateway, DynamoDB, Aurora, ECS/Fargate, EventBridge, AppSync).
Setting up CI/CD (CodePipeline, CodeBuild) or migrating workloads to AWS.
Hardening IAM, VPC, encryption, Cognito, WAF, or planning monitoring (CloudWatch, X-Ray).

Clarify First

Before designing the architecture, settle the inputs below. When one is missing or vague and would change the result, ask about it; when it wouldn't, use a sensible default and say which one you used.

App type & scale: workload type and expected traffic (selects the pattern: serverless, three-tier, microservices, data-pipeline, or multi-region).
IaC target: CloudFormation/SAM, CDK, or Terraform (sets the template format serverless_stack.py generates).
Budget & compliance constraints: cost ceiling and any regulatory needs (drive service selection and the cost-optimization recommendations).

Ask about the two or three inputs that matter most for this request, not the whole list. If the user wants a result straight away, produce it and state your assumptions at the top.

Tools

Each script is a command-line tool and an importable class. Every CLI prints an input template with --example (or --help) and supports --format json. See references/tool-reference.md for full parameters, methods, and examples.

Tool	Purpose	Usage
`architecture_designer.py`	Recommend a pattern + service stack + cost estimate from requirements	`python scripts/architecture_designer.py --input requirements.json`
`serverless_stack.py`	Generate CloudFormation / CDK / Terraform serverless templates	`python scripts/serverless_stack.py --app-name my-app --region us-east-1 --format cloudformation`
`cost_optimizer.py`	Analyze inventory + spend → prioritized savings recommendations	`python scripts/cost_optimizer.py --resources current_setup.json --monthly-spend 2000`

References

Load the reference that matches the task — keep this file lean and pull detail on demand:

references/workflow-and-usage.md — the 6-step design→deploy→validate workflow, quick-start scenarios (MVP, scaling, cost optimization, IaC), input-requirements JSON, and output formats. Read when running an end-to-end design.
references/architecture_patterns.md — the 6 detailed patterns (serverless, microservices, three-tier, data processing, GraphQL, multi-region) with full service specs. Read when selecting and designing a pattern.
references/service_selection.md — decision matrices for compute, database, storage, and messaging. Read when choosing between AWS services.
references/best_practices.md — serverless design, cost optimization, security hardening, scalability, plus service limitations, troubleshooting, and success criteria. Read before shipping an architecture.
references/tool-reference.md — full Python API (constructors, methods, requirement/resource dictionaries, examples) for the three tools. Read when invoking the tools programmatically.

Scope & Limitations

This skill covers:

AWS architecture design for startups and growth-stage companies (serverless, three-tier, microservices, data pipelines, IoT, multi-region patterns)
Infrastructure-as-code generation for CloudFormation (SAM), CDK (TypeScript), and Terraform (HCL)
Cost analysis, right-sizing recommendations, and Savings Plans evaluation
Service selection guidance for compute, database, storage, networking, and security

This skill does NOT cover:

Multi-cloud or hybrid-cloud architectures (Azure, GCP) -- see engineering/cloud-migration-specialist/ for cross-cloud strategies
Application-level code, business logic, or framework-specific implementation -- see engineering/senior-fullstack/ for fullstack development
Compliance audit execution or regulatory evidence collection -- see ra-qm-team/ for SOC 2, HIPAA, GDPR, and ISO compliance skills
AWS account management, organization policies, or billing disputes -- see AWS Support or engineering/ms365-tenant-manager/ for tenant administration patterns

Integration Points

Skill	Integration	Data Flow
`engineering/senior-devops`	CI/CD pipeline configuration for deploying generated IaC templates	Architecture templates flow into DevOps deployment pipelines and monitoring setup
`engineering/senior-secops`	Security hardening of generated architectures (IAM policies, WAF rules, GuardDuty)	Architecture design feeds into security review; SecOps findings feed back as architecture constraints
`ra-qm-team/soc2-compliance`	Compliance validation of AWS architectures against SOC 2 Trust Services Criteria	Architecture resource inventory feeds into compliance audit; audit findings drive architecture changes
`engineering/senior-backend`	Backend service implementation that runs on the designed AWS infrastructure	Architecture patterns define the runtime environment; backend requirements inform service selection
`engineering/tech-stack-evaluator`	Technology selection decisions that influence architecture pattern choice	Stack evaluation outputs (database, compute, messaging choices) feed into architecture requirements JSON
`c-level-advisor/cto-advisor`	Strategic infrastructure decisions, build-vs-buy, and cloud budget planning	Cost analysis from `cost_optimizer.py` informs CTO budget decisions; CTO constraints flow back as architecture requirements

Install aws-solution-architect and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

{ "ocm": "1", "id": "borghei-claude-skills-aws-solution-architect", "kind": "skill", "name": "aws-solution-architect", "description": "Design AWS serverless architectures for startups with IaC. Use when designing serverless architecture, writing CloudFormation, optimizing AWS costs, setting up CI/CD, or migrating to AWS across Lambda, API Gateway, and DynamoDB.", "publisher": "borghei", "version": "1.0.0", "capabilities": { "domains": [ "coding", "finance" ], "tags": [ "skill-md", "aws", "serverless", "cloudformation", "cost-optimization", "skills-sh" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "Design AWS serverless architectures for startups with IaC. Use when designing serverless architecture, writing CloudFormation, optimizing AWS costs, setting up CI/CD, or migrating to AWS across Lambda, API Gateway, and DynamoDB." ], "primary": false, "metadata": { "source": { "provider": "skills.sh", "repository": "https://github.com/borghei/claude-skills", "path": "engineering/aws-solution-architect/SKILL.md", "ref": "HEAD", "url": "https://github.com/borghei/claude-skills/blob/HEAD/engineering/aws-solution-architect/SKILL.md", "key": "borghei/claude-skills/engineering/aws-solution-architect/SKILL.md" }, "license": "MIT + Commons Clause" }, "instructions": "# AWS Solution Architect\n\nDesign scalable, cost-effective AWS architectures for startups with infrastructure-as-code templates — recommend the right pattern, generate CloudFormation/CDK/Terraform, and optimize spend.\n\n## Core Capabilities\n\n- **Architecture design** — recommend serverless, three-tier, microservices, data-pipeline, GraphQL, IoT, or multi-region patterns from app type, scale, budget, and compliance needs.\n- **IaC generation** — produce production-ready CloudFormation (SAM), CDK (TypeScript), and Terraform (HCL) with API Gateway, Lambda, DynamoDB, Cognito, IAM least-privilege, and", "cost": { "context_tokens": 1742 } }

aws-solution-architect

About

AWS Solution Architect

Core Capabilities

When to Use

Clarify First

Tools

References

Scope & Limitations

Integration Points

Install aws-solution-architect and it becomes one more candidate the router can pick - when it fits.

What it costs to adopt - in engineering time.

One base URL

No vendor lock-in

Failover built in

Use it

Manifest

Reviews