Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Design multi-cloud architectures using a decision framework to select and integrate services across AWS, Azure, and GCP. Use when building multi-cloud systems, avoiding vendor lock-in, or leveraging best-of-breed services from multiple providers.
.claude/skills/dicklesworthstone-multi-cloud-architecture/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-14 | ✗→✓ | ▲ Improved | 36% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 92% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 128% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 47% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 84% | 0% |
Decision framework and patterns for architecting applications across AWS, Azure, and GCP.
Design cloud-agnostic architectures and make informed decisions about service selection across cloud providers.
| AWS | Azure | GCP | Use Case | | ------- | ------------------- | --------------- | ------------------ | | EC2 | Virtual Machines | Compute Engine | IaaS VMs | | ECS | Container Instances | Cloud Run | Containers | | EKS | AKS | GKE | Kubernetes | | Lambda | Functions | Cloud Functions | Serverless | | Fargate | Container Apps | Cloud Run | Managed containers |
| AWS | Azure | GCP | Use Case | | ------- | --------------- | --------------- | -------------- | | S3 | Blob Storage | Cloud Storage | Object storage | | EBS | Managed Disks | Persistent Disk | Block storage | | EFS | Azure Files | Filestore | File storage | | Glacier | Archive Storage | Archive Storage | Cold storage |
| AWS | Azure | GCP | Use Case | | ----------- | ---------------- | ------------- | --------------- | | RDS | SQL Database | Cloud SQL | Managed SQL | | DynamoDB | Cosmos DB | Firestore | NoSQL | | Aurora | PostgreSQL/MySQL | Cloud Spanner | Distributed SQL | | ElastiCache | Cache for Redis | Memorystore | Caching |
Reference: See references/service-comparison.md for complete comparison
Application Layer
↓
Infrastructure Abstraction (Terraform)
↓
Cloud Provider APIs
↓
AWS / Azure / GCPReference: See references/multi-cloud-patterns.md
references/service-comparison.md - Complete service comparisonreferences/multi-cloud-patterns.md - Architecture patternsterraform-module-library - For IaC implementationcost-optimization - For cost managementhybrid-cloud-networking - For connectivity| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 7,039 | 18,948 | +169% | 1 | 1 | 0% | 1,145 | 2,612 | +128% | 0 | 0 | — |
case-02 | pass→pass | 11,878 | 9,683 | -18% | 1 | 1 | 0% | 1,956 | 2,879 | +47% | 0 | 0 | — |
case-03 | pass→pass | 6,838 | 5,901 | -14% | 1 | 1 | 0% | 1,195 | 2,202 | +84% | 0 | 0 | — |
case-04 | pass→pass | 14,079 | 10,886 | -23% | 1 | 1 | 0% | 2,320 | 3,024 | +30% | 0 | 0 | — |
case-05 | pass→pass | 13,974 | 10,732 | -23% | 1 | 1 | 0% | 2,116 | 2,774 | +31% | 0 | 0 | — |
case-06 | pass→pass | 11,552 | 6,030 | -48% | 1 | 1 | 0% | 2,030 | 2,208 | +9% | 0 | 0 | — |
case-07 | pass→pass | 11,786 | 14,720 | +25% | 1 | 1 | 0% | 2,074 | 3,638 | +75% | 0 | 0 | — |
case-08 | pass→pass | 7,525 | 5,612 | -25% | 1 | 1 | 0% | 1,158 | 2,015 | +74% | 0 | 0 | — |
case-09 | pass→pass | 8,928 | 5,486 | -39% | 1 | 1 | 0% | 1,390 | 1,980 | +42% | 0 | 0 | — |
case-10 | pass→pass | 16,445 | 10,197 | -38% | 1 | 1 | 0% | 2,522 | 2,976 | +18% | 0 | 0 | — |
case-11 | pass→pass | 6,507 | 7,231 | +11% | 1 | 1 | 0% | 1,066 | 2,293 | +115% | 0 | 0 | — |
case-12 | pass→pass | 6,382 | 4,065 | -36% | 1 | 1 | 0% | 1,043 | 1,841 | +77% | 0 | 0 | — |
case-13 | pass→pass | 12,396 | 6,044 | -51% | 1 | 1 | 0% | 1,855 | 2,164 | +17% | 0 | 0 | — |
case-14 | fail→pass | 9,998 | 5,814 | -42% | 1 | 1 | 0% | 1,545 | 2,097 | +36% | 0 | 0 | — |
case-15 | pass→pass | 10,080 | 8,138 | -19% | 1 | 1 | 0% | 1,554 | 2,511 | +62% | 0 | 0 | — |
case-16 | pass→pass | 13,411 | 11,567 | -14% | 1 | 1 | 0% | 2,194 | 2,951 | +35% | 0 | 0 | — |
case-17 | fail→pass | 6,157 | 3,720 | -40% | 1 | 1 | 0% | 909 | 1,749 | +92% | 0 | 0 | — |
case-18 | pass→pass | 11,386 | 13,378 | +17% | 1 | 1 | 0% | 2,234 | 3,381 | +51% | 0 | 0 | — |
case-19 | pass→pass | 15,006 | 7,850 | -48% | 1 | 1 | 0% | 2,452 | 2,547 | +4% | 0 | 0 | — |
case-20 | pass→pass | 7,305 | 8,331 | +14% | 1 | 1 | 0% | 1,196 | 2,554 | +114% | 0 | 0 | — |
case-21 | pass→pass | 25,041 | 31,648 | +26% | 1 | 1 | 0% | 4,924 | 7,533 | +53% | 0 | 0 | — |
case-22 | pass→pass | 8,973 | 7,131 | -21% | 1 | 1 | 0% | 1,943 | 2,637 | +36% | 0 | 0 | — |
case-23 | pass→pass | 21,372 | 19,182 | -10% | 1 | 1 | 0% | 3,407 | 4,376 | +28% | 0 | 0 | — |
case-24 | pass→pass | 8,883 | 10,841 | +22% | 1 | 1 | 0% | 1,453 | 2,655 | +83% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 24 cases were attempted. The headline lift of +8 percentage points is the difference between those two pass rates over the 24 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.