Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Imported from borghei/claude-skills
.claude/skills/borghei-senior-cloud-architect/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 46% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -54% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 166% | 0% |
| case-09 | ✓→✗ | ▼ Worse | 60% | 0% |
| case-12 | ✓→✓ | = Same ✓ | 78% | 0% |
Expert cloud architecture and infrastructure design across AWS, GCP, and Azure — production-grade VPC/compute/database topologies, cost optimization, disaster recovery, and security posture auditing.
cloud, aws, gcp, azure, terraform, infrastructure, vpc, eks, ecs, lambda, cost-optimization, disaster-recovery, multi-region, iam, security, migration
Before designing the architecture, confirm these inputs. If any is unknown or vague, ASK — do not assume:
Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.
Load the reference that matches the task — keep this file lean and pull detail on demand:
This skill covers:
This skill does NOT cover:
senior-architect)senior-devops)ra-qm-team/ compliance skills)senior-devops)| Skill | Integration | Data Flow | |-------|-------------|-----------| | senior-devops | Infrastructure provisioning feeds into CI/CD deployment pipelines | Terraform outputs (endpoints, ARNs) → deployment configs | | senior-secops | Security audit findings inform cloud hardening decisions | CIS benchmark results → security remediation tasks | | senior-architect | Application architecture requirements drive cloud resource selection | Capacity requirements → compute/storage/network sizing | | aws-solution-architect | AWS-specific deep dives complement multi-cloud strategy | Cloud platform comparison → AWS implementation details | | ra-qm-team/soc2-compliance | Compliance requirements shape infrastructure security controls | Compliance matrices → IAM policies, encryption configs, audit logging | | senior-fullstack | Fullstack application stacks deploy onto cloud infrastructure | Application stack definitions → ECS/EKS task definitions, RDS configs |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 27,912 | 24,699 | -12% | 1 | 1 | 0% | 6,194 | 5,966 | -4% | 0 | 0 | — |
case-02 | fail→pass | 21,581 | 23,672 | +10% | 1 | 1 | 0% | 3,476 | 5,080 | +46% | 0 | 0 | — |
case-12 | pass→pass | 13,470 | 20,752 | +54% | 1 | 1 | 0% | 2,846 | 5,061 | +78% | 0 | 0 | — |
case-03 | fail→pass | 25,252 | 3,912 | -85% | 1 | 1 | 0% | 3,932 | 1,797 | -54% | 0 | 0 | — |
case-04 | fail→pass | 15,780 | 23,960 | +52% | 1 | 1 | 0% | 2,731 | 7,251 | +166% | 0 | 0 | — |
case-05 | pass→pass | 20,464 | 16,901 | -17% | 1 | 1 | 0% | 3,989 | 3,528 | -12% | 0 | 0 | — |
case-06 | pass→pass | 10,073 | 12,621 | +25% | 1 | 1 | 0% | 1,841 | 2,962 | +61% | 0 | 0 | — |
case-07 | pass→pass | 11,166 | 22,298 | +100% | 1 | 1 | 0% | 2,150 | 4,975 | +131% | 0 | 0 | — |
case-08 | pass→pass | 18,710 | 20,623 | +10% | 1 | 1 | 0% | 3,697 | 5,530 | +50% | 0 | 0 | — |
case-09 | pass→fail | 13,768 | 16,186 | +18% | 1 | 1 | 0% | 2,501 | 3,994 | +60% | 0 | 0 | — |
case-10 | pass→pass | 22,186 | 29,316 | +32% | 1 | 1 | 0% | 3,602 | 5,595 | +55% | 0 | 0 | — |
case-11 | pass→pass | 12,211 | 19,592 | +60% | 1 | 1 | 0% | 2,343 | 4,467 | +91% | 0 | 0 | — |
case-13 | fail→fail | 23,010 | 26,705 | +16% | 1 | 1 | 0% | 2,078 | 5,852 | +182% | 0 | 0 | — |
case-14 | pass→pass | 19,321 | 21,673 | +12% | 1 | 1 | 0% | 3,201 | 5,074 | +59% | 0 | 0 | — |
case-15 | pass→pass | 12,024 | 27,093 | +125% | 1 | 1 | 0% | 2,371 | 3,651 | +54% | 0 | 0 | — |
case-16 | pass→pass | 20,210 | 25,040 | +24% | 1 | 1 | 0% | 3,275 | 5,256 | +60% | 0 | 0 | — |
case-17 | pass→pass | 16,569 | 21,620 | +30% | 1 | 1 | 0% | 2,729 | 4,872 | +79% | 0 | 0 | — |
case-18 | pass→pass | 16,181 | 16,255 | +0% | 1 | 1 | 0% | 2,235 | 3,566 | +60% | 0 | 0 | — |
case-19 | pass→pass | 12,114 | 14,015 | +16% | 1 | 1 | 0% | 1,846 | 3,268 | +77% | 0 | 0 | — |
case-20 | fail→fail | 17,827 | 21,231 | +19% | 1 | 1 | 0% | 3,045 | 4,726 | +55% | 0 | 0 | — |
case-21 | fail→fail | 30,672 | 17,265 | -44% | 1 | 1 | 0% | 4,144 | 4,688 | +13% | 0 | 0 | — |
case-22 | fail→fail | 30,765 | 39,395 | +28% | 1 | 1 | 0% | 4,181 | 4,941 | +18% | 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. 22 cases were attempted. The headline lift of +9 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
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.