Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Multi-cloud cost analysis and optimization expertise for FinOps practices
.claude/skills/a5c-ai-cloud-cost-analysis/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-17 | ✓→✗ | ▼ Worse | 43% | 0% |
| case-22 | ✓→✗ | ▼ Worse | 122% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 6% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 37% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 74% | 0% |
Specialized skill for multi-cloud cost analysis and optimization. Provides deep expertise in FinOps practices, cost visibility, and resource optimization across AWS, GCP, and Azure.
cost-optimization.js - Cost optimization initiativesauto-scaling.js - Cost-aware scaling policiesiac-implementation.js - Cost-tagged infrastructureThis skill is invoked when processes require:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 12,284 | 13,720 | +12% | 1 | 1 | 0% | 1,987 | 2,106 | +6% | 0 | 0 | — |
case-02 | pass→pass | 15,031 | 20,927 | +39% | 1 | 1 | 0% | 2,457 | 3,371 | +37% | 0 | 0 | — |
case-03 | pass→pass | 12,155 | 15,838 | +30% | 1 | 1 | 0% | 1,748 | 3,037 | +74% | 0 | 0 | — |
case-04 | pass→pass | 11,156 | 20,086 | +80% | 1 | 1 | 0% | 1,909 | 3,612 | +89% | 0 | 0 | — |
case-05 | pass→pass | 19,604 | 21,964 | +12% | 1 | 1 | 0% | 3,032 | 3,623 | +19% | 0 | 0 | — |
case-06 | pass→pass | 14,312 | 18,820 | +31% | 1 | 1 | 0% | 2,335 | 3,118 | +34% | 0 | 0 | — |
case-07 | pass→pass | 15,595 | 17,690 | +13% | 1 | 1 | 0% | 2,395 | 3,638 | +52% | 0 | 0 | — |
case-08 | fail→fail | 11,439 | 15,883 | +39% | 1 | 1 | 0% | 1,937 | 2,714 | +40% | 0 | 0 | — |
case-09 | pass→pass | 13,606 | 18,144 | +33% | 1 | 1 | 0% | 2,001 | 2,942 | +47% | 0 | 0 | — |
case-10 | pass→pass | 7,031 | 11,812 | +68% | 1 | 1 | 0% | 1,136 | 2,139 | +88% | 0 | 0 | — |
case-11 | pass→pass | 15,772 | 16,101 | +2% | 1 | 1 | 0% | 2,280 | 3,201 | +40% | 0 | 0 | — |
case-12 | pass→pass | 7,711 | 7,064 | -8% | 1 | 1 | 0% | 1,209 | 1,482 | +23% | 0 | 0 | — |
case-13 | pass→pass | 14,254 | 17,481 | +23% | 1 | 1 | 0% | 2,005 | 2,960 | +48% | 0 | 0 | — |
case-14 | pass→pass | 12,073 | 10,933 | -9% | 1 | 1 | 0% | 2,119 | 2,052 | -3% | 0 | 0 | — |
case-15 | pass→pass | 20,658 | 17,269 | -16% | 1 | 1 | 0% | 2,987 | 3,371 | +13% | 0 | 0 | — |
case-16 | pass→pass | 15,728 | 17,263 | +10% | 1 | 1 | 0% | 2,234 | 2,954 | +32% | 0 | 0 | — |
case-17 | pass→fail | 15,390 | 19,409 | +26% | 1 | 1 | 0% | 2,615 | 3,739 | +43% | 0 | 0 | — |
case-18 | pass→pass | 7,621 | 7,688 | +1% | 1 | 1 | 0% | 1,179 | 1,704 | +45% | 0 | 0 | — |
case-19 | fail→fail | 9,379 | 15,288 | +63% | 1 | 1 | 0% | 1,268 | 2,364 | +86% | 0 | 0 | — |
case-20 | pass→pass | 19,381 | 22,793 | +18% | 1 | 1 | 0% | 2,742 | 3,468 | +26% | 0 | 0 | — |
case-21 | pass→pass | 5,744 | 4,245 | -26% | 1 | 1 | 0% | 986 | 1,017 | +3% | 0 | 0 | — |
case-22 | pass→fail | 5,081 | 4,352 | -14% | 1 | 1 | 0% | 600 | 1,330 | +122% | 0 | 0 | — |
case-23 | pass→pass | 11,473 | 8,606 | -25% | 1 | 1 | 0% | 2,316 | 2,327 | +0% | 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. 23 cases were attempted. The headline lift of -33 percentage points is the difference between those two pass rates over the 23 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
Other measured skills in the registry, with their headline benchmark lift.