Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Aggregate and centralize performance metrics from applications, systems, databases, caches, and services. Use when consolidating monitoring data from multiple sources. Trigger with phrases like "aggregate metrics", "centralize monitoring", or "collect performance data".
.claude/skills/jeremylongshore-aggregating-performance-metrics/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | 32% | 0% |
| case-22 | ✗→✓ | ▲ Improved | 49% | 0% |
| case-12 | ✓→✗ | ▼ Worse | 22% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | 36% | 0% |
| case-07 | ✓→✓ | ＝ Same ✓ | 19% | 0% |
Aggregate and centralize performance metrics from applications, databases, caches, and infrastructure into Prometheus, StatsD, or CloudWatch with unified naming conventions.
This skill empowers Claude to streamline performance monitoring by aggregating metrics from diverse systems into a unified view. It simplifies the process of collecting, centralizing, and analyzing performance data, leading to improved insights and faster issue resolution.
This skill activates when you need to:
User request: "Aggregate application and system metrics into Prometheus."
The skill will:
User request: "Centralize database metrics and set up alerts for slow queries."
The skill will:
This skill integrates with other plugins that manage infrastructure, deploy applications, and monitor system health. For example, it can be used in conjunction with a deployment plugin to automatically configure metrics collection after a new application deployment.
If metrics aggregation fails:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 27,602 | 21,418 | -22% | 1 | 1 | 0% | 6,189 | 5,374 | -13% | 0 | 0 | — |
case-02 | fail→fail | 23,009 | 19,980 | -13% | 1 | 1 | 0% | 4,910 | 4,835 | -2% | 0 | 0 | — |
case-03 | fail→fail | 13,167 | 13,270 | +1% | 1 | 1 | 0% | 2,646 | 3,473 | +31% | 0 | 0 | — |
case-04 | fail→fail | 16,820 | 17,353 | +3% | 1 | 1 | 0% | 2,802 | 4,082 | +46% | 0 | 0 | — |
case-05 | fail→fail | 12,133 | 9,577 | -21% | 1 | 1 | 0% | 2,353 | 2,486 | +6% | 0 | 0 | — |
case-06 | pass→pass | 16,694 | 17,471 | +5% | 1 | 1 | 0% | 2,733 | 3,720 | +36% | 0 | 0 | — |
case-07 | pass→pass | 17,152 | 16,154 | -6% | 1 | 1 | 0% | 3,319 | 3,961 | +19% | 0 | 0 | — |
case-08 | pass→pass | 22,779 | 21,757 | -4% | 1 | 1 | 0% | 5,080 | 5,924 | +17% | 0 | 0 | — |
case-09 | fail→pass | 16,856 | 15,923 | -6% | 1 | 1 | 0% | 2,829 | 3,731 | +32% | 0 | 0 | — |
case-10 | pass→pass | 18,342 | 20,925 | +14% | 1 | 1 | 0% | 3,247 | 4,390 | +35% | 0 | 0 | — |
case-11 | pass→pass | 16,036 | 13,820 | -14% | 1 | 1 | 0% | 2,790 | 3,229 | +16% | 0 | 0 | — |
case-12 | pass→fail | 16,459 | 15,705 | -5% | 1 | 1 | 0% | 3,119 | 3,809 | +22% | 0 | 0 | — |
case-13 | pass→pass | 15,199 | 10,173 | -33% | 1 | 1 | 0% | 1,797 | 2,617 | +46% | 0 | 0 | — |
case-14 | pass→pass | 15,308 | 14,481 | -5% | 1 | 1 | 0% | 2,793 | 3,449 | +23% | 0 | 0 | — |
case-15 | pass→pass | 17,103 | 17,172 | +0% | 1 | 1 | 0% | 3,246 | 4,369 | +35% | 0 | 0 | — |
case-16 | pass→pass | 13,992 | 10,517 | -25% | 1 | 1 | 0% | 2,959 | 2,979 | +1% | 0 | 0 | — |
case-17 | pass→pass | 19,125 | 14,216 | -26% | 1 | 1 | 0% | 3,217 | 3,287 | +2% | 0 | 0 | — |
case-18 | pass→pass | 18,672 | 19,099 | +2% | 1 | 1 | 0% | 3,078 | 3,884 | +26% | 0 | 0 | — |
case-19 | pass→pass | 17,908 | 20,541 | +15% | 1 | 1 | 0% | 2,792 | 4,090 | +46% | 0 | 0 | — |
case-20 | pass→pass | 19,926 | 16,781 | -16% | 1 | 1 | 0% | 4,214 | 4,580 | +9% | 0 | 0 | — |
case-21 | pass→pass | 17,564 | 12,450 | -29% | 1 | 1 | 0% | 2,873 | 2,874 | +0% | 0 | 0 | — |
case-22 | fail→pass | 15,336 | 16,632 | +8% | 1 | 1 | 0% | 2,562 | 3,819 | +49% | 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 +5 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.