Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cursor rules for Knative development with Istio, Typesense, and GPU integration.
.claude/skills/amariahak-cursor-rules-for-knative-development-with-istio-typesense-and-gpu-integration/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -11% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 35% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 40% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 8% | 0% |
Cursor rules for Knative development with Istio, Typesense, and GPU integration.
Synced from https://github.com/PatrickJS/awesome-cursorrules/tree/main/rules/knative-istio-typesense-gpu-cursorrules-prompt-fil.mdc.
You are an expert AI programming assistant specializing in building Knative, Istio, Typesense, htmx and GPU accelerated applications.
As an AI assistant, your role is to provide guidance, code snippets, explanations, and troubleshooting support throughout the development process. You should be prepared to assist with all aspects of the project, from architecture design to implementation details.
Always prioritize security, scalability, and maintainability in your designs and implementations. Leverage the power and simplicity of knative to create efficient and idiomatic code.
Project-Specific Notes
Remember, your goal is to guide the development process, provide helpful insights, and assist in creating a robust, scalable, and efficient AI-powered search application.
These custom instructions provide a comprehensive guide for Claude to assist you with your AI-powered search project. They cover the key components of your system and outline the areas where you might need assistance.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | fail→pass | 13,038 | 7,525 | -42% | 1 | 1 | 0% | 2,341 | 2,095 | -11% | 0 | 0 | — |
case-01 | fail→pass | 15,449 | 12,455 | -19% | 1 | 1 | 0% | 2,974 | 3,325 | +12% | 0 | 0 | — |
case-02 | pass→pass | 15,389 | 13,190 | -14% | 1 | 1 | 0% | 2,783 | 3,176 | +14% | 0 | 0 | — |
case-03 | pass→pass | 15,054 | 6,000 | -60% | 1 | 1 | 0% | 2,279 | 1,801 | -21% | 0 | 0 | — |
case-05 | fail→pass | 11,366 | 11,993 | +6% | 1 | 1 | 0% | 2,281 | 3,087 | +35% | 0 | 0 | — |
case-06 | pass→pass | 9,633 | 11,601 | +20% | 1 | 1 | 0% | 1,806 | 2,499 | +38% | 0 | 0 | — |
case-07 | fail→pass | 18,879 | 11,929 | -37% | 1 | 1 | 0% | 2,189 | 3,062 | +40% | 0 | 0 | — |
case-08 | fail→pass | 13,998 | 11,134 | -20% | 1 | 1 | 0% | 2,688 | 2,903 | +8% | 0 | 0 | — |
case-09 | pass→pass | 5,930 | 4,334 | -27% | 1 | 1 | 0% | 1,069 | 1,439 | +35% | 0 | 0 | — |
case-10 | pass→pass | 8,254 | 5,509 | -33% | 1 | 1 | 0% | 1,040 | 1,701 | +64% | 0 | 0 | — |
case-11 | pass→pass | 13,888 | 13,699 | -1% | 1 | 1 | 0% | 2,246 | 3,016 | +34% | 0 | 0 | — |
case-12 | pass→pass | 14,706 | 13,518 | -8% | 1 | 1 | 0% | 2,494 | 3,099 | +24% | 0 | 0 | — |
case-13 | fail→pass | 10,062 | 9,178 | -9% | 1 | 1 | 0% | 1,611 | 2,623 | +63% | 0 | 0 | — |
case-14 | pass→pass | 12,494 | 10,691 | -14% | 1 | 1 | 0% | 2,286 | 2,719 | +19% | 0 | 0 | — |
case-15 | pass→pass | 7,444 | 6,172 | -17% | 1 | 1 | 0% | 1,408 | 1,782 | +27% | 0 | 0 | — |
case-16 | fail→pass | 9,526 | 9,223 | -3% | 1 | 1 | 0% | 1,877 | 2,576 | +37% | 0 | 0 | — |
case-17 | pass→pass | 5,417 | 8,489 | +57% | 1 | 1 | 0% | 965 | 1,880 | +95% | 0 | 0 | — |
case-18 | pass→pass | 4,163 | 4,726 | +14% | 1 | 1 | 0% | 757 | 1,550 | +105% | 0 | 0 | — |
case-19 | pass→pass | 7,915 | 9,065 | +15% | 1 | 1 | 0% | 1,448 | 2,326 | +61% | 0 | 0 | — |
case-20 | pass→pass | 3,999 | 4,961 | +24% | 1 | 1 | 0% | 811 | 1,608 | +98% | 0 | 0 | — |
case-21 | pass→pass | 7,419 | 7,056 | -5% | 1 | 1 | 0% | 1,546 | 2,089 | +35% | 0 | 0 | — |
case-22 | pass→pass | 12,376 | 9,379 | -24% | 1 | 1 | 0% | 2,580 | 2,780 | +8% | 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 +32 percentage points is the difference between those two pass rates over the 22 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.