Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →KubeStellar Console — Multi-cluster Kubernetes dashboard development rules
.claude/skills/amariahak-kubestellar-console-multi-cluster-kubernetes-dashboard-development-rules/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 100% | 12 |
| gemini-3.1-pro-preview | 100% | 1 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -19% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -25% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -19% | 0% |
KubeStellar Console — Multi-cluster Kubernetes dashboard development rules
Synced from https://github.com/PatrickJS/awesome-cursorrules/tree/main/rules/kubestellar-console.mdc.
/web/cd web && npm run build && npm run lint before every commitweb/src/components/cards/web/src/hooks/useCache/useCached* hooksisDemoData and isRefreshing to useCardLoadingState()isDemoFallback && !isLoadinguseCardLoadingState AFTER hooks providing isDemoData.join(), .map(), .filter(), .forEach(), for...of on values that might be undefined(data || []).map(...) or (data || []).join(', ')0, 1, -1) in clear local contextslib/constants/ (time.ts, network.ts, ui.ts)cn() utility for merging classNamestext-foreground, bg-primary, bg-card)text-green-400/bg-green-500/10 (success), text-yellow-400/bg-yellow-500/10 (warning), text-red-400/bg-red-500/10 (error), text-cyan-400/bg-cyan-500/10 (info) — these map to the design system's semantic status tokens and are the only permitted palette classest() from react-i18nextweb/src/locales/en/ JSON filesfunc(c *fiber.Ctx) errorfiber.NewError(statusCode, message) for errorsmake([]T, 0) not var x []T (nil → null in JSON)log/slog for structured loggingDeduplicatedClusters() when iterating clusters| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 20,973 | 13,916 | -34% | 1 | 1 | 0% | 4,775 | 3,890 | -19% | 0 | 0 | — |
case-02 | fail→fail | 21,160 | 10,039 | -53% | 1 | 1 | 0% | 4,571 | 2,749 | -40% | 0 | 0 | — |
case-03 | fail→pass | 27,791 | 16,805 | -40% | 1 | 1 | 0% | 6,190 | 4,645 | -25% | 0 | 0 | — |
case-04 | fail→pass | 10,623 | 5,947 | -44% | 1 | 1 | 0% | 1,818 | 1,828 | +1% | 0 | 0 | — |
case-05 | pass→pass | 9,912 | 4,590 | -54% | 1 | 1 | 0% | 1,784 | 1,516 | -15% | 0 | 0 | — |
case-06 | pass→pass | 11,537 | 3,941 | -66% | 1 | 1 | 0% | 2,102 | 1,359 | -35% | 0 | 0 | — |
case-07 | fail→pass | 9,612 | 4,705 | -51% | 1 | 1 | 0% | 1,714 | 1,613 | -6% | 0 | 0 | — |
case-08 | pass→pass | 5,235 | 3,996 | -24% | 1 | 1 | 0% | 974 | 1,468 | +51% | 0 | 0 | — |
case-09 | fail→fail | 5,837 | 2,152 | -63% | 1 | 1 | 0% | 1,007 | 1,067 | +6% | 0 | 0 | — |
case-10 | fail→pass | 8,534 | 4,584 | -46% | 1 | 1 | 0% | 1,675 | 1,365 | -19% | 0 | 0 | — |
case-11 | pass→pass | 9,091 | 3,552 | -61% | 1 | 1 | 0% | 1,699 | 1,416 | -17% | 0 | 0 | — |
case-12 | pass→pass | 6,426 | 4,385 | -32% | 1 | 1 | 0% | 1,008 | 1,083 | +7% | 0 | 0 | — |
case-13 | fail→pass | 14,616 | 2,876 | -80% | 1 | 1 | 0% | 2,501 | 1,188 | -52% | 0 | 0 | — |
case-14 | pass→pass | 8,388 | 3,812 | -55% | 1 | 1 | 0% | 1,641 | 1,426 | -13% | 0 | 0 | — |
case-15 | fail→pass | 11,120 | 4,784 | -57% | 1 | 1 | 0% | 2,333 | 1,700 | -27% | 0 | 0 | — |
case-16 | fail→pass | 9,318 | 2,933 | -69% | 1 | 1 | 0% | 1,975 | 1,212 | -39% | 0 | 0 | — |
case-17 | fail→pass | 13,891 | 3,458 | -75% | 1 | 1 | 0% | 2,536 | 1,231 | -51% | 0 | 0 | — |
case-18 | fail→pass | 7,458 | 3,101 | -58% | 1 | 1 | 0% | 1,226 | 1,212 | -1% | 0 | 0 | — |
case-19 | pass→pass | 8,569 | 2,331 | -73% | 1 | 1 | 0% | 1,530 | 1,124 | -27% | 0 | 0 | — |
case-20 | pass→pass | 9,269 | 7,372 | -20% | 1 | 1 | 0% | 1,840 | 2,117 | +15% | 0 | 0 | — |
case-21 | pass→pass | 13,658 | 8,228 | -40% | 1 | 1 | 0% | 2,282 | 2,172 | -5% | 0 | 0 | — |
case-22 | pass→pass | 10,366 | 5,410 | -48% | 1 | 1 | 0% | 1,986 | 1,686 | -15% | 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 +45 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.