Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create Zustand stores following established patterns with proper TypeScript types and middleware.
.claude/skills/lingxling-zustand-store-ts/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -9% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -17% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -51% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -44% | 0% |
Create Zustand stores following established patterns with proper TypeScript types and middleware.
Copy the template from assets/template.ts and replace placeholders:
{{StoreName}} → PascalCase store name (e.g., Project){{description}} → Brief description for JSDoctypescriptimport { create } from 'zustand'; import { subscribeWithSelector } from 'zustand/middleware'; export const useMyStore = create<MyStore>()( subscribeWithSelector((set, get) => ({ // state and actions })) );
typescriptexport interface MyState { items: Item[]; isLoading: boolean; } export interface MyActions { addItem: (item: Item) => void; loadItems: () => Promise<void>; } export type MyStore = MyState & MyActions;
typescript// Good - only re-renders when `items` changes const items = useMyStore((state) => state.items); // Avoid - re-renders on any state change const { items, isLoading } = useMyStore();
typescriptuseMyStore.subscribe( (state) => state.selectedId, (selectedId) => console.log('Selected:', selectedId) );
src/frontend/src/store/src/frontend/src/store/index.tssrc/frontend/src/store/*.test.tsThis skill is applicable to execute the workflow or actions described in the overview.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 11,624 | 9,961 | -14% | 1 | 1 | 0% | 2,354 | 2,141 | -9% | 0 | 0 | — |
case-02 | fail→pass | 21,022 | 15,297 | -27% | 1 | 1 | 0% | 3,329 | 3,532 | +6% | 0 | 0 | — |
case-03 | fail→pass | 24,233 | 13,690 | -44% | 1 | 1 | 0% | 3,851 | 3,209 | -17% | 0 | 0 | — |
case-04 | pass→pass | 10,629 | 10,024 | -6% | 1 | 1 | 0% | 1,867 | 1,885 | +1% | 0 | 0 | — |
case-05 | fail→pass | 12,979 | 2,479 | -81% | 1 | 1 | 0% | 1,758 | 862 | -51% | 0 | 0 | — |
case-06 | pass→pass | 10,579 | 6,278 | -41% | 1 | 1 | 0% | 1,893 | 1,820 | -4% | 0 | 0 | — |
case-07 | pass→pass | 13,672 | 5,962 | -56% | 1 | 1 | 0% | 1,941 | 1,481 | -24% | 0 | 0 | — |
case-08 | fail→pass | 20,921 | 3,368 | -84% | 1 | 1 | 0% | 1,844 | 1,037 | -44% | 0 | 0 | — |
case-09 | pass→pass | 5,167 | 3,023 | -41% | 1 | 1 | 0% | 822 | 831 | +1% | 0 | 0 | — |
case-10 | fail→pass | 11,417 | 2,091 | -82% | 1 | 1 | 0% | 1,894 | 788 | -58% | 0 | 0 | — |
case-11 | pass→fail | 13,387 | 2,592 | -81% | 1 | 1 | 0% | 1,917 | 780 | -59% | 0 | 0 | — |
case-12 | fail→pass | 13,444 | 16,964 | +26% | 1 | 1 | 0% | 2,716 | 3,332 | +23% | 0 | 0 | — |
case-13 | pass→pass | 12,041 | 9,050 | -25% | 1 | 1 | 0% | 2,246 | 2,081 | -7% | 0 | 0 | — |
case-14 | pass→pass | 11,928 | 8,682 | -27% | 1 | 1 | 0% | 2,124 | 1,643 | -23% | 0 | 0 | — |
case-15 | fail→pass | 15,923 | 19,290 | +21% | 1 | 1 | 0% | 3,232 | 3,402 | +5% | 0 | 0 | — |
case-16 | pass→pass | 23,154 | 6,827 | -71% | 1 | 1 | 0% | 2,817 | 1,430 | -49% | 0 | 0 | — |
case-17 | fail→pass | 21,859 | 21,603 | -1% | 1 | 1 | 0% | 4,798 | 5,437 | +13% | 0 | 0 | — |
case-18 | pass→pass | 18,219 | 9,487 | -48% | 1 | 1 | 0% | 2,000 | 1,924 | -4% | 0 | 0 | — |
case-19 | fail→pass | 15,992 | 13,697 | -14% | 1 | 1 | 0% | 3,283 | 2,764 | -16% | 0 | 0 | — |
case-20 | fail→pass | 10,635 | 9,775 | -8% | 1 | 1 | 0% | 2,174 | 2,537 | +17% | 0 | 0 | — |
case-21 | pass→pass | 23,566 | 21,455 | -9% | 1 | 1 | 0% | 3,760 | 3,970 | +6% | 0 | 0 | — |
case-22 | pass→pass | 10,439 | 8,898 | -15% | 1 | 1 | 0% | 1,931 | 2,141 | +11% | 0 | 0 | — |
case-23 | pass→pass | 12,960 | 11,292 | -13% | 1 | 1 | 0% | 2,593 | 2,875 | +11% | 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 +43 percentage points is the difference between those two pass rates over the 23 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.