Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate React components with TypeScript, proper props, hooks, and accessibility. Use when creating new React components, UI elements, or refactoring existing components.
.claude/skills/onewave-ai-react-component-generator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | -11% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 0% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 21% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 1% | 0% |
When creating React components:
tsx'use client'; import { useState, useCallback } from 'react'; import { cn } from '@/lib/utils'; interface ButtonProps extends React.ButtonHTMLAttributes<HTMLButtonElement> { variant?: 'primary' | 'secondary' | 'ghost'; size?: 'sm' | 'md' | 'lg'; isLoading?: boolean; children: React.ReactNode; } export function Button({ variant = 'primary', size = 'md', isLoading = false, children, className, disabled, ...props }: ButtonProps) { const baseStyles = 'inline-flex items-center justify-center rounded-md font-medium transition-colors focus-visible:outline-none focus-visible:ring-2'; const variants = { primary: 'bg-blue-600 text-white hover:bg-blue-700', secondary: 'bg-gray-200 text-gray-900 hover:bg-gray-300', ghost: 'hover:bg-gray-100', }; const sizes = { sm: 'h-8 px-3 text-sm', md: 'h-10 px-4', lg: 'h-12 px-6 text-lg', }; return ( <button className={cn(baseStyles, variants[variant], sizes[size], className)} disabled={disabled || isLoading} aria-busy={isLoading} {...props} > {isLoading ? <span className="animate-spin mr-2">⏳</span> : null} {children} </button> ); }
tsximport { db } from '@/lib/db'; interface UserListProps { limit?: number; } export async function UserList({ limit = 10 }: UserListProps) { const users = await db.user.findMany({ take: limit }); if (users.length === 0) { return <p className="text-gray-500">No users found.</p>; } return ( <ul role="list" className="divide-y"> {users.map((user) => ( <li key={user.id} className="py-4"> <span>{user.name}</span> </li> ))} </ul> ); }
tsx'use client'; import { useForm } from 'react-hook-form'; import { zodResolver } from '@hookform/resolvers/zod'; import { z } from 'zod'; const schema = z.object({ email: z.string().email('Invalid email'), password: z.string().min(8, 'Min 8 characters'), }); type FormData = z.infer<typeof schema>; export function LoginForm({ onSubmit }: { onSubmit: (data: FormData) => void }) { const { register, handleSubmit, formState: { errors, isSubmitting }, } = useForm<FormData>({ resolver: zodResolver(schema), }); return ( <form onSubmit={handleSubmit(onSubmit)} noValidate> <div> <label htmlFor="email">Email</label> <input id="email" type="email" aria-invalid={!!errors.email} aria-describedby={errors.email ? 'email-error' : undefined} {...register('email')} /> {errors.email && ( <p id="email-error" role="alert">{errors.email.message}</p> )} </div> <button type="submit" disabled={isSubmitting}> {isSubmitting ? 'Loading...' : 'Submit'} </button> </form> ); }
aria-label for icon-only buttonsrole attributes where neededaria-invalid and aria-describedby for form errorsaria-busy for loading states| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | pass→pass | 13,020 | 8,540 | -34% | 1 | 1 | 0% | 2,936 | 3,116 | +6% | 0 | 0 | — |
case-05 | fail→pass | 15,035 | 10,399 | -31% | 1 | 1 | 0% | 3,640 | 3,242 | -11% | 0 | 0 | — |
case-01 | fail→pass | 15,095 | 14,120 | -6% | 1 | 1 | 0% | 3,525 | 3,517 | -0% | 0 | 0 | — |
case-02 | fail→pass | 17,385 | 11,484 | -34% | 1 | 1 | 0% | 4,074 | 3,866 | -5% | 0 | 0 | — |
case-03 | fail→pass | 17,362 | 15,357 | -12% | 1 | 1 | 0% | 4,130 | 5,002 | +21% | 0 | 0 | — |
case-06 | fail→pass | 18,374 | 12,879 | -30% | 1 | 1 | 0% | 4,296 | 4,321 | +1% | 0 | 0 | — |
case-07 | fail→pass | 9,897 | 8,699 | -12% | 1 | 1 | 0% | 2,152 | 3,027 | +41% | 0 | 0 | — |
case-08 | fail→pass | 15,355 | 13,609 | -11% | 1 | 1 | 0% | 3,313 | 3,582 | +8% | 0 | 0 | — |
case-09 | fail→pass | 18,161 | 15,449 | -15% | 1 | 1 | 0% | 3,535 | 4,415 | +25% | 0 | 0 | — |
case-10 | fail→pass | 13,383 | 8,851 | -34% | 1 | 1 | 0% | 2,808 | 2,913 | +4% | 0 | 0 | — |
case-11 | fail→pass | 11,658 | 9,554 | -18% | 1 | 1 | 0% | 2,476 | 3,099 | +25% | 0 | 0 | — |
case-12 | fail→pass | 12,617 | 11,780 | -7% | 1 | 1 | 0% | 2,858 | 3,607 | +26% | 0 | 0 | — |
case-13 | fail→pass | 12,128 | 7,612 | -37% | 1 | 1 | 0% | 2,732 | 2,774 | +2% | 0 | 0 | — |
case-14 | pass→pass | 13,465 | 13,918 | +3% | 1 | 1 | 0% | 2,924 | 4,452 | +52% | 0 | 0 | — |
case-15 | fail→pass | 16,461 | 12,291 | -25% | 1 | 1 | 0% | 3,000 | 3,486 | +16% | 0 | 0 | — |
case-16 | fail→pass | 14,977 | 9,371 | -37% | 1 | 1 | 0% | 2,377 | 2,988 | +26% | 0 | 0 | — |
case-17 | pass→pass | 16,851 | 13,737 | -18% | 1 | 1 | 0% | 3,560 | 3,984 | +12% | 0 | 0 | — |
case-18 | fail→pass | 14,116 | 12,784 | -9% | 1 | 1 | 0% | 3,365 | 4,168 | +24% | 0 | 0 | — |
case-19 | fail→pass | 28,482 | 13,978 | -51% | 1 | 1 | 0% | 4,870 | 4,438 | -9% | 0 | 0 | — |
case-20 | pass→pass | 8,451 | 6,266 | -26% | 1 | 1 | 0% | 1,903 | 2,400 | +26% | 0 | 0 | — |
case-21 | pass→pass | 12,738 | 10,966 | -14% | 1 | 1 | 0% | 2,699 | 3,600 | +33% | 0 | 0 | — |
case-22 | pass→pass | 10,933 | 6,960 | -36% | 1 | 1 | 0% | 2,511 | 2,623 | +4% | 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 +73 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.