Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cursor rules for JavaScript development with Astro and Tailwind CSS integration.
.claude/skills/amariahak-cursor-rules-for-javascript-development-with-astro-and-tailwind-css-integration/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-22 | ✓→✗ | ▼ Worse | 66% | 0% |
| case-04 | ✓→✓ | = Same ✓ | 35% | 0% |
| case-05 | ✓→✓ | = Same ✓ | 140% | 0% |
| case-06 | ✓→✓ | = Same ✓ | 58% | 0% |
Cursor rules for JavaScript development with Astro and Tailwind CSS integration.
Synced from https://github.com/PatrickJS/awesome-cursorrules/tree/main/rules/javascript-astro-tailwind-css-cursorrules-prompt-f.mdc.
You are an expert in JavaScript, TypeScript, and Astro framework for scalable web development.
Key Principles
Astro Project Structure
Component Development
Routing and Pages
Content Management
Styling
Performance Optimization
Data Fetching
SEO and Meta Tags
Integrations and Plugins
Build and Deployment
Styling with Tailwind CSS
Tailwind CSS Best Practices
Testing
Accessibility
Key Conventions
Performance Metrics
Refer to Astro's official documentation for detailed information on components, routing, and integrations for best practices.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 23,623 | 27,334 | +16% | 1 | 1 | 0% | 5,445 | 5,691 | +5% | 0 | 0 | — |
case-02 | fail→fail | 31,784 | 18,030 | -43% | 1 | 1 | 0% | 4,182 | 5,033 | +20% | 0 | 0 | — |
case-03 | fail→pass | 12,986 | 14,903 | +15% | 1 | 1 | 0% | 2,703 | 2,868 | +6% | 0 | 0 | — |
case-04 | pass→pass | 9,653 | 7,535 | -22% | 1 | 1 | 0% | 1,840 | 2,483 | +35% | 0 | 0 | — |
case-05 | pass→pass | 4,253 | 3,997 | -6% | 1 | 1 | 0% | 725 | 1,743 | +140% | 0 | 0 | — |
case-06 | pass→pass | 6,550 | 3,511 | -46% | 1 | 1 | 0% | 1,034 | 1,636 | +58% | 0 | 0 | — |
case-07 | pass→pass | 4,831 | 4,580 | -5% | 1 | 1 | 0% | 866 | 1,738 | +101% | 0 | 0 | — |
case-08 | pass→pass | 4,198 | 3,252 | -23% | 1 | 1 | 0% | 801 | 1,657 | +107% | 0 | 0 | — |
case-09 | pass→pass | 4,014 | 3,388 | -16% | 1 | 1 | 0% | 682 | 1,599 | +134% | 0 | 0 | — |
case-10 | pass→pass | 13,366 | 9,572 | -28% | 1 | 1 | 0% | 2,552 | 3,112 | +22% | 0 | 0 | — |
case-11 | pass→pass | 7,192 | 5,590 | -22% | 1 | 1 | 0% | 1,583 | 2,094 | +32% | 0 | 0 | — |
case-12 | pass→pass | 10,939 | 8,961 | -18% | 1 | 1 | 0% | 2,113 | 2,865 | +36% | 0 | 0 | — |
case-13 | pass→pass | 7,032 | 4,695 | -33% | 1 | 1 | 0% | 1,312 | 1,939 | +48% | 0 | 0 | — |
case-14 | pass→pass | 16,044 | 7,451 | -54% | 1 | 1 | 0% | 2,443 | 2,509 | +3% | 0 | 0 | — |
case-15 | pass→pass | 8,885 | 5,638 | -37% | 1 | 1 | 0% | 2,004 | 2,226 | +11% | 0 | 0 | — |
case-16 | pass→pass | 8,193 | 4,438 | -46% | 1 | 1 | 0% | 1,065 | 1,874 | +76% | 0 | 0 | — |
case-17 | pass→pass | 8,236 | 6,028 | -27% | 1 | 1 | 0% | 1,761 | 2,247 | +28% | 0 | 0 | — |
case-18 | pass→pass | 10,279 | 6,740 | -34% | 1 | 1 | 0% | 1,988 | 2,385 | +20% | 0 | 0 | — |
case-19 | pass→pass | 5,946 | 5,029 | -15% | 1 | 1 | 0% | 1,066 | 2,067 | +94% | 0 | 0 | — |
case-20 | pass→pass | 10,736 | 7,643 | -29% | 1 | 1 | 0% | 2,079 | 2,646 | +27% | 0 | 0 | — |
case-21 | pass→pass | 7,704 | 6,475 | -16% | 1 | 1 | 0% | 1,488 | 2,323 | +56% | 0 | 0 | — |
case-22 | pass→fail | 7,435 | 10,835 | +46% | 1 | 1 | 0% | 1,423 | 2,360 | +66% | 0 | 0 | — |
case-23 | pass→pass | 6,134 | 4,792 | -22% | 1 | 1 | 0% | 1,144 | 2,039 | +78% | 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 0 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.