Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cursor rules for HTML development with Tailwind CSS and JavaScript integration.
.claude/skills/amariahak-cursor-rules-for-html-development-with-tailwind-css-and-javascript-integration/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 193% | 0% |
| case-03 | ✓→✗ | ▼ Worse | 26% | 0% |
| case-04 | ✓→✗ | ▼ Worse | -51% | 0% |
| case-19 | ✓→✗ | ▼ Worse | -25% | 0% |
| case-07 | ✓→✓ | ＝ Same ✓ | 4% | 0% |
Cursor rules for HTML development with Tailwind CSS and JavaScript integration.
Synced from https://github.com/PatrickJS/awesome-cursorrules/tree/main/rules/html-tailwind-css-javascript-cursorrules-prompt-fi.mdc.
You are an expert AI programming assistant that primarily focuses on producing clear, readable HTML, Tailwind CSS and vanilla JavaScript code.
You always use the latest version of HTML, Tailwind CSS and vanilla JavaScript, and you are familiar with the latest features and best practices.
You carefully provide accurate, factual, thoughtful answers, and excel at reasoning.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 15,338 | 14,111 | -8% | 1 | 1 | 0% | 3,557 | 3,827 | +8% | 0 | 0 | — |
case-02 | fail→fail | 11,865 | 6,564 | -45% | 1 | 1 | 0% | 2,541 | 1,800 | -29% | 0 | 0 | — |
case-03 | pass→fail | 19,651 | 20,078 | +2% | 1 | 1 | 0% | 4,214 | 5,318 | +26% | 0 | 0 | — |
case-04 | pass→fail | 18,010 | 7,430 | -59% | 1 | 1 | 0% | 2,883 | 1,421 | -51% | 0 | 0 | — |
case-05 | fail→pass | 5,139 | 10,727 | +109% | 1 | 1 | 0% | 907 | 2,658 | +193% | 0 | 0 | — |
case-06 | fail→fail | 4,981 | 3,138 | -37% | 1 | 1 | 0% | 957 | 912 | -5% | 0 | 0 | — |
case-07 | pass→pass | 6,636 | 5,144 | -22% | 1 | 1 | 0% | 1,051 | 1,088 | +4% | 0 | 0 | — |
case-08 | pass→pass | 21,008 | 11,672 | -44% | 1 | 1 | 0% | 4,252 | 2,683 | -37% | 0 | 0 | — |
case-09 | pass→pass | 15,914 | 16,272 | +2% | 1 | 1 | 0% | 3,086 | 2,495 | -19% | 0 | 0 | — |
case-10 | pass→pass | 18,053 | 13,203 | -27% | 1 | 1 | 0% | 3,033 | 2,581 | -15% | 0 | 0 | — |
case-11 | pass→pass | 8,358 | 3,835 | -54% | 1 | 1 | 0% | 1,285 | 908 | -29% | 0 | 0 | — |
case-12 | pass→pass | 15,511 | 9,045 | -42% | 1 | 1 | 0% | 3,138 | 2,090 | -33% | 0 | 0 | — |
case-13 | pass→pass | 16,327 | 8,795 | -46% | 1 | 1 | 0% | 2,522 | 2,074 | -18% | 0 | 0 | — |
case-14 | pass→pass | 18,053 | 15,448 | -14% | 1 | 1 | 0% | 3,894 | 4,167 | +7% | 0 | 0 | — |
case-15 | pass→pass | 19,472 | 14,067 | -28% | 1 | 1 | 0% | 4,627 | 3,479 | -25% | 0 | 0 | — |
case-16 | fail→fail | 4,130 | 3,414 | -17% | 1 | 1 | 0% | 579 | 967 | +67% | 0 | 0 | — |
case-17 | pass→pass | 14,158 | 8,301 | -41% | 1 | 1 | 0% | 2,916 | 2,176 | -25% | 0 | 0 | — |
case-18 | pass→pass | 15,096 | 9,755 | -35% | 1 | 1 | 0% | 3,170 | 2,358 | -26% | 0 | 0 | — |
case-19 | pass→fail | 28,100 | 19,388 | -31% | 1 | 1 | 0% | 6,166 | 4,608 | -25% | 0 | 0 | — |
case-20 | pass→pass | 9,497 | 9,437 | -1% | 1 | 1 | 0% | 2,134 | 2,401 | +13% | 0 | 0 | — |
case-21 | pass→pass | 18,315 | 11,702 | -36% | 1 | 1 | 0% | 4,093 | 2,877 | -30% | 0 | 0 | — |
case-22 | fail→fail | 14,187 | 6,457 | -54% | 1 | 1 | 0% | 3,106 | 1,637 | -47% | 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 -50 percentage points is the difference between those two pass rates over the 22 comparable cases. 3 cases got worse with the skill loaded, and they are 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.