Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cursor rules for HTMX development with basic setup.
.claude/skills/amariahak-cursor-rules-for-htmx-development-with-basic-setup/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -38% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 11% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -21% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -68% | 0% |
| case-21 | ✗→✓ | ▲ Improved | -56% | 0% |
Cursor rules for HTMX development with basic setup.
Synced from https://github.com/PatrickJS/awesome-cursorrules/tree/main/rules/htmx-basic-cursorrules-prompt-file.mdc.
// HTMX Basic Setup .cursorrules
// HTMX best practices
const htmxBestPractices = "Use hx-get for GET requests", "Implement hx-post for POST requests", "Utilize hx-trigger for custom events", "Use hx-swap to control how content is swapped", "Implement hx-target to specify where to swap content", "Utilize hx-indicator for loading indicators", ];
// Folder structure
const folderStructure = src/ templates/ static/ css/ js/ app.py ;
// Additional instructions
const additionalInstructions =
;
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 18,259 | 7,968 | -56% | 1 | 1 | 0% | 3,234 | 1,991 | -38% | 0 | 0 | — |
case-02 | fail→pass | 13,529 | 17,094 | +26% | 1 | 1 | 0% | 2,628 | 2,915 | +11% | 0 | 0 | — |
case-03 | fail→pass | 18,931 | 12,707 | -33% | 1 | 1 | 0% | 3,357 | 2,637 | -21% | 0 | 0 | — |
case-04 | pass→pass | 11,257 | 6,721 | -40% | 1 | 1 | 0% | 2,238 | 1,648 | -26% | 0 | 0 | — |
case-05 | pass→pass | 13,698 | 7,291 | -47% | 1 | 1 | 0% | 2,562 | 1,694 | -34% | 0 | 0 | — |
case-06 | pass→pass | 11,853 | 7,833 | -34% | 1 | 1 | 0% | 2,155 | 1,748 | -19% | 0 | 0 | — |
case-07 | fail→pass | 14,671 | 3,213 | -78% | 1 | 1 | 0% | 2,700 | 870 | -68% | 0 | 0 | — |
case-08 | pass→pass | 3,943 | 2,575 | -35% | 1 | 1 | 0% | 680 | 720 | +6% | 0 | 0 | — |
case-09 | pass→pass | 2,444 | 2,744 | +12% | 1 | 1 | 0% | 423 | 756 | +79% | 0 | 0 | — |
case-10 | pass→pass | 3,314 | 3,229 | -3% | 1 | 1 | 0% | 585 | 829 | +42% | 0 | 0 | — |
case-11 | pass→pass | 8,949 | 6,416 | -28% | 1 | 1 | 0% | 1,753 | 1,481 | -16% | 0 | 0 | — |
case-12 | pass→pass | 3,466 | 3,137 | -9% | 1 | 1 | 0% | 572 | 854 | +49% | 0 | 0 | — |
case-13 | pass→pass | 9,356 | 5,582 | -40% | 1 | 1 | 0% | 1,729 | 1,322 | -24% | 0 | 0 | — |
case-14 | pass→pass | 5,741 | 4,862 | -15% | 1 | 1 | 0% | 951 | 1,062 | +12% | 0 | 0 | — |
case-15 | pass→pass | 6,786 | 3,806 | -44% | 1 | 1 | 0% | 1,049 | 877 | -16% | 0 | 0 | — |
case-16 | pass→pass | 14,235 | 8,055 | -43% | 1 | 1 | 0% | 2,412 | 1,688 | -30% | 0 | 0 | — |
case-17 | pass→pass | 7,968 | 5,177 | -35% | 1 | 1 | 0% | 1,402 | 1,152 | -18% | 0 | 0 | — |
case-18 | pass→pass | 17,511 | 13,411 | -23% | 1 | 1 | 0% | 3,019 | 2,608 | -14% | 0 | 0 | — |
case-19 | pass→pass | 15,220 | 12,175 | -20% | 1 | 1 | 0% | 2,695 | 2,637 | -2% | 0 | 0 | — |
case-20 | pass→pass | 7,608 | 5,715 | -25% | 1 | 1 | 0% | 1,157 | 1,237 | +7% | 0 | 0 | — |
case-21 | fail→pass | 10,649 | 3,772 | -65% | 1 | 1 | 0% | 2,023 | 890 | -56% | 0 | 0 | — |
case-22 | pass→pass | 6,300 | 5,214 | -17% | 1 | 1 | 0% | 1,095 | 1,264 | +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 +23 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.