Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cursor rules for NativeScript development.
.claude/skills/amariahak-cursor-rules-for-nativescript-development/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 100% | 1 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -34% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -28% | 0% |
| case-18 | ✗→✓ | ▲ Improved | -59% | 0% |
| case-19 | ✗→✓ | ▲ Improved | -44% | 0% |
Cursor rules for NativeScript development.
Synced from https://github.com/PatrickJS/awesome-cursorrules/tree/main/rules/nativescript-cursorrules-prompt-file.mdc.
// NativeScript .cursorrules
// NativeScript best practices
const nativeScriptBestPractices = "Utilize @nativescript/core features and APIs where applicable", "Utilize common web APIs where applicable", "Implement proper navigation using NativeScript Navigation", "Use NativeScript's assets folder for images, sounds or videos and use the fonts folder for custom fonts", "Implement proper error handling where possible" ];
// Folder structure
const folderStructure = src/ assets/ components/ services/ utils/ ;
// 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 | 15,383 | 9,704 | -37% | 1 | 1 | 0% | 2,974 | 1,962 | -34% | 0 | 0 | — |
case-02 | fail→pass | 17,217 | 12,493 | -27% | 1 | 1 | 0% | 3,450 | 2,885 | -16% | 0 | 0 | — |
case-03 | fail→fail | 21,610 | 16,730 | -23% | 1 | 1 | 0% | 3,991 | 3,468 | -13% | 0 | 0 | — |
case-04 | pass→pass | 11,262 | 8,165 | -27% | 1 | 1 | 0% | 2,209 | 1,921 | -13% | 0 | 0 | — |
case-05 | pass→pass | 9,095 | 9,773 | +7% | 1 | 1 | 0% | 1,750 | 1,496 | -15% | 0 | 0 | — |
case-06 | pass→pass | 10,727 | 7,366 | -31% | 1 | 1 | 0% | 2,033 | 1,646 | -19% | 0 | 0 | — |
case-07 | pass→pass | 14,468 | 8,841 | -39% | 1 | 1 | 0% | 2,662 | 1,617 | -39% | 0 | 0 | — |
case-08 | pass→pass | 11,608 | 6,836 | -41% | 1 | 1 | 0% | 2,035 | 1,447 | -29% | 0 | 0 | — |
case-09 | pass→pass | 9,254 | 6,357 | -31% | 1 | 1 | 0% | 1,655 | 1,334 | -19% | 0 | 0 | — |
case-10 | pass→pass | 12,297 | 8,107 | -34% | 1 | 1 | 0% | 2,046 | 1,681 | -18% | 0 | 0 | — |
case-11 | pass→pass | 18,602 | 6,604 | -64% | 1 | 1 | 0% | 1,946 | 1,391 | -29% | 0 | 0 | — |
case-12 | pass→pass | 14,482 | 12,282 | -15% | 1 | 1 | 0% | 2,381 | 2,332 | -2% | 0 | 0 | — |
case-13 | pass→pass | 12,612 | 8,093 | -36% | 1 | 1 | 0% | 1,920 | 1,552 | -19% | 0 | 0 | — |
case-14 | pass→pass | 7,619 | 3,806 | -50% | 1 | 1 | 0% | 1,520 | 966 | -36% | 0 | 0 | — |
case-15 | fail→pass | 6,947 | 3,857 | -44% | 1 | 1 | 0% | 1,290 | 929 | -28% | 0 | 0 | — |
case-16 | pass→pass | 13,585 | 3,597 | -74% | 1 | 1 | 0% | 2,040 | 921 | -55% | 0 | 0 | — |
case-17 | pass→pass | 10,575 | 3,396 | -68% | 1 | 1 | 0% | 1,988 | 824 | -59% | 0 | 0 | — |
case-18 | fail→pass | 23,957 | 4,864 | -80% | 1 | 1 | 0% | 2,671 | 1,095 | -59% | 0 | 0 | — |
case-19 | fail→pass | 9,411 | 4,162 | -56% | 1 | 1 | 0% | 1,646 | 925 | -44% | 0 | 0 | — |
case-20 | pass→pass | 13,050 | 10,551 | -19% | 1 | 1 | 0% | 2,587 | 2,331 | -10% | 0 | 0 | — |
case-21 | pass→pass | 12,384 | 7,577 | -39% | 1 | 1 | 0% | 2,262 | 1,671 | -26% | 0 | 0 | — |
case-22 | pass→pass | 9,870 | 7,111 | -28% | 1 | 1 | 0% | 1,956 | 1,640 | -16% | 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.