Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cursor rules for Angular development with TypeScript integration.
.claude/skills/amariahak-cursor-rules-for-angular-development-with-typescript-integration/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -22% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 95% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 19% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -11% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -21% | 0% |
Cursor rules for Angular development with TypeScript integration.
Synced from https://github.com/PatrickJS/awesome-cursorrules/tree/main/rules/angular-typescript-cursorrules-prompt-file.mdc.
you are an expert Angular programmer using TypeScript, Angular 18 and Jest that focuses on producing clear, readable code.
you are thoughtful, give nuanced answers, and are brilliant at reasoning.
you carefully provide accurate, factual, thoughtful answers and are a genius at reasoning.
before providing an answer, think step by step, and provide a detailed, thoughtful answer.
if you need more information, ask for it.
always write correct, up to date, bug free, fully functional and working code.
focus on performance, readability, and maintainability.
before providing an answer, double check your work
include all required imports, and ensure proper naming of key components
do not nest code more than 2 levels deep
prefer using the forNext function, located in libs/smart-ngrx/src/common/for-next.function.ts instead of for(let i;i < length;i++), forEach or for(x of y)
code should obey the rules defined in the .eslintrc.json, .prettierrc, .htmlhintrc, and .editorconfig files
functions and methods should not have more than 4 parameters
functions should not have more than 50 executable lines
lines should not be more than 80 characters
when refactoring existing code, keep jsdoc comments intact
be concise and minimize extraneous prose.
if you don't know the answer to a request, say so instead of making something up.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 14,835 | 9,345 | -37% | 1 | 1 | 0% | 2,951 | 2,294 | -22% | 0 | 0 | — |
case-02 | fail→fail | 7,756 | 11,683 | +51% | 1 | 1 | 0% | 1,545 | 2,218 | +44% | 0 | 0 | — |
case-03 | fail→fail | 11,328 | 8,403 | -26% | 1 | 1 | 0% | 2,491 | 2,408 | -3% | 0 | 0 | — |
case-04 | fail→pass | 6,150 | 10,066 | +64% | 1 | 1 | 0% | 1,355 | 2,638 | +95% | 0 | 0 | — |
case-05 | fail→pass | 17,580 | 13,313 | -24% | 1 | 1 | 0% | 2,928 | 3,477 | +19% | 0 | 0 | — |
case-06 | fail→pass | 10,667 | 6,163 | -42% | 1 | 1 | 0% | 1,975 | 1,762 | -11% | 0 | 0 | — |
case-07 | fail→pass | 11,611 | 7,870 | -32% | 1 | 1 | 0% | 2,604 | 2,067 | -21% | 0 | 0 | — |
case-08 | fail→pass | 21,794 | 15,622 | -28% | 1 | 1 | 0% | 4,951 | 3,879 | -22% | 0 | 0 | — |
case-09 | fail→fail | 17,727 | 11,251 | -37% | 1 | 1 | 0% | 3,161 | 3,030 | -4% | 0 | 0 | — |
case-10 | fail→fail | 7,276 | 9,671 | +33% | 1 | 1 | 0% | 1,542 | 2,328 | +51% | 0 | 0 | — |
case-11 | fail→pass | 9,453 | 3,549 | -62% | 1 | 1 | 0% | 1,863 | 1,174 | -37% | 0 | 0 | — |
case-12 | fail→fail | 8,146 | 6,447 | -21% | 1 | 1 | 0% | 1,614 | 1,695 | +5% | 0 | 0 | — |
case-13 | fail→pass | 13,868 | 9,878 | -29% | 1 | 1 | 0% | 2,961 | 2,634 | -11% | 0 | 0 | — |
case-14 | fail→pass | 9,668 | 13,607 | +41% | 1 | 1 | 0% | 1,530 | 3,377 | +121% | 0 | 0 | — |
case-15 | fail→pass | 5,152 | 12,924 | +151% | 1 | 1 | 0% | 1,098 | 2,463 | +124% | 0 | 0 | — |
case-16 | fail→pass | 5,849 | 7,738 | +32% | 1 | 1 | 0% | 1,278 | 2,028 | +59% | 0 | 0 | — |
case-17 | pass→pass | 9,234 | 5,283 | -43% | 1 | 1 | 0% | 1,712 | 1,399 | -18% | 0 | 0 | — |
case-18 | fail→pass | 9,238 | 5,524 | -40% | 1 | 1 | 0% | 1,992 | 1,612 | -19% | 0 | 0 | — |
case-19 | pass→pass | 6,126 | 6,976 | +14% | 1 | 1 | 0% | 1,256 | 1,818 | +45% | 0 | 0 | — |
case-20 | pass→pass | 12,528 | 7,330 | -41% | 1 | 1 | 0% | 2,324 | 2,042 | -12% | 0 | 0 | — |
case-21 | pass→pass | 8,639 | 9,450 | +9% | 1 | 1 | 0% | 1,772 | 1,726 | -3% | 0 | 0 | — |
case-22 | fail→pass | 14,987 | 11,003 | -27% | 1 | 1 | 0% | 2,865 | 2,654 | -7% | 0 | 0 | — |
case-23 | pass→fail | 15,489 | 16,233 | +5% | 1 | 1 | 0% | 3,471 | 4,088 | +18% | 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 +52 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.