Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cursor rules for TypeScript, React, Node.js, clean architecture, testing, and WHY-oriented engineering guidance.
.claude/skills/amariahak-cursor-rules-for-typescript-react-node/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | -9% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 15% | 0% |
| case-21 | ✗→✓ | ▲ Improved | -12% | 0% |
Cursor rules for TypeScript, React, Node.js, clean architecture, testing, and WHY-oriented engineering guidance.
Synced from https://github.com/PatrickJS/awesome-cursorrules/tree/main/rules/ai-agent-specialist.mdc.
You are a senior full-stack developer specializing in TypeScript, React, and Node.js. Every rule includes a WHY explanation for the reasoning behind it.
any. Use unknown for dynamic data.> WHY: Type safety prevents runtime errors and improves developer experience.
> WHY: Improves testability, readability, and makes code review easier.
> WHY: Consistent with TypeScript ecosystem standards.
> WHY: Interfaces are extendable and produce better error messages.
> WHY: Testable business logic that survives framework changes.
> WHY: Decouples persistence from domain, enables testing with in-memory implementations.
> WHY: Lighter weight, better TypeScript support, less boilerplate.
> WHY: Clear intent — callers know which errors to catch vs handle.
> WHY: Observability without security risk. Structured logs enable alerting.
> WHY: Factory functions are maintainable and composable. Fixtures become stale.
> WHY: Tests should reflect reality. Over-mocking hides real bugs.
> WHY: Runtime validation catches what TypeScript can't — malformed external data.
> WHY: Defense in depth against abuse and common web vulnerabilities.
> WHY: Small PRs get reviewed faster and have fewer bugs.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-20 | pass→pass | 13,455 | 11,585 | -14% | 1 | 1 | 0% | 2,865 | 2,619 | -9% | 0 | 0 | — |
case-01 | fail→fail | 16,434 | 9,765 | -41% | 1 | 1 | 0% | 3,751 | 2,757 | -26% | 0 | 0 | — |
case-02 | fail→pass | 22,001 | 16,606 | -25% | 1 | 1 | 0% | 4,841 | 4,415 | -9% | 0 | 0 | — |
case-03 | fail→pass | 18,391 | 18,035 | -2% | 1 | 1 | 0% | 4,093 | 4,456 | +9% | 0 | 0 | — |
case-04 | pass→pass | 8,713 | 7,624 | -12% | 1 | 1 | 0% | 1,875 | 2,195 | +17% | 0 | 0 | — |
case-05 | pass→pass | 6,764 | 7,057 | +4% | 1 | 1 | 0% | 1,221 | 1,978 | +62% | 0 | 0 | — |
case-06 | pass→pass | 4,447 | 4,153 | -7% | 1 | 1 | 0% | 894 | 1,361 | +52% | 0 | 0 | — |
case-07 | pass→pass | 12,702 | 7,680 | -40% | 1 | 1 | 0% | 2,616 | 2,060 | -21% | 0 | 0 | — |
case-08 | fail→pass | 13,796 | 10,845 | -21% | 1 | 1 | 0% | 3,033 | 3,164 | +4% | 0 | 0 | — |
case-09 | pass→pass | 16,963 | 8,893 | -48% | 1 | 1 | 0% | 3,017 | 2,498 | -17% | 0 | 0 | — |
case-10 | pass→pass | 13,034 | 11,311 | -13% | 1 | 1 | 0% | 2,774 | 3,080 | +11% | 0 | 0 | — |
case-11 | pass→pass | 15,881 | 15,032 | -5% | 1 | 1 | 0% | 3,232 | 4,232 | +31% | 0 | 0 | — |
case-12 | pass→pass | 16,833 | 14,991 | -11% | 1 | 1 | 0% | 3,490 | 3,773 | +8% | 0 | 0 | — |
case-13 | pass→pass | 18,039 | 14,292 | -21% | 1 | 1 | 0% | 3,880 | 3,866 | -0% | 0 | 0 | — |
case-14 | pass→pass | 21,685 | 10,102 | -53% | 1 | 1 | 0% | 3,544 | 2,583 | -27% | 0 | 0 | — |
case-15 | pass→pass | 14,553 | 12,983 | -11% | 1 | 1 | 0% | 3,125 | 3,311 | +6% | 0 | 0 | — |
case-16 | fail→fail | 17,764 | 18,740 | +5% | 1 | 1 | 0% | 3,601 | 5,149 | +43% | 0 | 0 | — |
case-17 | pass→pass | 13,609 | 10,836 | -20% | 1 | 1 | 0% | 2,819 | 3,163 | +12% | 0 | 0 | — |
case-18 | pass→pass | 15,922 | 20,390 | +28% | 1 | 1 | 0% | 3,531 | 3,866 | +9% | 0 | 0 | — |
case-19 | fail→pass | 16,152 | 14,262 | -12% | 1 | 1 | 0% | 3,410 | 3,930 | +15% | 0 | 0 | — |
case-21 | fail→pass | 18,798 | 13,848 | -26% | 1 | 1 | 0% | 4,015 | 3,548 | -12% | 0 | 0 | — |
case-22 | pass→pass | 10,063 | 7,383 | -27% | 1 | 1 | 0% | 2,093 | 1,996 | -5% | 0 | 0 | — |
case-23 | fail→pass | 17,834 | 12,184 | -32% | 1 | 1 | 0% | 3,017 | 2,719 | -10% | 0 | 0 | — |
case-24 | pass→pass | 17,044 | 17,187 | +1% | 1 | 1 | 0% | 3,352 | 4,263 | +27% | 0 | 0 | — |
case-25 | fail→pass | 9,718 | 11,543 | +19% | 1 | 1 | 0% | 2,104 | 3,041 | +45% | 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. 25 cases were attempted. The headline lift of +28 percentage points is the difference between those two pass rates over the 25 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.