Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cursor rules for Aspnet Abp.
.claude/skills/amariahak-cursor-rules-for-aspnet-abp/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 33% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 49% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 66% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 66% | 0% |
Cursor rules for Aspnet Abp.
Synced from https://github.com/PatrickJS/awesome-cursorrules/tree/main/rules/aspnet-abp-cursorrules-prompt-file.mdc.
You are a senior .NET backend developer and an expert in C#, ASP.NET Core, ABP Framework, and Entity Framework Core.
IsUserSignedIn, CalculateTotal).IUserService).DbContext and repository abstractions.var for implicit typing when the type is obvious.HttpApi controllers.HttpApi layer.async/await for I/O-bound operations.IDistributedCache for caching strategies (instead of IMemoryCache), in line with ABP’s caching abstractions.PagedResultDto for large data sets in your application service methods.IHostedService/BackgroundService where appropriate.AuditedAggregateRoot, FullAuditedEntity).DomainService.Domain Best Practices
Application Layer Best Practices
Data Access Best Practices
Additionally, refer to the EventHub repository for various examples and best practices beyond testing.
Application.Tests, Domain.Tests), leveraging ABP’s test base classes.Adhere to official Microsoft documentation, ASP.NET Core guides, and ABP’s documentation (https://docs.abp.io) for best practices in routing, domain-driven design, controllers, modules, and other ABP components.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 19,951 | 12,586 | -37% | 1 | 1 | 0% | 3,967 | 4,135 | +4% | 0 | 0 | — |
case-02 | fail→pass | 12,435 | 9,204 | -26% | 1 | 1 | 0% | 2,509 | 3,339 | +33% | 0 | 0 | — |
case-03 | fail→fail | 12,335 | 11,455 | -7% | 1 | 1 | 0% | 2,784 | 4,134 | +48% | 0 | 0 | — |
case-04 | pass→pass | 11,445 | 9,181 | -20% | 1 | 1 | 0% | 2,216 | 3,294 | +49% | 0 | 0 | — |
case-05 | pass→pass | 11,127 | 6,546 | -41% | 1 | 1 | 0% | 2,168 | 2,726 | +26% | 0 | 0 | — |
case-06 | pass→pass | 15,264 | 13,731 | -10% | 1 | 1 | 0% | 3,137 | 4,128 | +32% | 0 | 0 | — |
case-07 | fail→fail | 11,566 | 10,121 | -12% | 1 | 1 | 0% | 2,175 | 3,600 | +66% | 0 | 0 | — |
case-08 | fail→pass | 12,771 | 7,354 | -42% | 1 | 1 | 0% | 1,962 | 2,922 | +49% | 0 | 0 | — |
case-09 | fail→pass | 13,283 | 14,833 | +12% | 1 | 1 | 0% | 2,681 | 4,452 | +66% | 0 | 0 | — |
case-10 | pass→pass | 13,525 | 8,792 | -35% | 1 | 1 | 0% | 2,691 | 3,199 | +19% | 0 | 0 | — |
case-11 | pass→pass | 9,993 | 9,980 | -0% | 1 | 1 | 0% | 2,079 | 3,464 | +67% | 0 | 0 | — |
case-12 | fail→pass | 11,345 | 10,308 | -9% | 1 | 1 | 0% | 1,973 | 3,269 | +66% | 0 | 0 | — |
case-13 | pass→pass | 12,965 | 12,818 | -1% | 1 | 1 | 0% | 2,471 | 3,006 | +22% | 0 | 0 | — |
case-14 | pass→pass | 10,246 | 8,850 | -14% | 1 | 1 | 0% | 2,026 | 3,273 | +62% | 0 | 0 | — |
case-15 | fail→pass | 10,223 | 9,606 | -6% | 1 | 1 | 0% | 1,855 | 2,956 | +59% | 0 | 0 | — |
case-16 | fail→pass | 12,254 | 10,987 | -10% | 1 | 1 | 0% | 2,354 | 3,781 | +61% | 0 | 0 | — |
case-17 | fail→pass | 12,349 | 6,561 | -47% | 1 | 1 | 0% | 2,293 | 2,649 | +16% | 0 | 0 | — |
case-18 | fail→pass | 12,065 | 11,086 | -8% | 1 | 1 | 0% | 2,255 | 3,658 | +62% | 0 | 0 | — |
case-19 | fail→pass | 12,876 | 11,973 | -7% | 1 | 1 | 0% | 2,672 | 3,764 | +41% | 0 | 0 | — |
case-20 | pass→pass | 14,446 | 10,759 | -26% | 1 | 1 | 0% | 2,917 | 3,568 | +22% | 0 | 0 | — |
case-21 | pass→pass | 7,369 | 7,721 | +5% | 1 | 1 | 0% | 1,449 | 3,044 | +110% | 0 | 0 | — |
case-22 | pass→pass | 11,840 | 9,816 | -17% | 1 | 1 | 0% | 2,863 | 3,633 | +27% | 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 +45 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.