Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cursor rules for Nextjs Supabase Shadcn Pwa.
.claude/skills/amariahak-cursor-rules-for-nextjs-supabase-shadcn-pwa/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 53% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 72% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 52% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 13% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 130% | 0% |
Cursor rules for Nextjs Supabase Shadcn Pwa.
Synced from https://github.com/PatrickJS/awesome-cursorrules/tree/main/rules/nextjs-supabase-shadcn-pwa-cursorrules-prompt-file.mdc.
isLoading, hasError).components/auth-wizard).projectContext.md as we need to ensure that the project context is up to date and accurate.npx shadcn@latest add for new components.use client and other client-only APIs.packages/ directory and app-specific code in app/.Taskfile.yml commands for development, testing, and deployment tasks..env files or similar configuration.Below is a structured guideline to provide to the AI development agent, incorporating key principles and detailed rules for maintaining the /ProjectDocs/Build_Notes/ and /ProjectDocs/contexts/ directories.
/ProjectDocs/Build_Notes/.build-title_phase-#_task-group-name.md.<build-title> to describe the build task.<phase-#> to apply the Phase # to the build task.<task-group-name> to describe the task group name.supabase-schema-standardization_phase-1_preparation-and-code-analysis.mdsupabase-schema-standardization is the build titlephase-1 is the phase numberpreparation-and-code-analysis is the task group name/ProjectDocs/Build_Notes/completed/ directory./ProjectDocs/Build_Notes/archived/ directory.projectContext.md):/ProjectDocs/contexts/.uiContext.md, featureAContext.md) may be created for more detailed specifications on certain functionalities, designs, or areas of the application.Adopt a clear, modular directory structure:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 11,713 | 9,052 | -23% | 1 | 1 | 0% | 2,073 | 3,182 | +53% | 0 | 0 | — |
case-02 | fail→fail | 21,915 | 15,250 | -30% | 1 | 1 | 0% | 5,099 | 4,774 | -6% | 0 | 0 | — |
case-03 | fail→pass | 11,132 | 8,961 | -20% | 1 | 1 | 0% | 1,786 | 3,065 | +72% | 0 | 0 | — |
case-04 | pass→pass | 5,310 | 7,230 | +36% | 1 | 1 | 0% | 1,082 | 3,135 | +190% | 0 | 0 | — |
case-05 | pass→pass | 7,706 | 8,292 | +8% | 1 | 1 | 0% | 1,701 | 3,358 | +97% | 0 | 0 | — |
case-06 | pass→pass | 7,542 | 7,550 | +0% | 1 | 1 | 0% | 1,618 | 3,139 | +94% | 0 | 0 | — |
case-07 | fail→pass | 10,744 | 6,292 | -41% | 1 | 1 | 0% | 1,988 | 3,031 | +52% | 0 | 0 | — |
case-08 | pass→pass | 4,936 | 5,599 | +13% | 1 | 1 | 0% | 841 | 2,495 | +197% | 0 | 0 | — |
case-09 | fail→pass | 14,319 | 1,911 | -87% | 1 | 1 | 0% | 1,635 | 1,852 | +13% | 0 | 0 | — |
case-10 | pass→pass | 5,754 | 1,913 | -67% | 1 | 1 | 0% | 1,075 | 1,790 | +67% | 0 | 0 | — |
case-11 | fail→pass | 4,939 | 3,469 | -30% | 1 | 1 | 0% | 913 | 2,103 | +130% | 0 | 0 | — |
case-12 | pass→pass | 14,972 | 6,124 | -59% | 1 | 1 | 0% | 2,509 | 2,805 | +12% | 0 | 0 | — |
case-13 | pass→pass | 6,315 | 1,951 | -69% | 1 | 1 | 0% | 1,145 | 1,845 | +61% | 0 | 0 | — |
case-14 | fail→pass | 9,120 | 6,996 | -23% | 1 | 1 | 0% | 1,735 | 2,952 | +70% | 0 | 0 | — |
case-15 | pass→pass | 4,617 | 5,322 | +15% | 1 | 1 | 0% | 824 | 2,175 | +164% | 0 | 0 | — |
case-16 | fail→pass | 8,427 | 2,039 | -76% | 1 | 1 | 0% | 1,407 | 1,866 | +33% | 0 | 0 | — |
case-17 | fail→pass | 16,639 | 8,624 | -48% | 1 | 1 | 0% | 3,156 | 3,317 | +5% | 0 | 0 | — |
case-18 | fail→pass | 9,689 | 5,254 | -46% | 1 | 1 | 0% | 1,624 | 2,532 | +56% | 0 | 0 | — |
case-19 | fail→pass | 3,726 | 1,638 | -56% | 1 | 1 | 0% | 615 | 1,803 | +193% | 0 | 0 | — |
case-20 | fail→pass | 7,931 | 3,304 | -58% | 1 | 1 | 0% | 1,523 | 1,984 | +30% | 0 | 0 | — |
case-21 | pass→pass | 14,899 | 14,295 | -4% | 1 | 1 | 0% | 2,699 | 4,137 | +53% | 0 | 0 | — |
case-22 | fail→pass | 12,140 | 1,870 | -85% | 1 | 1 | 0% | 965 | 1,888 | +96% | 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 +55 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.