Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cursor rules for Go development with basic setup.
.claude/skills/amariahak-cursor-rules-for-go-development-with-basic-setup/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 5% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -54% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -70% | 0% |
| case-21 | ✓→✓ | = Same ✓ | -16% | 0% |
| case-06 | ✓→✓ | = Same ✓ | -16% | 0% |
Cursor rules for Go development with basic setup.
Synced from https://github.com/PatrickJS/awesome-cursorrules/tree/main/rules/htmx-go-basic-cursorrules-prompt-file.mdc.
// HTMX with Go (Basic Setup) .cursorrules
// HTMX and Go best practices
const htmxGoBestPractices = "Use html/template for server-side rendering", "Implement http.HandlerFunc for handling HTMX requests", "Utilize gorilla/mux for routing if needed", "Use encoding/json for JSON responses", "Implement proper error handling and logging", "Utilize context for request cancellation and timeouts", ];
// Folder structure
const folderStructure = cmd/ main.go internal/ handlers/ models/ templates/ static/ css/ js/ go.mod go.sum ;
// 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-21 | pass→pass | 13,281 | 8,849 | -33% | 1 | 1 | 0% | 2,261 | 1,900 | -16% | 0 | 0 | — |
case-01 | fail→fail | 18,405 | 16,345 | -11% | 1 | 1 | 0% | 3,258 | 3,353 | +3% | 0 | 0 | — |
case-02 | fail→fail | 28,049 | 15,844 | -44% | 1 | 1 | 0% | 4,337 | 3,276 | -24% | 0 | 0 | — |
case-03 | fail→fail | 20,250 | 13,996 | -31% | 1 | 1 | 0% | 3,569 | 2,891 | -19% | 0 | 0 | — |
case-04 | fail→pass | 14,045 | 11,631 | -17% | 1 | 1 | 0% | 2,259 | 2,362 | +5% | 0 | 0 | — |
case-05 | fail→pass | 11,047 | 3,387 | -69% | 1 | 1 | 0% | 1,937 | 890 | -54% | 0 | 0 | — |
case-06 | pass→pass | 15,461 | 11,383 | -26% | 1 | 1 | 0% | 2,895 | 2,440 | -16% | 0 | 0 | — |
case-07 | fail→fail | 14,658 | 10,342 | -29% | 1 | 1 | 0% | 2,447 | 2,253 | -8% | 0 | 0 | — |
case-08 | pass→pass | 13,948 | 7,575 | -46% | 1 | 1 | 0% | 2,044 | 1,657 | -19% | 0 | 0 | — |
case-09 | pass→pass | 7,613 | 5,146 | -32% | 1 | 1 | 0% | 1,438 | 1,252 | -13% | 0 | 0 | — |
case-10 | pass→pass | 13,801 | 4,113 | -70% | 1 | 1 | 0% | 1,572 | 946 | -40% | 0 | 0 | — |
case-11 | pass→pass | 4,692 | 3,027 | -35% | 1 | 1 | 0% | 845 | 674 | -20% | 0 | 0 | — |
case-12 | pass→pass | 15,804 | 11,638 | -26% | 1 | 1 | 0% | 2,508 | 2,503 | -0% | 0 | 0 | — |
case-13 | pass→pass | 8,995 | 2,211 | -75% | 1 | 1 | 0% | 1,514 | 619 | -59% | 0 | 0 | — |
case-14 | pass→pass | 13,478 | 6,249 | -54% | 1 | 1 | 0% | 2,234 | 1,362 | -39% | 0 | 0 | — |
case-15 | fail→fail | 10,424 | 8,249 | -21% | 1 | 1 | 0% | 1,783 | 1,767 | -1% | 0 | 0 | — |
case-16 | fail→pass | 11,493 | 1,747 | -85% | 1 | 1 | 0% | 1,964 | 594 | -70% | 0 | 0 | — |
case-17 | pass→pass | 13,435 | 8,373 | -38% | 1 | 1 | 0% | 2,202 | 1,688 | -23% | 0 | 0 | — |
case-18 | pass→pass | 10,934 | 1,728 | -84% | 1 | 1 | 0% | 1,949 | 566 | -71% | 0 | 0 | — |
case-19 | pass→pass | 12,204 | 2,373 | -81% | 1 | 1 | 0% | 2,178 | 702 | -68% | 0 | 0 | — |
case-20 | pass→pass | 14,547 | 10,507 | -28% | 1 | 1 | 0% | 2,730 | 2,264 | -17% | 0 | 0 | — |
case-22 | pass→pass | 10,661 | 13,665 | +28% | 1 | 1 | 0% | 2,178 | 2,543 | +17% | 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 +14 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.