Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cursor rules for Go development with Fiber integration.
.claude/skills/amariahak-cursor-rules-for-go-development-with-fiber-integration/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -50% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -36% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -21% | 0% |
Cursor rules for Go development with Fiber integration.
Synced from https://github.com/PatrickJS/awesome-cursorrules/tree/main/rules/htmx-go-fiber-cursorrules-prompt-file.mdc.
// HTMX with Go and Fiber .cursorrules
// HTMX, Go, and Fiber best practices
const htmxGoFiberBestPractices = "Use Fiber's HTML rendering for server-side templates", "Implement Fiber's routing system for HTMX requests", "Utilize Fiber's middleware for request processing", "Use Fiber's JSON methods for API responses", "Implement proper error handling with Fiber's error handling", "Utilize Fiber's static file serving for assets", ];
// 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-01 | fail→fail | 21,335 | 10,157 | -52% | 1 | 1 | 0% | 3,466 | 2,415 | -30% | 0 | 0 | — |
case-02 | fail→pass | 18,548 | 11,337 | -39% | 1 | 1 | 0% | 3,878 | 2,736 | -29% | 0 | 0 | — |
case-03 | fail→pass | 22,310 | 16,989 | -24% | 1 | 1 | 0% | 3,733 | 3,136 | -16% | 0 | 0 | — |
case-04 | fail→pass | 10,898 | 3,282 | -70% | 1 | 1 | 0% | 1,848 | 920 | -50% | 0 | 0 | — |
case-05 | pass→pass | 12,772 | 2,054 | -84% | 1 | 1 | 0% | 2,246 | 681 | -70% | 0 | 0 | — |
case-06 | fail→pass | 9,232 | 3,622 | -61% | 1 | 1 | 0% | 1,465 | 935 | -36% | 0 | 0 | — |
case-07 | fail→pass | 17,246 | 12,587 | -27% | 1 | 1 | 0% | 3,441 | 2,733 | -21% | 0 | 0 | — |
case-08 | fail→pass | 14,914 | 12,021 | -19% | 1 | 1 | 0% | 2,870 | 2,248 | -22% | 0 | 0 | — |
case-09 | pass→pass | 10,905 | 10,025 | -8% | 1 | 1 | 0% | 2,174 | 1,918 | -12% | 0 | 0 | — |
case-10 | pass→pass | 11,417 | 8,398 | -26% | 1 | 1 | 0% | 2,411 | 2,000 | -17% | 0 | 0 | — |
case-11 | pass→pass | 14,076 | 11,229 | -20% | 1 | 1 | 0% | 2,700 | 2,476 | -8% | 0 | 0 | — |
case-12 | fail→pass | 9,964 | 7,714 | -23% | 1 | 1 | 0% | 1,994 | 1,737 | -13% | 0 | 0 | — |
case-13 | fail→pass | 9,009 | 6,180 | -31% | 1 | 1 | 0% | 1,836 | 1,623 | -12% | 0 | 0 | — |
case-14 | fail→pass | 16,678 | 22,357 | +34% | 1 | 1 | 0% | 3,634 | 3,029 | -17% | 0 | 0 | — |
case-15 | fail→pass | 13,770 | 6,961 | -49% | 1 | 1 | 0% | 2,141 | 1,670 | -22% | 0 | 0 | — |
case-16 | fail→pass | 17,941 | 10,222 | -43% | 1 | 1 | 0% | 2,742 | 2,414 | -12% | 0 | 0 | — |
case-17 | pass→pass | 5,815 | 5,198 | -11% | 1 | 1 | 0% | 1,004 | 1,018 | +1% | 0 | 0 | — |
case-18 | fail→fail | 13,537 | 10,481 | -23% | 1 | 1 | 0% | 2,384 | 2,292 | -4% | 0 | 0 | — |
case-19 | fail→fail | 14,018 | 8,400 | -40% | 1 | 1 | 0% | 2,541 | 1,994 | -22% | 0 | 0 | — |
case-20 | fail→pass | 8,943 | 6,621 | -26% | 1 | 1 | 0% | 1,861 | 1,641 | -12% | 0 | 0 | — |
case-21 | pass→pass | 6,921 | 4,900 | -29% | 1 | 1 | 0% | 1,282 | 1,181 | -8% | 0 | 0 | — |
case-22 | pass→pass | 5,688 | 8,047 | +41% | 1 | 1 | 0% | 1,102 | 1,620 | +47% | 0 | 0 | — |
case-23 | pass→pass | 6,311 | 6,629 | +5% | 1 | 1 | 0% | 1,315 | 1,768 | +34% | 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.
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.