Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Master Go 1.21+ with modern patterns, advanced concurrency, performance optimization, and production-ready microservices.
.claude/skills/davila7-golang-pro/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | 81% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 107% | 0% |
| case-06 | ✓→✓ | = Same ✓ | 31% | 0% |
| case-04 | ✓→✓ | = Same ✓ | 60% | 0% |
| case-05 | ✓→✓ | = Same ✓ | 34% | 0% |
You are a Go expert specializing in modern Go 1.21+ development with advanced concurrency patterns, performance optimization, and production-ready system design.
Expert Go developer mastering Go 1.21+ features, modern development practices, and building scalable, high-performance applications. Deep knowledge of concurrent programming, microservices architecture, and the modern Go ecosystem.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | pass→pass | 14,430 | 11,620 | -19% | 1 | 1 | 0% | 2,987 | 3,920 | +31% | 0 | 0 | — |
case-01 | fail→fail | 37,111 | 29,722 | -20% | 1 | 1 | 0% | 6,214 | 7,276 | +17% | 0 | 0 | — |
case-02 | fail→fail | 30,316 | 38,223 | +26% | 1 | 1 | 0% | 6,205 | 6,652 | +7% | 0 | 0 | — |
case-03 | fail→fail | 48,396 | 32,544 | -33% | 1 | 1 | 0% | 6,208 | 7,585 | +22% | 0 | 0 | — |
case-04 | pass→pass | 11,813 | 12,975 | +10% | 1 | 1 | 0% | 2,200 | 3,525 | +60% | 0 | 0 | — |
case-05 | pass→pass | 19,166 | 17,838 | -7% | 1 | 1 | 0% | 3,585 | 4,792 | +34% | 0 | 0 | — |
case-07 | fail→fail | 17,377 | 17,256 | -1% | 1 | 1 | 0% | 3,241 | 4,622 | +43% | 0 | 0 | — |
case-08 | pass→pass | 15,678 | 15,885 | +1% | 1 | 1 | 0% | 2,939 | 4,353 | +48% | 0 | 0 | — |
case-09 | fail→pass | 15,553 | 20,482 | +32% | 1 | 1 | 0% | 3,034 | 5,484 | +81% | 0 | 0 | — |
case-10 | fail→fail | 16,247 | 17,227 | +6% | 1 | 1 | 0% | 2,685 | 4,323 | +61% | 0 | 0 | — |
case-11 | fail→fail | 10,517 | 11,482 | +9% | 1 | 1 | 0% | 2,103 | 3,694 | +76% | 0 | 0 | — |
case-12 | pass→pass | 10,182 | 17,263 | +70% | 1 | 1 | 0% | 1,905 | 4,561 | +139% | 0 | 0 | — |
case-13 | fail→pass | 10,826 | 12,994 | +20% | 1 | 1 | 0% | 1,771 | 3,663 | +107% | 0 | 0 | — |
case-14 | fail→fail | 14,858 | 15,226 | +2% | 1 | 1 | 0% | 2,643 | 4,409 | +67% | 0 | 0 | — |
case-15 | fail→fail | 13,616 | 18,804 | +38% | 1 | 1 | 0% | 2,519 | 4,398 | +75% | 0 | 0 | — |
case-16 | fail→fail | 13,318 | 12,993 | -2% | 1 | 1 | 0% | 2,417 | 3,875 | +60% | 0 | 0 | — |
case-17 | fail→fail | 15,415 | 16,863 | +9% | 1 | 1 | 0% | 2,713 | 4,673 | +72% | 0 | 0 | — |
case-18 | fail→fail | 17,988 | 23,812 | +32% | 1 | 1 | 0% | 3,078 | 5,591 | +82% | 0 | 0 | — |
case-19 | pass→pass | 14,949 | 12,422 | -17% | 1 | 1 | 0% | 2,665 | 3,545 | +33% | 0 | 0 | — |
case-20 | fail→fail | 14,056 | 17,038 | +21% | 1 | 1 | 0% | 2,514 | 4,543 | +81% | 0 | 0 | — |
case-21 | fail→fail | 16,629 | 20,130 | +21% | 1 | 1 | 0% | 3,388 | 5,261 | +55% | 0 | 0 | — |
case-22 | fail→fail | 7,670 | 10,026 | +31% | 1 | 1 | 0% | 1,130 | 3,017 | +167% | 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 +9 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.