Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →AI-powered Shopify page speed optimization skill. Diagnoses performance bottlenecks, provides Core Web Vitals improvement plans, and recommends theme and app optimizations for faster Shopify stores.
.claude/skills/nexscope-ai-shopify-page-speed/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 41% | 0% |
| case-09 | ✓→✓ | ＝ Same ✓ | 11% | 0% |
| case-14 | ✓→✓ | ＝ Same ✓ | 11% | 0% |
| case-15 | ✓→✓ | ＝ Same ✓ | 20% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 20% | 0% |
AI-powered Shopify page speed optimization skill. Diagnoses performance bottlenecks, provides Core Web Vitals improvement plans, and recommends theme and app optimizations for faster Shopify stores.
clawhub install shopify-page-speedInput: Shopify store URL, current theme, installed apps
Output: Speed diagnostic report, Core Web Vitals improvement plan, theme optimization guide, app performance audit
> "I run a your business type] on platform]. Help me set up shopify page speed for my business. Here's my current situation: describe context]."
Built by Nexscope AI — AI-powered e-commerce intelligence.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-09 | pass→pass | 19,141 | 18,775 | -2% | 1 | 1 | 0% | 2,941 | 3,273 | +11% | 0 | 0 | — |
case-14 | pass→pass | 17,606 | 16,803 | -5% | 1 | 1 | 0% | 2,526 | 2,792 | +11% | 0 | 0 | — |
case-15 | pass→pass | 17,881 | 18,913 | +6% | 1 | 1 | 0% | 2,667 | 3,207 | +20% | 0 | 0 | — |
case-01 | pass→pass | 14,185 | 14,286 | +1% | 1 | 1 | 0% | 2,087 | 2,501 | +20% | 0 | 0 | — |
case-02 | pass→pass | 11,723 | 14,684 | +25% | 1 | 1 | 0% | 1,922 | 2,513 | +31% | 0 | 0 | — |
case-03 | pass→pass | 14,358 | 13,587 | -5% | 1 | 1 | 0% | 2,274 | 2,302 | +1% | 0 | 0 | — |
case-04 | pass→pass | 12,824 | 11,408 | -11% | 1 | 1 | 0% | 1,898 | 1,839 | -3% | 0 | 0 | — |
case-05 | pass→pass | 14,706 | 18,277 | +24% | 1 | 1 | 0% | 2,311 | 3,138 | +36% | 0 | 0 | — |
case-06 | pass→pass | 10,971 | 12,858 | +17% | 1 | 1 | 0% | 1,706 | 2,375 | +39% | 0 | 0 | — |
case-07 | fail→pass | 13,501 | 17,817 | +32% | 1 | 1 | 0% | 2,194 | 3,097 | +41% | 0 | 0 | — |
case-08 | pass→pass | 12,959 | 15,073 | +16% | 1 | 1 | 0% | 1,917 | 2,558 | +33% | 0 | 0 | — |
case-10 | pass→pass | 10,060 | 14,513 | +44% | 1 | 1 | 0% | 1,695 | 2,583 | +52% | 0 | 0 | — |
case-11 | pass→pass | 17,719 | 19,556 | +10% | 1 | 1 | 0% | 2,674 | 3,338 | +25% | 0 | 0 | — |
case-12 | pass→pass | 11,950 | 14,302 | +20% | 1 | 1 | 0% | 1,885 | 2,469 | +31% | 0 | 0 | — |
case-13 | pass→pass | 15,360 | 15,796 | +3% | 1 | 1 | 0% | 2,223 | 2,858 | +29% | 0 | 0 | — |
case-16 | pass→pass | 13,610 | 14,623 | +7% | 1 | 1 | 0% | 1,929 | 2,329 | +21% | 0 | 0 | — |
case-17 | pass→pass | 15,368 | 14,807 | -4% | 1 | 1 | 0% | 2,290 | 2,859 | +25% | 0 | 0 | — |
case-18 | fail→fail | 16,352 | 14,679 | -10% | 1 | 1 | 0% | 2,349 | 2,612 | +11% | 0 | 0 | — |
case-19 | fail→fail | 13,428 | 15,658 | +17% | 1 | 1 | 0% | 2,029 | 2,675 | +32% | 0 | 0 | — |
case-20 | fail→fail | 18,987 | 17,444 | -8% | 1 | 1 | 0% | 3,524 | 3,558 | +1% | 0 | 0 | — |
case-21 | pass→pass | 13,612 | 13,420 | -1% | 1 | 1 | 0% | 2,057 | 2,338 | +14% | 0 | 0 | — |
case-22 | pass→pass | 11,986 | 16,494 | +38% | 1 | 1 | 0% | 1,649 | 2,686 | +63% | 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 +5 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.