Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →AI-powered digital share of shelf analysis skill. Measures brand visibility within product categories, benchmarks against competitors, and tracks shelf position trends across e-commerce platforms.
.claude/skills/nexscope-ai-share-of-shelf/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 101% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-20 | ✓→✗ | ▼ Worse | 21% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 0% | 0% |
AI-powered digital share of shelf analysis skill. Measures brand visibility within product categories, benchmarks against competitors, and tracks shelf position trends across e-commerce platforms.
clawhub install share-of-shelfInput: Brand name, product category, target marketplace(s), competitor brands
Output: Share of shelf score, category positioning map, competitor visibility comparison, trend tracking framework
> "I run a your business type] on platform]. Help me set up share of shelf 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-01 | pass→pass | 21,501 | 19,614 | -9% | 1 | 1 | 0% | 3,432 | 3,447 | +0% | 0 | 0 | — |
case-02 | pass→pass | 20,609 | 20,250 | -2% | 1 | 1 | 0% | 3,011 | 3,359 | +12% | 0 | 0 | — |
case-03 | pass→pass | 18,717 | 18,691 | -0% | 1 | 1 | 0% | 2,979 | 3,340 | +12% | 0 | 0 | — |
case-04 | pass→pass | 18,711 | 16,730 | -11% | 1 | 1 | 0% | 2,759 | 2,729 | -1% | 0 | 0 | — |
case-05 | pass→pass | 18,526 | 20,125 | +9% | 1 | 1 | 0% | 2,778 | 3,426 | +23% | 0 | 0 | — |
case-06 | pass→pass | 18,412 | 16,511 | -10% | 1 | 1 | 0% | 2,655 | 2,595 | -2% | 0 | 0 | — |
case-07 | fail→pass | 17,438 | 16,858 | -3% | 1 | 1 | 0% | 2,627 | 2,839 | +8% | 0 | 0 | — |
case-08 | pass→pass | 17,439 | 15,229 | -13% | 1 | 1 | 0% | 2,586 | 2,686 | +4% | 0 | 0 | — |
case-09 | pass→pass | 15,191 | 16,370 | +8% | 1 | 1 | 0% | 2,606 | 2,957 | +13% | 0 | 0 | — |
case-10 | pass→pass | 19,928 | 17,697 | -11% | 1 | 1 | 0% | 3,105 | 3,108 | +0% | 0 | 0 | — |
case-11 | fail→pass | 40,495 | 17,933 | -56% | 1 | 1 | 0% | 1,540 | 3,091 | +101% | 0 | 0 | — |
case-12 | fail→pass | 21,658 | 17,425 | -20% | 1 | 1 | 0% | 3,249 | 3,047 | -6% | 0 | 0 | — |
case-13 | fail→fail | 6,923 | 12,563 | +81% | 1 | 1 | 0% | 1,218 | 2,382 | +96% | 0 | 0 | — |
case-14 | pass→pass | 15,611 | 15,717 | +1% | 1 | 1 | 0% | 1,981 | 2,605 | +31% | 0 | 0 | — |
case-15 | pass→pass | 21,358 | 21,768 | +2% | 1 | 1 | 0% | 3,416 | 3,835 | +12% | 0 | 0 | — |
case-16 | pass→pass | 20,579 | 21,078 | +2% | 1 | 1 | 0% | 3,221 | 3,597 | +12% | 0 | 0 | — |
case-17 | pass→pass | 18,324 | 16,433 | -10% | 1 | 1 | 0% | 2,696 | 2,847 | +6% | 0 | 0 | — |
case-18 | pass→pass | 14,358 | 15,107 | +5% | 1 | 1 | 0% | 2,243 | 2,694 | +20% | 0 | 0 | — |
case-19 | pass→pass | 17,228 | 17,318 | +1% | 1 | 1 | 0% | 2,598 | 2,921 | +12% | 0 | 0 | — |
case-20 | pass→fail | 11,535 | 12,041 | +4% | 1 | 1 | 0% | 2,188 | 2,654 | +21% | 0 | 0 | — |
case-21 | pass→pass | 15,370 | 15,415 | +0% | 1 | 1 | 0% | 2,351 | 2,630 | +12% | 0 | 0 | — |
case-22 | pass→pass | 11,154 | 7,658 | -31% | 1 | 1 | 0% | 1,975 | 1,767 | -11% | 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, and 21 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +9 percentage points is the difference between those two pass rates over the 21 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
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.