Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →AI-powered MAP (Minimum Advertised Price) policy and enforcement skill. Helps brands create MAP policies, monitor violations across channels, manage dealer compliance, and design enforcement workflows.
.claude/skills/nexscope-ai-minimum-advertised-price/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 20% | 0% |
| case-10 | ✓→✓ | ＝ Same ✓ | 46% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 27% | 0% |
AI-powered MAP (Minimum Advertised Price) policy and enforcement skill. Helps brands create MAP policies, monitor violations across channels, manage dealer compliance, and design enforcement workflows.
clawhub install minimum-advertised-priceInput: Brand name, product line, distribution channels, current pricing policy
Output: MAP policy document, violation monitoring plan, dealer compliance checklist, enforcement escalation procedures
> "I run a your business type] on platform]. Help me set up minimum advertised price 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-10 | pass→pass | 16,350 | 18,986 | +16% | 1 | 1 | 0% | 2,358 | 3,439 | +46% | 0 | 0 | — |
case-01 | pass→pass | 16,849 | 19,526 | +16% | 1 | 1 | 0% | 2,604 | 3,308 | +27% | 0 | 0 | — |
case-02 | pass→pass | 14,232 | 15,559 | +9% | 1 | 1 | 0% | 2,084 | 2,543 | +22% | 0 | 0 | — |
case-03 | pass→pass | 15,920 | 16,497 | +4% | 1 | 1 | 0% | 2,188 | 2,654 | +21% | 0 | 0 | — |
case-04 | pass→pass | 14,093 | 16,481 | +17% | 1 | 1 | 0% | 2,344 | 2,714 | +16% | 0 | 0 | — |
case-05 | fail→pass | 11,398 | 11,604 | +2% | 1 | 1 | 0% | 1,738 | 1,973 | +14% | 0 | 0 | — |
case-06 | pass→pass | 17,728 | 15,549 | -12% | 1 | 1 | 0% | 2,480 | 2,503 | +1% | 0 | 0 | — |
case-07 | pass→pass | 13,252 | 16,738 | +26% | 1 | 1 | 0% | 1,890 | 2,292 | +21% | 0 | 0 | — |
case-08 | pass→pass | 14,017 | 12,043 | -14% | 1 | 1 | 0% | 2,044 | 2,026 | -1% | 0 | 0 | — |
case-09 | pass→pass | 16,949 | 15,187 | -10% | 1 | 1 | 0% | 2,446 | 2,508 | +3% | 0 | 0 | — |
case-11 | fail→pass | 10,839 | 10,349 | -5% | 1 | 1 | 0% | 1,744 | 1,801 | +3% | 0 | 0 | — |
case-12 | pass→pass | 13,020 | 16,729 | +28% | 1 | 1 | 0% | 1,813 | 2,705 | +49% | 0 | 0 | — |
case-13 | pass→pass | 13,617 | 14,915 | +10% | 1 | 1 | 0% | 1,942 | 2,646 | +36% | 0 | 0 | — |
case-14 | fail→fail | 13,050 | 12,966 | -1% | 1 | 1 | 0% | 2,013 | 2,208 | +10% | 0 | 0 | — |
case-15 | pass→pass | 11,152 | 14,058 | +26% | 1 | 1 | 0% | 1,749 | 2,411 | +38% | 0 | 0 | — |
case-16 | pass→pass | 14,612 | 14,730 | +1% | 1 | 1 | 0% | 2,330 | 2,540 | +9% | 0 | 0 | — |
case-17 | pass→pass | 12,308 | 14,095 | +15% | 1 | 1 | 0% | 1,729 | 2,364 | +37% | 0 | 0 | — |
case-18 | pass→pass | 12,666 | 14,251 | +13% | 1 | 1 | 0% | 1,928 | 2,466 | +28% | 0 | 0 | — |
case-19 | fail→pass | 12,835 | 14,737 | +15% | 1 | 1 | 0% | 2,113 | 2,539 | +20% | 0 | 0 | — |
case-20 | fail→fail | 20,019 | 19,451 | -3% | 1 | 1 | 0% | 3,153 | 3,342 | +6% | 0 | 0 | — |
case-21 | fail→fail | 18,264 | 17,432 | -5% | 1 | 1 | 0% | 3,040 | 3,000 | -1% | 0 | 0 | — |
case-22 | fail→fail | 12,795 | 13,037 | +2% | 1 | 1 | 0% | 2,268 | 2,662 | +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. 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.