Rooftop-vs-rooftop performance comparison. Triggers: "compare my stores", "best performing location", "benchmark rooftops", "rank my locations", "which store is best", "location comparison", "store performance ranking", "rooftop efficiency", comparing operational metrics across locations, identifying best practices and underperformers.
From dealership-groupnpx claudepluginhub marketcheckhub/marketcheck-cowork-plugin --plugin dealership-groupThis skill uses the workspace's default tool permissions.
Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Calculates TAM/SAM/SOM using top-down, bottom-up, and value theory methodologies for market sizing, revenue estimation, and startup validation.
Date anchor: Today's date comes from the
# currentDatesystem context. Compute ALL relative dates from it. Example: if today = 2026-03-14, then "prior month" = 2026-02-01 to 2026-02-28, "current month" (most recent complete) = February 2026, "three months ago" = December 2025. Never use training-data dates.
Load the marketcheck-profile.md project memory file. If missing, prompt /onboarding. Requires 2+ locations. Extract: locations[] (dealer_id, name, zip, state, dealer_type, franchise_brands), preferences, country. Confirm: "Benchmarking [N] locations for [group_name]"
Dealer group executive (CEO, VP Ops, Regional Director) identifying top-performing and underperforming stores to surface best practices and flag intervention targets.
For each location, use the Agent tool to spawn the dealership-group:lot-scanner agent in facets mode:
Fetch inventory stats for dealer_id=[dealer_id], country=[country]. Mode: full (with DOM stats) Return: total_units, avg_dom, median_dom, units_under_30_dom, units_30_60_dom, units_over_60_dom, avg_price
→ Extract only: per location — total_units, avg_dom, median_dom, units by DOM bucket, avg_price. Discard full response.
From the scanner results, calculate per location:
For each US location, use the Agent tool to spawn the dealership-group:lot-pricer agent on a SAMPLE of units (e.g., the 10 oldest and 5 newest per location):
Price these vehicles: [sample VINs with miles and listed_price] zip: [location zip], dealer_type: [location dealer_type]
→ Extract only: per VIN — predicted_price, listed_price, gap %. Discard full response.
From results, calculate per location:
For each location, call mcp__marketcheck__get_sold_summary with:
state: location's stateinventory_type: Usedranking_measure: average_days_on_marketdate_from / date_to: prior month→ Extract only: local market average_days_on_market per state. Discard full response.
Calculate:
Create rankings (1 = best):
GROUP BENCHMARKING — [Group Name]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[N] locations compared | Period: [Month Year]
PERFORMANCE RANKINGS (1 = best)
Location | Units | Avg DOM | Turn Rate | Aged % | Price Eff | DOM vs Mkt | Composite
-------------------|-------|---------|-----------|--------|-----------|------------|----------
★ [Location 1] | XXX | XX | X.XX | X% | +X.X% | -X days | 1
[Location 2] | XXX | XX | X.XX | XX% | +X.X% | +X days | 2
[Location 3] | XXX | XX | X.XX | XX% | +X.X% | +X days | 3
...
⚠ [Location N] | XXX | XX | X.XX | XX% | +X.X% | +X days | N
★ = Top performer | ⚠ = Needs attention
GROUP AVERAGES
Avg DOM: XX days | Turn Rate: X.XX | Aged %: XX% | Price-to-Market: +X.X%
KPI DEEP DIVE
Turn Rate:
Best: [Location] at X.XX (XX units sold per 30 days equivalent)
Worst: [Location] at X.XX
Gap: X.XX (X.Xx difference — [worst] is turning XXx slower)
Aging:
Best: [Location] at X% aged (only X units over 60 days)
Worst: [Location] at XX% aged (XX units — $X,XXX/day in floor plan)
Gap: XX percentage points
Pricing Efficiency:
Best: [Location] at +X.X% vs market (tight, competitive pricing)
Worst: [Location] at +XX.X% (significantly overpriced, contributing to aging)
BEST PRACTICES (from top performer)
- [e.g., "[Location 1] prices within 3% of market on 90% of units — aggressive day-1 pricing prevents aging"]
- [e.g., "[Location 1] has only 4% aged inventory — suggests strong reconditioning-to-frontline speed"]
IMPROVEMENT OPPORTUNITIES (for bottom performers)
- [e.g., "[Location N] has 25% aged inventory costing $X,XXX/day. Immediate action: reduce prices on XX aged units by avg $X,XXX to reach market level"]
- [e.g., "[Location N-1] is priced XX% above market on average. Aligning to market could reduce avg DOM by XX days"]
RECOMMENDED ACTIONS
1. [Most impactful action with specific location, metric, and dollar impact]
2. [Second action]
3. [Third action]
dealer_id for all locations. Locations without a dealer_id are excluded with a note./weekly-review on the underperforming location.