Industry cohort benchmarking and performance intelligence. Triggers: "performance report", "benchmark my group", "how do I compare to industry", "competitive analysis", "performance intelligence", "where am I winning", "where can I improve", "industry benchmarking", "dealer performance report", "how do we stack up", "competitive strengths", "improvement opportunities", benchmarking against 400+ dealer group industry cohort and named public peers.
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. Never use training-data dates.
Benchmark your dealer group's operational performance against the full ~400 US dealer group industry cohort. Identifies competitive strengths (where you outperform) and improvement opportunities (where targeted focus could drive gains), with named comparisons to the 8 publicly traded dealer groups.
Architecture: This skill uses a multi-agent Wave pattern. Wave 1 runs the cohort benchmarking agent and lot scanner in parallel. Wave 2 assembles the report.
Load the marketcheck-profile.md project memory file. If missing, prompt /onboarding and stop.
Extract: dealer_group.group_name, dealer_group.locations[] (all location details), preferences.default_inventory_type (default: "used"), dealer_group.franchise_brands, dealer_type.
Target group identification: The group name from the profile is used to search for this dealer in the MarketCheck cohort data. If the profile contains a dealer_group_name_mc field (the exact name as it appears in MarketCheck), use that. Otherwise try group_name.
Confirm: "Generating Performance Intelligence Report for [group name] | Locations: [N] | Brands: [list]"
These 8 publicly traded groups are always included as named comparison points:
SAH → Sonic Automotive | KMX → CarMax
CVNA → Carvana | GPI → Group 1 Automotive
PAG → Penske Automotive Group | LAD → Lithia Motors
AN → AutoNation | ABG → Asbury Automotive Group
From # currentDate, compute:
Agent A: cohort-benchmarking-agent
Use the Agent tool to spawn the marketcheck-cowork-plugin:cohort-benchmarking-agent with:
Benchmark these target groups against the full industry cohort: Target groups: [dealer group name from profile], AutoNation, Lithia Motors, Penske Automotive Group, Sonic Automotive, Group 1 Automotive, Asbury Automotive Group, CarMax, Carvana
Date ranges:
- current_month_from: [date] | current_month_to: [date]
- prior_year_month_from: [date] | prior_year_month_to: [date]
- q1_from: [date] | q1_to: [date]
- q4_from: [date] | q4_to: [date]
Return: quintile thresholds, per-group KPI values, quintile assignments, and composite scores.
Agent B: lot-scanner (facets + stats mode)
For each location in the profile, use the Agent tool to spawn dealership-group:lot-scanner with:
Pull lot composition for dealer_id=[location's dealer_id], country=[location's country], mode=facets_only. Use rows=0 with facets=make|0|10|1,body_type|0|10|1 and stats=price,dom,miles. Also pull car_type=new and car_type=used separately to get new/used split. Return: total units, new count, used count, avg price, avg DOM (used vs new), avg mileage (used), top makes, body type mix. Location label: [location name].
Using the cohort benchmarking results + lot scanner results:
Create a summary table of key KPIs with industry context:
KPI | [Group Name] | Industry P20 | Median | Industry P80 | Position
───────────────────────|──────────────|──────────────|────────|──────────────|──────────
Used Vehicle DOM | [val] days | [val] | [val] | [val] | [quintile or %ile]
YoY Unit Volume Growth | [val]% | [val]% | [val]% | [val]% | [position]
DOM Trend (Q1→Q4) | [val] days | [val] | [val] | [val] | [position]
New Vehicle DOM | [val] days | -- | ~[val] | -- | [context]
New Price vs. MSRP | [val]% | [val]% | [val]% | [val]% | [position]
Highlight the 2-3 strongest KPIs as "Where [Group] is winning" and the 1-2 weakest as "Where there is opportunity to improve."
For each KPI where the target group outperforms the industry median (P50) or outperforms named public peers:
Write a focused paragraph covering:
Example structure: "Used vehicle velocity — faster than Carvana. [Group]'s used vehicles sell in an average of [X] days — faster than Carvana ([Y] days) and CarMax ([Z] days)..."
Include a horizontal bar comparison showing the target group vs. named peers for each strength metric.
For each KPI where the target group underperforms the industry median:
Write a focused paragraph covering:
Use a callout box format for the recommended action.
From the lot-scanner results:
Brief section (2-3 bullet points) on how ongoing weekly data access enables:
Present the full report with clear section headers. Use tables for benchmarks, narrative paragraphs for strengths/opportunities, and callout boxes for recommended actions.
The report should read as a standalone document that a dealer group executive or owner can review without needing additional context.
get_sold_summary data. UK locations receive inventory composition only.preferences.default_inventory_type from profile. If set to "used," used vehicle KPIs are primary. If "new," emphasize new vehicle KPIs.