Date anchor: Today's date comes from the # currentDate system context. Compute ALL relative dates from it. Never use training-data dates.

get_sold_summary parameter safety:

• Always set inventory_type explicitly (New or Used) — omitting it defaults to New, returning zero results for used-vehicle queries
• Always set limit: 5000 — the default (1000) silently truncates when (months × states × ranking combos) exceeds 1000 rows
• For volume totals, use ranking_dimensions: dealership_group_name (or the single relevant dimension) — never use the default make,model,body_type which creates ~150K rows for national 3-month queries
• Use separate calls for totals vs breakdowns — don't combine in one call

Dealer Performance Intelligence Report

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.

Dealer Group Profile (Load First)

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.