Auction lane optimization by demand signals. Triggers: "what should I run this week", "lane planning", "auction lineup", "what sells at auction", "which categories to feature", "lane optimization", "sale day planning", "what segments have the best sell-through", "plan my lanes for next sale", deciding which vehicle categories to prioritize in upcoming auction events based on demand signals and sell-through predictions.
From auction-housenpx claudepluginhub marketcheckhub/marketcheck-cowork-plugin --plugin auction-houseThis 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 exists. Extract: zip/postcode, state/region, target_dmas, vehicle_segments, avg_weekly_lanes, target_sell_through_pct, buyer_fee_pct, seller_fee_pct, country, radius. If missing, ask minimum fields (state). US: get_sold_summary, search_active_cars. UK: search_uk_active_cars only (limited — no demand data, skip sell-through prediction). Confirm: "Using profile: [company], [state], [Country]". All preference values from profile — do not re-ask.
Lane manager or sales exec planning which vehicle segments to feature in upcoming auction events. Goal: maximize sell-through rate and bidder engagement by featuring segments with strong demand and limited supply.
get_sold_summary date ranges are inclusive — If you pass date_from=2026-02-01 and date_to=2026-02-28, February 29 (leap year) is excluded. Always compute the correct last day of the month.facets=body_type|0|20|1 the counts are exact only when the total result set is under ~100k. For large states (TX, CA, FL) the body_type facet is fine, but make|0|50|1 may show rounded counts. Never treat facet counts as exact inventory figures — label them "approx." when total exceeds 50k.ranking_dimensions=body_type can return inconsistent labels — The API may return "Sport Utility Vehicle" vs "SUV" depending on source. Normalize all body_type values before comparing demand to supply: map "Sport Utility Vehicle" to "SUV", "Passenger Van" to "Van", "Crew Cab Pickup" to "Pickup", etc.get_sold_summary for demand data. UK profiles can only see current supply via search_uk_active_cars; skip sell-through prediction entirely and note "Demand data unavailable for UK — supply snapshot only."| Field | Source | Default |
|---|---|---|
| State/ZIP | Profile | — |
| Avg weekly lanes | Profile | ask |
| Target sell-through % | Profile | 85% |
| Buyer fee %, seller fee % | Profile | 5%, 3% |
Use this when the user says "plan my lanes" or "what should I run this week."
Get demand by segment (current month) — Call mcp__marketcheck__get_sold_summary with state, inventory_type=Used, ranking_dimensions=body_type, ranking_measure=sold_count, ranking_order=desc, date_from (first of prior month), date_to (last of prior month), top_n=10.
→ Extract only: per body_type — sold_count, average_sale_price, average_days_on_market. Discard full response.
Get demand by segment (prior month for trend) — Same call with date range shifted back one month. → Extract only: per body_type — sold_count. Discard full response.
Get fastest-turning models — Call mcp__marketcheck__get_sold_summary with state, inventory_type=Used, ranking_dimensions=make,model, ranking_measure=average_days_on_market, ranking_order=asc, top_n=20, same date range as step 1.
→ Extract only: per make/model — average_days_on_market, sold_count. Discard full response.
Get current supply snapshot — Call mcp__marketcheck__search_active_cars with state, car_type=used, seller_type=dealer, facets=body_type|0|20|1, stats=price,dom, rows=0, price_min=1.
→ Extract only: per body_type — active supply count (from facets), median_price, avg_dom (from stats). Normalize body_type labels (see Gotcha #3). Discard full response.
Calculate lane metrics per segment:
Allocate lane slots — If avg_weekly_lanes is known, distribute proportionally:
Use this when the user asks "which specific models should I feature" or "what are the hottest auction vehicles."
mcp__marketcheck__search_active_cars with make, model, state, car_type=used, stats=price, rows=0.
→ Extract only: total_count (supply), median_price. Discard full response.Present lane lineup table: Segment/Model, Recommended Units, Predicted Sell-Through %, Avg Expected Hammer, Fee Revenue Estimate, Demand Signal (HOT/WARM/COOL/DECLINING), Volume Trend (arrow up/down/flat). Include event summary: "Recommended [X] total lanes. Predicted overall sell-through: [Y]%. Estimated total fee revenue: $[Z]." End with top 3 sourcing priorities ("source more SUVs — they'll move") and any segments to reduce ("avoid overloading sedans — soft demand").
-- Lane Lineup: [State] — Week of [Date] ------------------------------------------
| Segment | Rec. Units | Est. Sell-Through | Avg Hammer | Fee Rev/Unit | Lane Rev | Signal | Trend |
|-----------|------------|-------------------|------------|--------------|----------|-----------|-------|
| SUV | 35 | 92% | $24,500 | $1,960 | $63,504 | HOT | +12% |
| Pickup | 30 | 88% | $28,200 | $2,256 | $59,561 | HOT | +8% |
| Sedan | 15 | 72% | $18,400 | $1,472 | $15,898 | COOL | -3% |
| ... | ... | ... | ... | ... | ... | ... | ... |
-- Event Summary ------------------------------------------------------------------
Total Lanes: [X]
Predicted Sell-Through: [Y]%
Est. Total Fee Revenue: $[Z]
-- Sourcing Priorities -------------------------------------------------------------
1. Source more [segment] — [reason]
2. Source more [segment] — [reason]
3. Reduce [segment] — [reason]
# currentDate.