Comparable-backed vehicle valuation and appraisal. Triggers: "appraise this vehicle", "what's it worth", "trade-in value", "comparable analysis", "fair market value", "wholesale vs retail", "appraisal report", "how much should I offer", "vehicle valuation", building a defensible, comparable-backed vehicle valuation for trade-ins, insurance claims, estate valuations, fleet revaluation, or retail pricing decisions.
From appraisernpx claudepluginhub marketcheckhub/marketcheck-cowork-plugin --plugin appraiserThis 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.
Builds 3-5 year financial models for startups with cohort revenue projections, cost structures, cash flow, headcount plans, burn rate, runway, and scenario analysis.
Load the marketcheck-profile.md project memory file if exists. Extract: zip/postcode, specialization, radius, country, min_comp_count. If missing, ask for ZIP and radius. US: all tools (decode, predict, search, history); UK: search_uk_active_cars/search_uk_recent_cars only (no decode — ask YMMT, use comp median). Confirm profile.
When appraising a vehicle, determine if it is Certified Pre-Owned (CPO):
is_certified=true.get_car_history shows the vehicle currently listed as certified.When the vehicle IS CPO, the Full Comparable Appraisal workflow adds these steps:
predict_price_with_comparables with is_certified=true to get the certified market value.predict_price_with_comparables WITHOUT is_certified to get the standard market value.search_active_cars with the YMMT filters PLUS is_certified=true to find certified-only comparables.In the Valuation Summary output, add:
| Measure | Value |
|---|---|
| CPO Predicted Retail Value | $XX,XXX |
| Non-CPO Predicted Retail Value | $XX,XXX |
| CPO Premium | +$X,XXX (+X.X%) |
| Active CPO Comps | N within radius |
| Active Non-CPO Comps | N within radius |
For the Trade-In Quick Appraisal: if CPO, note the premium but keep the quick format. Show: "CPO Value: $XX,XXX | Standard Value: $XX,XXX | Premium: +$X,XXX"
User is an appraiser needing a defensible, comparable-backed valuation with cited comparables, methodology notes, and confidence assessment.
| Required | Field | Source |
|---|---|---|
| Yes | VIN or YMMT | Ask |
| Yes | Odometer reading | Ask |
| Auto/Ask | ZIP, radius | Profile or ask |
| Recommended | Condition (Clean/Average/Rough), purpose | Ask |
| Optional | CPO status | Ask |
VIN provided → decode first (US only). Assumed trims lose credibility.
Use this for formal appraisals, insurance claims, estate valuations, or any situation where the valuation must be supported by cited comparables.
Decode VIN — Call mcp__marketcheck__decode_vin_neovin with vin.
→ Extract only: year, make, model, trim, body_type, drivetrain, engine, transmission. Discard full response.
Predict price — Call mcp__marketcheck__predict_price_with_comparables with vin, miles, zip, dealer_type=franchise, is_certified if applicable.
→ Extract only: predicted_price, comparable VINs with prices and miles. Discard full response.
Pull active comps — Call mcp__marketcheck__search_active_cars with YMMT from step 1, zip, radius=75, miles_range=<odo-15k>-<odo+15k>, car_type=used, sort_by=price, sort_order=asc, rows=20.
→ Extract only: per listing — VIN, price, miles, dealer_name, distance, dom. Discard full response.
Pull sold transactions — Call mcp__marketcheck__search_past_90_days with same YMMT + location filters, sold=true.
→ Extract only: per listing — VIN, sold_price, miles, dealer_name, sale_date. Discard full response.
Synthesize the valuation — Combine all three data sources:
Present the appraisal report — Deliver a structured report with the valuation, every cited comparable (VIN, price, miles, dealer, distance), methodology notes, and confidence assessment. The report must be defensible — include enough detail for a third party to verify the conclusion.
Use this when speed matters — a quick but credible estimate is needed in under 60 seconds.
Predict price — Call mcp__marketcheck__predict_price_with_comparables with vin, miles, zip, dealer_type=franchise.
→ Extract only: predicted_price, top comparable VINs with prices and miles. Discard full response.
Pull tight comps — Call mcp__marketcheck__search_active_cars with YMMT, zip, radius=75, car_type=used, sort_by=price, sort_order=asc, rows=5.
→ Extract only: per listing — price, miles, dealer_name, distance. Discard full response.
Deliver the quick value — Present:
min_comp_count from profile, default 10)Use this when the user needs to understand how values differ across geographies, common for fleet valuations, multi-state insurance claims, or relocation decisions.
Primary market stats — Call mcp__marketcheck__search_active_cars with year, make, model, zip, radius=100, stats=price,miles, rows=0, car_type=used.
→ Extract only: mean, median, min, max, count for price and miles. Discard full response.
Comparison market stats — Repeat step 1 for each additional ZIP. → Extract only: mean, median, count per market. Discard full response.
Sold summary by state — Call mcp__marketcheck__get_sold_summary with make, model, inventory_type=Used, summary_by=state, ranking_measure=average_sale_price, ranking_order=desc, top_n=10.
→ Extract only: per state — average_sale_price, sold_count. Discard full response.
Calculate regional variance — Build a comparison table: market, median price, mean price, sample size, and delta from the lowest market. Identify arbitrage opportunities where the same vehicle sells for significantly more in one region.
Present the regional map — Show the price variance table and highlight any market where the price delta exceeds 5% — these represent real geographic value differences relevant to the appraisal.
Use this when the user needs to understand the gap between wholesale and retail values, critical for trade-in offers, insurance claim valuations, and auction buying decisions.
Predict franchise (retail) price — Call mcp__marketcheck__predict_price_with_comparables with vin, miles, zip, dealer_type=franchise.
→ Extract only: predicted_price. Discard full response.
Predict independent (wholesale-proxy) price — Call mcp__marketcheck__predict_price_with_comparables with vin, miles, zip, dealer_type=independent.
→ Extract only: predicted_price. Discard full response.
Pull franchise listings — Call mcp__marketcheck__search_active_cars with YMMT, zip, radius=75, dealer_type=franchise, car_type=used, sort_by=price, sort_order=asc, rows=10.
→ Extract only: per listing — price, miles, dealer_name; plus median. Discard full response.
Pull independent listings — Call mcp__marketcheck__search_active_cars with same filters, dealer_type=independent, rows=10.
→ Extract only: per listing — price, miles, dealer_name; plus median. Discard full response.
Calculate the spread — Present:
Note: Always show both franchise and independent prices. The appraiser selects the appropriate benchmark based on the purpose of the appraisal (insurance = retail, trade-in = wholesale, estate = midpoint).
Use this when the user asks "what has this VIN been listed at over time" or needs to understand depreciation patterns for a specific unit.
Pull listing history — Call mcp__marketcheck__get_car_history with vin, sort_order=asc.
→ Extract only: per event — date, dealer_name, price, dom. Discard full response.
Decode VIN — Call mcp__marketcheck__decode_vin_neovin with vin.
→ Extract only: year, make, model, trim, MSRP. Discard full response.
Build the trajectory — From the history, extract each listing event: date, dealer, asking price, and DOM at that dealer. Calculate:
Current market context — Call mcp__marketcheck__predict_price_with_comparables with vin, miles, zip.
→ Extract only: predicted_price. Discard full response.
Present the timeline — Show a chronological table of all listings with price, dealer, and DOM. Highlight any unusual patterns (rapid dealer hops, price increases between dealers suggesting reconditioning, or steep drops suggesting undisclosed issues). These patterns are critical context for an appraiser assessing the vehicle's market history.
Present: vehicle identification summary, valuation table (predicted/comp range/sold range/recommended value/confidence), comparable data tables (active retail + sold transactions with VIN/price/miles/dealer), and methodology notes with condition adjustments and caveats.