▮ Automotive AI Skills
Doc /skills/used-car-listing-assistant/README.htmlENJA

Used Car Listing Assistant

English 日本語

Prepare a used-vehicle listing from documented facts, with visible condition disclosures and a clear price breakdown.

Description

This skill supports sellers after vehicle information has been gathered. Build an evidence ledger before drafting the title, description, and buyer FAQ; keep unsupported claims and missing documents visible to the seller. It complements buyer-side inspection and does not replace an appraisal, condition inspection, or local advertising review.

Audience: Independent dealers, sales staff, and private owners preparing an accurate vehicle advertisement.

Capabilities

Example Prompts

2019 Toyota Prius 1.8 hybrid, 82,000 km, Japan. I have service invoices,
two keys, and a photographed bumper scratch, but no structural repair
history assessment. Draft a listing without claiming “accident-free.”
2017 Mazda MX-5 2.0 gasoline manual, 65,000 km, UK. Service records cover
only my ownership. Write an honest description and photo checklist;
do not turn these partial records into “full service history.”
2020 Nissan Leaf 40 kWh, 52,000 km, Japan. The dashboard shows an estimated
range, but I have no battery health test. Draft a buyer FAQ that separates
that display from measured battery capacity and guaranteed range.
2018 Honda N-BOX 660 cc gasoline, 60,000 km, Japan. Vehicle price is
¥900,000 and stated required charges total ¥80,000, including applicable
taxes. An optional warranty is ¥30,000. Make a price table, flag missing
registration/delivery conditions, and verify current advertising guidance.

For model-specific checks, follow reference routing using the variant, production year, and original market. The browser builder can prepare the prompt. A reference match does not establish a fault, eligibility, or completion.

Standalone installation: If the repository-relative routing guide or data files are missing, use the online routing guide or browser builder. Ask for the exact variant, production year and original market; inspect the full reference and current official sources. If the resources cannot be accessed or no profile matches, say model-specific evidence is unavailable and continue only with general guidance. A match is not a diagnosis, recall eligibility, or proof of completion.

  1. Collect the facts and market. Record year/first registration, make, model, powertrain, trim, mileage and units, location, seller type, equipment, records, defects, and price conditions. Use the relevant platform’s current listing requirements.
  2. Build an evidence ledger. Output claim; source/date; confirmed, seller-reported, or unknown; and permitted wording. Treat “no evidence supplied” as unknown. Do not infer accident history from a clean-looking photo or an auction grade alone.
  3. Resolve material gaps. Ask for missing condition disclosures, mileage history, inspection findings, warranty terms, and price components before calling the draft ready to publish. Keep a conspicuous “needs confirmation” checklist outside the customer-facing draft; do not hide known defects there.
  4. Check the total. Show vehicle price and stated required charges separately from genuinely optional items. Use stated tax treatment without double-counting. If a required charge is unknown, the final payable total remains unconfirmed. For Japan, verify current AFTC guidance and its applicability; do not assume one market’s rules apply elsewhere.
  5. Draft the listing. Return a factual title, short description, specification/condition table, visible known-defect disclosures, price breakdown, photo checklist, and buyer FAQ. Avoid unsupported superlatives, urgency, certification, or warranty promises.
  6. Review before publishing. Cross-check every claim against its source and the current local/platform requirements. Remove private owner details and unnecessary document identifiers from public material. Preserve required public disclosures. Publishing remains a separate action requiring the seller’s instruction.

Limitations