dossier-builderlisted
Install: claude install-skill DaizeDong/buy-me-a-car
# Decision Dossier Builder
Deliver the buying report from the evidence already collected. A broad buying
workflow includes this artifact without a separate request for detail or a PDF.
The agent prepares the config; do not ask the buyer to populate schema fields.
## Choose the document purpose first
| Purpose | Generator | Evidence needed |
|---|---|---|
| Buyer research and shortlisting | `generate_research_report.py` | Dated source coverage, candidate listings, analysis and explicit unknowns. Zero written dealer quotes is allowed. |
| Dealer-facing purchase proposal | `generate_dossier.py` | Complete competing written OTD quotes, supported facts and an itemized authorized proposal. |
The first is the default during market research. The second is a later outward
document. Do not make the proposal's two-quote or complete-fee requirement block
useful research. Both have separate demo/live privacy modes; research versus
proposal is not the same choice as synthetic versus real data.
## Generate the buyer research packet
Follow [report delivery](../orchestrator/references/report_delivery.md). Reuse the
current private cycle, criteria and captured evidence. Produce substantive
comparisons, configuration tradeoffs, delivered-cost uncertainties, suitability,
ownership risks, shortlist rationale and next actions, rather than a long intake
questionnaire or validation log. Use the
[research schema](references/research_schema.md) to assemble structured input.
```sh
python skills/