proposal-makerlisted

<objective> End-to-end commercial-proposal generator. Input: a free-form offer (client block + itemised order with prices + total, usually pasted from Telegram/WhatsApp) and a brand site to copy the look from. Output: a single self-contained `proposal.html` that genuinely **looks like that brand** and prints to a clean PDF. The default is **LLM-authored, screenshot-driven**. A deterministic template can't capture "dark, bold, dramatic brand with a green accent and uppercase display type" — it reads colours by frequency and gets the mood wrong. So instead: a Python step assembles a **brand kit**, and you (the orchestrator) *look at the brand* and *write the markup*. Execute-layer modules under `common/runners/`: 1. `proposal_parse.py` — offer text → structured `skills.proposal.plan.v1` (items, prices, recomputed subtotal, mismatch + outlier flags). 2. `proposal_brand.py` — scrape brand tokens (accent / fonts / logo / name) + enrich each item with its real catalogue photo + description (`og:` tags). 3. `proposal_kit.py` — screenshot the brand site (headless Chrome), download the logo, write `BRIEF.md` bundling tokens + the item table + authoring rules. 4. `proposal_render.py` — the `--quick` deterministic themed template + HTML→PDF helper. Why a document and NOT an image deck: a proposal carries **exact prices** and **clickable product links**. AI image generation garbles both. You write real HTML text. This skill does NOT: generate slides/images (use `carousel-bui