Extract ourdigital-estimate-engine; presales-seo now calls it

New skill 96-ourdigital-estimate-engine: method-aware quoting engine
(effort / coaching / procurement) with universal rate_card + per-service
catalog. Real catalogs: seo (effort), education (coaching); stubs:
digital_ads, digital_branding. Validated to reproduce real quotes —
SEO basic ₩10.5M / treatment ₩25.0M, SHR chain ₩29.5M, L'Escape basic
₩10.5M, GA4/GTM coaching ₩1,570,000, procurement +15%.

Refactor 95-ourdigital-presales-seo: remove rate_card.yaml, sow_templates.yaml,
estimate.py (migrated to engine); add findings_to_scope.py; Stage 5 now maps
findings→scope.json and calls the engine CLI. build_deck/kg_query unchanged;
end-to-end validated on SHR (29.5M) + deck renders engine estimate.json.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

custom-skills/95-ourdigital-presales-seo/SKILL.md

@@ -55,10 +55,12 @@ headless Chrome, python-pptx. Create `data/` subfolder. Initialize `findings.jso
   → write `03_presales-opportunity-brief.md`.
 
 ## Stage 5 — Estimate (견적) — REVIEW GATE
-- `python scripts/estimate.py --findings <out>/data/findings.json --rate-card references/rate_card.yaml --sow references/sow_templates.yaml --out-dir <out> --seq <N> [--baseline basic|treatment] [--billing 0.70]`
-- **Effort-based** (OurDigital real model): cost = role_rate × 청구율 × 표준 업무시간, by module; 제안가 = 합계 절사. findings auto-select a tier (**smb / basic / treatment**) and scale **On-page** hours sub-linearly by `subbrands_total` (cap ×2.0); Technical is fixed. `smb` tier bills at 0.55, others 0.70. Override with `--baseline` / `--billing`. Premium verticals (luxury/5성/특1급…) are auto-floored to `basic` via `rate_card.tiering` (so a luxury single property won't drop to `smb`).
-- Produces `05_estimate_ko.md`, `05_estimate.xlsx`, `data/estimate.json`. Present the 견적; get sign-off.
-- Logic in `references/findings_to_service.md`; rates/hours in `rate_card.yaml` + `sow_templates.yaml` (edit together). Reproduces real Basic ₩10.5M / Treatment ₩25.0M; SMB entry ~₩3M; chains stay SMB-acceptable (e.g. 25-property → ~₩29.5M).
+Pricing is delegated to the **`ourdigital-estimate-engine`** skill (`../96-ourdigital-estimate-engine`); this skill only maps findings → scope, then calls the engine:
+- `python scripts/findings_to_scope.py --findings <out>/data/findings.json --out <out>/data/scope.json --seq <N> [--tier auto|smb|basic|treatment] [--billing 0.70]`
+- `ENG=../96-ourdigital-estimate-engine; python $ENG/scripts/estimate.py --rate-card $ENG/references/rate_card.yaml --catalog-dir $ENG/catalog --scope <out>/data/scope.json --out-dir <out>`
+- Engine (effort method, `seo` catalog): auto-tier (smb/basic/treatment) by portfolio + premium-vertical floor; On-page hours scale by `subbrands_total` (cap ×2.0); 제안가 = 합계 절사. Reproduces Basic ₩10.5M / Treatment ₩25.0M; SMB ~₩3M; 25-property chain ~₩29.5M.
+- Produces `05_estimate_ko.md`, `05_estimate.xlsx`, `data/estimate.json` (effort shape → consumed by `build_deck.py`). Present the 견적; get sign-off.
+- SEO findings→scope/tier mapping lives here (`findings_to_service.md`); **rates/hours/tiers live in the engine** (`rate_card.yaml` + `catalog/seo.yaml`) — edit pricing there, not here.
 
 ## Stage 6 — Deliverables — REVIEW GATE before send
 - **Client PDF**: author the short brief HTML from `templates/client_brief.html` (fill the content; keep the CSS),