Implement ourdigital-presales-seo skill

SKILL.md orchestration (8 gated stages), references (rate_card.yaml,
findings_to_service rubric, competitor sets), findings.schema.json contract,
and scripts: kg_query.py (generalized KG examination), estimate.py
(findings→rate-card 견적 md/xlsx/json), build_deck.py (9-slide branded PPTX),
render_pdf.sh (Korean PDF via headless Chrome), plus client_brief.html template.

Validated on Sono Hotels & Resorts findings: estimate OD-2026-001
(23-47M KRW) and a 9-slide deck generated cleanly.

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

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

@@ -0,0 +1,89 @@
+---
+name: ourdigital-presales-seo
+description: Standardized pre-sales SEO + Knowledge Graph diagnostic for a prospect domain that produces a technical/on-page scan, KG/entity analysis, consolidated brief, a rate-card-based cost estimate (견적), and an editable PPTX sales deck. Use for pre-sales prospecting, sales briefing prep, "pre-sales SEO audit", "프리세일즈 진단", "견적 + 제안 슬라이드", or when preparing for a prospect meeting. Public-data only (no client GSC/GA4 access required). Korean-first output.
+---
+
+# OurDigital Pre-sales SEO Workflow
+
+Runs the full pre-sales diagnostic for **any prospect domain** as **step-by-step
+confirmed stages**, ending in a cost estimate and a sales-briefing deck. Public-data
+only — designed for prospects where you don't yet have GSC/GA4/GTM access.
+
+Origin: standardizes the Sono Hotels & Resorts pre-sales diagnostic.
+
+## Execution model — STEP BY STEP
+
+Run one stage at a time. After each stage, **present the result and WAIT for the
+user's go-ahead** before the next. Create a TodoWrite/Task item per stage. Stages 5
+(estimate) and 6 (deliverables) are explicit review gates — never send without sign-off.
+
+## Stage 0 — Scope & preflight
+Collect (ask only for what you can't infer):
+- `domain` (required); `brand_name` + `aliases` (앤/& / EN variants — infer from `<title>`/og first)
+- `sub_brands`, `properties` (auto-extract from crawl URL patterns in Stage 1 if not given)
+- `competitors` (else pick a set from `references/competitor_sets.md` by vertical)
+- `market`/`language` (default South Korea / ko), `vertical`
+- `output_dir` — default routing: if `~/Workspaces/<slug>-workspace/` exists →
+  `…/audits/<YYYY-MM-DD>-presales/`, else `~/Workspaces/seo-workspace/prospecting/<YYYY-MM-DD>-<prospect>/`
+
+Preflight tool check (report missing + fallback): Firecrawl, DataForSEO, `GOOGLE_KG_API_KEY`,
+headless Chrome, python-pptx. Create `data/` subfolder. Initialize `findings.json` (see `findings.schema.json`).
+
+## Stage 1 — Discovery & crawl
+- `WebFetch` robots.txt + `/sitemap.xml` + `/sitemap_index.xml` (note status; 500/404 = finding).
+- `firecrawl_map` (limit high, includeSubdomains) → URL inventory; record `discoverable_urls`,
+  derive URL architecture, `estimated_pages`, and hygiene flags (`/test`, params, duplicate path schemes).
+- Populate `findings.json.discovery`. → write scan §1.
+
+## Stage 2 — Technical / on-page
+- `firecrawl_scrape` (json) homepage + 1-2 property pages: JSON-LD `@type`s, Organization completeness
+  (sameAs/alternateName/address), meta/title/H1, hreflang set, robots/googlebot meta.
+- `mcp__dfs-mcp__on_page_lighthouse` homepage (+ a property) → CWV.
+- Populate `findings.json.technical`. → write `01_technical-onpage-scan.md`.
+- **Honesty rule:** never claim "noindexed" if the page ranks — flag conflicting directives as "verify".
+
+## Stage 3 — Knowledge Graph / entity
+- `python scripts/kg_query.py --brand … --aliases … --parent … --legacy … --subbrands … --properties … --competitors … --out-dir <out>/data`
+  (needs `GOOGLE_KG_API_KEY`; run with sandbox disabled — read-only API GET).
+- Live SERP panel verification: `mcp__dfs-mcp__serp_organic_live_advanced` (ko, South Korea) for brand,
+  a sub-brand, a property, and one competitor → record actual panel type/title, local packs, reseller leakage.
+- Populate `findings.json.entity` (panel, name_split, legacy_contamination, sub-brand/property entity counts,
+  competitor_benchmark[], wikipedia). → write `02_knowledge-graph-entity.md` + `data/serp_panels_findings.md`.
+
+## Stage 4 — Consolidated brief
+- Synthesize, rank by severity, build the competitive-gap table. Populate `findings.json.findings[]`.
+  → 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 --out-dir <out> --seq <N>`
+- Produces `05_estimate_ko.md`, `05_estimate.xlsx`, `data/estimate.json`. Present the ranged 견적; get sign-off.
+- Rules in `references/findings_to_service.md`; rates in `references/rate_card.yaml` (edit both together).
+
+## 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),
+  then `bash scripts/render_pdf.sh <brief>.html` → PDF. Verify Korean renders (Read the PDF).
+- **Sales deck**: `python scripts/build_deck.py --findings <out>/data/findings.json --estimate <out>/data/estimate.json --out <out>/sales-deck.pptx`
+- Sanitize the client-facing pieces: no internal pricing strategy beyond the 견적; tasteful competitor benchmark only.
+
+## Stage 7 — Archive (standard)
+Push the consolidated report to the OurDigital SEO Audit DB:
+```
+python <notion-writer path>/notion_writer.py \
+  --database 2c8581e5-8a1e-8035-880b-e38cefc2f3ef \
+  --title "<프로스펙트> SEO 사전진단 (Pre-sales) — <YYYY-MM-DD>" \
+  --properties '{"Target URL": "<domain>", "Audit Date": "<YYYY-MM-DD>", "Account Code": "<CODE>"}' \
+  --file <out>/03_presales-opportunity-brief.md
+```
+Property names are exact: `Target URL`, `Audit Date`, `Account Code`. **Do NOT set `Audit ID`**
+(read-only formula). notion-writer path: `~/Project/our-claude-skills/custom-skills/32-notion-writer/code/scripts/notion_writer.py`.
+
+## Tool gotchas (learned)
+- OurSEO `crawl_website` **caps ~60 pages** regardless of `max_pages` — use Firecrawl `map` for inventory; report the discoverable count as a finding.
+- Firecrawl `scrape` cache may return empty — re-scrape.
+- KG API + headless Chrome + Notion push need network → run those Bash calls with the sandbox disabled.
+- Korean PDF: headless Chrome uses system fonts (AppleSDGothicNeo on macOS). On Windows set deck font to Malgun Gothic in `build_deck.py`.
+
+## Conventions
+- Korean-first for all client-facing output; keep technical terms in English (SEO, CWV, Schema, hreflang).
+- File names: `01_/02_/03_/05_` prefixes as above; raw artifacts in `data/`.
+- Outputs go to the workspace (Stage 0 routing), **never** into this skills repo.

custom-skills/95-ourdigital-presales-seo/findings.schema.json

@@ -0,0 +1,99 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "title": "ourdigital-presales-seo findings contract",
+  "description": "Shared artifact populated by analysis stages 1-4 and consumed by estimate.py (5) and build_deck.py (6). Generators must never re-crawl; they read this file.",
+  "type": "object",
+  "required": ["prospect", "discovery", "technical", "entity", "findings"],
+  "properties": {
+    "prospect": {
+      "type": "object",
+      "required": ["name", "domain"],
+      "properties": {
+        "name": {"type": "string"},
+        "domain": {"type": "string"},
+        "aliases": {"type": "array", "items": {"type": "string"}},
+        "vertical": {"type": "string"},
+        "audit_date": {"type": "string", "description": "YYYY-MM-DD"},
+        "account_code": {"type": "string"}
+      }
+    },
+    "discovery": {
+      "type": "object",
+      "properties": {
+        "sitemap_status": {"type": "integer"},
+        "robots_sitemap_declared": {"type": "boolean"},
+        "discoverable_urls": {"type": "integer"},
+        "estimated_pages": {"type": "string"},
+        "url_hygiene": {"type": "array", "items": {"type": "string"}}
+      }
+    },
+    "technical": {
+      "type": "object",
+      "properties": {
+        "cwv": {
+          "type": "object",
+          "properties": {
+            "lcp_ms": {"type": "number"}, "cls": {"type": "number"},
+            "ttfb_ms": {"type": "number"}, "perf": {"type": "number"}
+          }
+        },
+        "schema": {
+          "type": "object",
+          "properties": {
+            "org": {"type": "string", "enum": ["bare", "complete", "none"]},
+            "hotel_on_property": {"type": "boolean"}
+          }
+        },
+        "meta_dupe": {"type": "boolean"},
+        "title_i18n_mismatch": {"type": "boolean"},
+        "hreflang": {"type": "string", "enum": ["complete", "incomplete", "none"]}
+      }
+    },
+    "entity": {
+      "type": "object",
+      "properties": {
+        "panel": {"type": "string", "enum": ["company", "hotel", "none"]},
+        "name_split": {"type": "boolean"},
+        "legacy_contamination": {"type": "boolean"},
+        "subbrands_with_entity": {"type": "integer"},
+        "subbrands_total": {"type": "integer"},
+        "properties_with_entity": {"type": "integer"},
+        "properties_total": {"type": "integer"},
+        "wikipedia": {"type": "boolean"},
+        "competitor_benchmark": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "properties": {
+              "name": {"type": "string"}, "score": {"type": "number"},
+              "type": {"type": "string"}, "wikipedia": {"type": "boolean"}
+            }
+          }
+        }
+      }
+    },
+    "measurement": {
+      "type": "object",
+      "properties": {
+        "gsc_access": {"type": "boolean"},
+        "ga4_access": {"type": "boolean"},
+        "tag_gaps": {"type": "boolean"}
+      }
+    },
+    "findings": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "required": ["id", "class", "severity"],
+        "properties": {
+          "id": {"type": "string"},
+          "class": {"type": "string", "description": "crawlability|cwv|schema_entity|subbrand_entity|local|measurement|onpage"},
+          "severity": {"type": "string", "enum": ["critical", "high", "medium", "low"]},
+          "title_ko": {"type": "string"},
+          "evidence": {"type": "string"},
+          "recommended_services": {"type": "array", "items": {"type": "string"}}
+        }
+      }
+    }
+  }
+}

custom-skills/95-ourdigital-presales-seo/references/competitor_sets.md

@@ -0,0 +1,23 @@
+# Default competitor benchmark sets (Korean market)
+
+Used by Stage 3 (KG/entity) when the user doesn't supply competitors. Pick the set
+matching the prospect's vertical; pass as `--competitors` to `kg_query.py`.
+
+## hotel_resort (호텔·리조트)
+- 롯데호텔 (Lotte Hotel) — strong KG, LodgingBusiness type, Korean Wikipedia
+- 신라호텔 / 호텔신라 (Shilla)
+- 조선호텔앤리조트 (Josun)
+- 한화리조트 / 한화호텔앤드리조트 (Hanwha)
+- 켄싱턴리조트 (Kensington)
+
+## city_hotel (시티 호텔)
+- 롯데호텔, 신라호텔, 조선호텔, 글래드호텔, 나인트리
+
+## condo_membership (콘도·회원권)
+- 한화리조트, 대명(소노), 한솔오크밸리, 금호리조트
+
+## benchmark_signals
+For each competitor record in `findings.json.entity.competitor_benchmark`:
+`{name, score (KG result_score), type (@type), wikipedia (bool)}`.
+The benchmark table contrasts the prospect's entity strength/type/Wikipedia
+presence against these — the core competitive-gap visual in the deck.

custom-skills/95-ourdigital-presales-seo/references/findings_to_service.md

@@ -0,0 +1,26 @@
+# Findings → service rubric
+
+How `estimate.py` maps detected findings (from `findings.json`) to `rate_card.yaml`
+service lines. The script reads the structured signals below; this file is the
+human-readable source of truth for the rules.
+
+| Trigger (signal in findings.json) | Service line(s) | Scope driver |
+|---|---|---|
+| `discovery.sitemap_status != 200` OR `discovery.robots_sitemap_declared == false` OR `discovery.discoverable_urls` low vs `estimated_pages` | `technical_audit` + `technical_remediation` | site size / # templates |
+| `technical.cwv.perf < 0.5` OR `cls > 0.1` OR `lcp_ms > 2500` OR `ttfb_ms > 600` | `technical_audit` (if not already) + `technical_remediation` | # templates |
+| `technical.schema.org == "bare"/"none"` OR `entity.panel != "hotel"` OR `entity.name_split` OR `entity.legacy_contamination` OR `entity.subbrands_with_entity == 0` | `schema_build` (one-time) + `onpage_entity` (retainer) | # sub-brands + # properties |
+| `entity.properties_with_entity == 0` OR `url_hygiene` contains GBP/local mismatch | `local_seo` | # properties |
+| `findings[].class` includes measurement gap / no GSC-GA4 | `ga4_impl` and/or `dashboard` (+ `gtm_setup` if tag gaps) | — |
+| `technical.meta_dupe` OR `technical.title_i18n_mismatch` OR `technical.hreflang == "incomplete"` | `onpage_entity` | # templates |
+
+**Severity → priority** (for the brief/deck ordering, not pricing):
+- `critical`: crawl/index blocking, CWV failing, entity mistyped
+- `high`: entity/sub-brand gaps, duplicate URLs, meta dupes
+- `medium`: hreflang, H1, hygiene
+
+**Quantity rules**
+- `monthly` line items use `rate_card.defaults.retainer_months` (default 6).
+- `local_seo` scope note scales with property count (`entity` / discovery counts).
+- One-time items counted once even if triggered by multiple findings.
+
+Edit this file and `rate_card.yaml` together when rates or rules change.

custom-skills/95-ourdigital-presales-seo/references/rate_card.yaml

@@ -0,0 +1,51 @@
+# OurDigital service rate card — single source for estimate.py
+# Mirrors the ourdigital-backoffice quote ranges. Values are KRW, treated as
+# pre-sales estimate RANGES (finalize after a precise diagnostic with access).
+quote_prefix: OD          # quote number format: OD-YYYY-NNN
+currency: KRW
+
+services:
+  technical_audit:
+    label_ko: "Technical Audit / 기술 SEO 진단"
+    unit: one_time          # one_time | monthly | project
+    min: 3000000
+    max: 5000000
+  technical_remediation:
+    label_ko: "기술 개선 실행 (sitemap/CWV/SSR)"
+    unit: project
+    min: 3000000
+    max: 8000000
+  onpage_entity:
+    label_ko: "On-Page / Entity Optimization (월 운영)"
+    unit: monthly
+    min: 1500000
+    max: 3000000
+  schema_build:
+    label_ko: "구조화 데이터(Schema) 구축 (1회)"
+    unit: one_time
+    min: 2000000
+    max: 4000000
+  local_seo:
+    label_ko: "Local SEO (프로퍼티 로컬 최적화)"
+    unit: monthly
+    min: 1000000
+    max: 2000000
+  gtm_setup:
+    label_ko: "GTM Setup / 태그 관리 구축"
+    unit: project
+    min: 2000000
+    max: 4000000
+  ga4_impl:
+    label_ko: "GA4 Implementation / 분석 환경 구축"
+    unit: project
+    min: 1500000
+    max: 3000000
+  dashboard:
+    label_ko: "Dashboard Development / 대시보드 개발"
+    unit: project
+    min: 3000000
+    max: 6000000
+
+defaults:
+  retainer_months: 6        # default contract length for monthly line items
+  disclaimer_ko: "본 견적은 공개 데이터 기반 사전 추정 범위이며, Search Console/Analytics 권한 확보 후 정밀 진단을 통해 확정됩니다."

custom-skills/95-ourdigital-presales-seo/scripts/build_deck.py

@@ -0,0 +1,315 @@
+#!/usr/bin/env python3
+"""Build an editable OurDigital-branded sales-briefing deck (PPTX) for pre-sales SEO.
+
+Part of the ourdigital-presales-seo skill (Stage 6). Reads findings.json (+ optional
+estimate.json) and writes a 9-slide .pptx. Content is populated from data; text stays
+editable in PowerPoint/Keynote.
+
+Usage:
+  python build_deck.py --findings findings.json --estimate data/estimate.json \
+    --out sales-deck.pptx
+"""
+import argparse
+import json
+
+from pptx import Presentation
+from pptx.dml.color import RGBColor
+from pptx.enum.shapes import MSO_SHAPE
+from pptx.enum.text import PP_ALIGN
+from pptx.util import Inches, Pt
+
+NAVY = RGBColor(0x11, 0x24, 0x3D)
+ACCENT = RGBColor(0x1B, 0x6F, 0xB3)
+LIGHT = RGBColor(0xF3, 0xF7, 0xFB)
+GREY = RGBColor(0x6B, 0x77, 0x87)
+WHITE = RGBColor(0xFF, 0xFF, 0xFF)
+RED = RGBColor(0xC0, 0x39, 0x2B)
+FONT = "Apple SD Gothic Neo"   # macOS Korean; edit in deck if on Windows (Malgun Gothic)
+
+EMU_W, EMU_H = Inches(13.333), Inches(7.5)
+
+
+def _style(run, size, color=NAVY, bold=False):
+    run.font.size = Pt(size)
+    run.font.bold = bold
+    run.font.color.rgb = color
+    run.font.name = FONT
+
+
+def textbox(slide, l, t, w, h, lines, align=PP_ALIGN.LEFT):
+    """lines: list of (text, size, color, bold) or list of such lists (paragraphs)."""
+    tb = slide.shapes.add_textbox(Inches(l), Inches(t), Inches(w), Inches(h))
+    tf = tb.text_frame
+    tf.word_wrap = True
+    if lines and not isinstance(lines[0], list):
+        lines = [lines]
+    for idx, para in enumerate(lines):
+        p = tf.paragraphs[0] if idx == 0 else tf.add_paragraph()
+        p.alignment = align
+        p.space_after = Pt(4)
+        # para is a list of runs: each (text, size, color, bold)
+        if para and isinstance(para[0], str):
+            para = [tuple(para)]
+        for (text, size, color, bold) in para:
+            r = p.add_run()
+            r.text = text
+            _style(r, size, color, bold)
+    return tb
+
+
+def bar(slide, l, t, w, h, color=ACCENT):
+    shp = slide.shapes.add_shape(MSO_SHAPE.RECTANGLE, Inches(l), Inches(t), Inches(w), Inches(h))
+    shp.fill.solid()
+    shp.fill.fore_color.rgb = color
+    shp.line.fill.background()
+    shp.shadow.inherit = False
+    return shp
+
+
+def blank(prs):
+    return prs.slides.add_slide(prs.slide_layouts[6])
+
+
+def fill_bg(slide, color):
+    slide.background.fill.solid()
+    slide.background.fill.fore_color.rgb = color
+
+
+def header(slide, kicker, title):
+    bar(slide, 0.6, 0.55, 0.12, 0.9)
+    textbox(slide, 0.85, 0.5, 11.8, 1.1, [
+        [(kicker, 11, ACCENT, True)],
+        [(title, 24, NAVY, True)],
+    ])
+
+
+def card(slide, l, t, w, h, fill=LIGHT):
+    shp = slide.shapes.add_shape(MSO_SHAPE.ROUNDED_RECTANGLE, Inches(l), Inches(t), Inches(w), Inches(h))
+    shp.fill.solid()
+    shp.fill.fore_color.rgb = fill
+    shp.line.color.rgb = RGBColor(0xDC, 0xE7, 0xF1)
+    shp.line.width = Pt(0.75)
+    shp.shadow.inherit = False
+    return shp
+
+
+def finding_slide(prs, kicker, title, headline, bullets, metric=None):
+    s = blank(prs)
+    header(s, kicker, title)
+    if metric:
+        card(s, 0.85, 1.95, 3.5, 4.6, NAVY)
+        textbox(s, 1.0, 2.5, 3.2, 3.5, [
+            [(metric[0], 40, WHITE, True)],
+            [(metric[1], 13, RGBColor(0xCF, 0xDD, 0xEE), False)],
+        ])
+        bx = 4.7
+    else:
+        bx = 0.85
+    rows = [[(headline, 15, NAVY, True)]]
+    for b in bullets:
+        rows.append([("•  ", 12, ACCENT, True), (b, 12, RGBColor(0x33, 0x3A, 0x45), False)])
+    textbox(s, bx, 2.1, 13.0 - bx - 0.6, 4.4, rows)
+    return s
+
+
+def main():
+    ap = argparse.ArgumentParser(description="Build pre-sales SEO sales deck (PPTX)")
+    ap.add_argument("--findings", required=True)
+    ap.add_argument("--estimate", default=None)
+    ap.add_argument("--out", default="sales-deck.pptx")
+    args = ap.parse_args()
+
+    with open(args.findings, encoding="utf-8") as fh:
+        F = json.load(fh)
+    EST = None
+    if args.estimate:
+        try:
+            with open(args.estimate, encoding="utf-8") as fh:
+                EST = json.load(fh)
+        except FileNotFoundError:
+            EST = None
+
+    p = F.get("prospect", {})
+    name = p.get("name", "(프로스펙트)")
+    date = p.get("audit_date", "")
+    d = F.get("discovery", {})
+    t = F.get("technical", {})
+    e = F.get("entity", {})
+
+    prs = Presentation()
+    prs.slide_width, prs.slide_height = EMU_W, EMU_H
+
+    # 1) Title
+    s = blank(prs)
+    fill_bg(s, NAVY)
+    bar(s, 0.9, 2.7, 1.6, 0.14, ACCENT)
+    textbox(s, 0.9, 2.9, 11.5, 3.0, [
+        [("SEO PRE-SALES BRIEF", 13, RGBColor(0x7F, 0xA8, 0xCF), True)],
+        [(f"{name}", 40, WHITE, True)],
+        [("검색 가시성 사전 진단", 26, RGBColor(0xCF, 0xDD, 0xEE), True)],
+        [(f"OurDigital  ·  {date}  ·  공개 데이터 기준 사전 스냅샷", 12, RGBColor(0x9F, 0xB4, 0xCC), False)],
+    ])
+
+    # 2) Overview
+    s = blank(prs)
+    header(s, "OVERVIEW", "한눈에 보기")
+    card(s, 0.85, 1.95, 11.6, 1.7)
+    textbox(s, 1.1, 2.15, 11.1, 1.4, [
+        [(f"{name}는 국내 최대급 호텔·리조트 자산을 보유하지만, ", 14, NAVY, False),
+         ("검색에서의 디지털 가시성은 그 규모에 미치지 못합니다.", 14, ACCENT, True)],
+    ])
+    textbox(s, 0.95, 3.95, 11.6, 2.6, [
+        [("핵심 병목 두 가지", 14, NAVY, True)],
+        [("①  기술 — ", 13, RED, True), ('"보이지 않는 사이트": 색인·CWV 문제로 발견 가능 페이지가 극소수', 13, RGBColor(0x33, 0x3A, 0x45), False)],
+        [("②  엔티티 — ", 13, RED, True), ('"잘못 인식된 브랜드": 회사 타입·표기 분열·레거시 잔존, 서브브랜드 부재', 13, RGBColor(0x33, 0x3A, 0x45), False)],
+    ])
+
+    # 3) Finding 1 — crawl/index
+    finding_slide(
+        prs, "FINDING 01", "크롤링 / 색인 — 사이트가 검색엔진에 보이지 않습니다",
+        '사이트맵 오류와 크롤성 한계로 대부분의 페이지가 발견·색인되지 못합니다.',
+        [
+            f"sitemap 상태: HTTP {d.get('sitemap_status', 'N/A')}" + (" (정상)" if d.get('sitemap_status') == 200 else " — 오류/미동작"),
+            "robots.txt 사이트맵 선언: " + ("있음" if d.get("robots_sitemap_declared") else "없음"),
+            f"추정 전체 페이지: {d.get('estimated_pages', 'N/A')}",
+            "위생 이슈: " + (", ".join(d.get("url_hygiene", [])) or "없음"),
+        ],
+        metric=(str(d.get("discoverable_urls", "—")), "외부 발견 가능 URL (개)"),
+    )
+
+    # 4) Finding 2 — CWV
+    cwv = t.get("cwv", {})
+    finding_slide(
+        prs, "FINDING 02", "Core Web Vitals — 속도·안정성 취약",
+        "구글 순위 요소이자 예약 전환·모바일 경험에 직접 영향을 줍니다.",
+        [
+            f"LCP {cwv.get('lcp_ms', 0)/1000:.1f}초 (기준 <2.5초)",
+            f"TTFB {cwv.get('ttfb_ms', 0)/1000:.1f}초 (기준 <0.6초)",
+            f"Performance score {cwv.get('perf', 0):.2f} (기준 ≥0.9)",
+        ],
+        metric=(f"{cwv.get('cls', 0):.3f}", "CLS (화면 밀림) · 기준 <0.1"),
+    )
+
+    # 5) Finding 3 — entity recognition
+    panel_ko = {"company": '"회사"로만 인식 (호텔 아님)', "hotel": "호텔로 인식", "none": "지식패널 없음"}
+    finding_slide(
+        prs, "FINDING 03", "엔티티 인식 — 구글이 브랜드를 호텔로 보지 않습니다",
+        "호텔 전용 검색 노출에 불리하고 리브랜딩 효과가 검색에 반영되지 못합니다.",
+        [
+            "지식패널 분류: " + panel_ko.get(e.get("panel"), "확인 필요"),
+            "브랜드 표기 분열(앤 vs &): " + ("있음" if e.get("name_split") else "없음"),
+            "레거시(구 브랜드명) 잔존: " + ("있음" if e.get("legacy_contamination") else "없음"),
+            "Korean Wikipedia 등재: " + ("있음" if e.get("wikipedia") else "없음"),
+        ],
+    )
+
+    # 6) Finding 4 — subbrand/competitor
+    s = finding_slide(
+        prs, "FINDING 04", "서브브랜드·프로퍼티 엔티티 + 경쟁 벤치마크",
+        "다(多)브랜드 체계가 검색 자산으로 축적되지 못하고 있습니다.",
+        [
+            f"서브브랜드 엔티티: {e.get('subbrands_with_entity', 0)} / {e.get('subbrands_total', 0)}",
+            f"프로퍼티 엔티티: {e.get('properties_with_entity', 0)} / {e.get('properties_total', 0)}",
+        ],
+    )
+    bench = e.get("competitor_benchmark", [])
+    if bench:
+        rows = min(len(bench) + 1, 7)
+        tbl = s.shapes.add_table(rows, 4, Inches(7.0), Inches(2.4), Inches(5.5), Inches(0.4 * rows)).table
+        for j, htxt in enumerate(["브랜드", "KG 강도", "타입", "위키"]):
+            c = tbl.cell(0, j)
+            c.text = htxt
+            c.fill.solid()
+            c.fill.fore_color.rgb = NAVY
+            for para in c.text_frame.paragraphs:
+                for r in para.runs:
+                    _style(r, 11, WHITE, True)
+        for i, b in enumerate(bench[:rows - 1], 1):
+            vals = [b.get("name", ""), str(int(b.get("score", 0))), b.get("type", ""), "○" if b.get("wikipedia") else "—"]
+            for j, v in enumerate(vals):
+                c = tbl.cell(i, j)
+                c.text = v
+                for para in c.text_frame.paragraphs:
+                    for r in para.runs:
+                        _style(r, 10, NAVY, False)
+
+    # 7) Roadmap
+    s = blank(prs)
+    header(s, "ROADMAP", "개선 로드맵")
+    phases = [
+        ("Phase 0 · 긴급 기술 복구", "사이트맵 복구 · CWV(CLS/LCP/TTFB) · 중복 URL canonical", ACCENT),
+        ("Phase 1 · 엔티티 정합", "Organization/Hotel schema · 표기 통일 · 서브브랜드/프로퍼티 엔티티 · Wikipedia", NAVY),
+        ("Phase 2 · 콘텐츠·로컬·확장", "프로퍼티 로컬 SEO · 브랜드 체계 콘텐츠 · Naver · AI 검색 가시성", GREY),
+    ]
+    for i, (h, body, col) in enumerate(phases):
+        top = 2.1 + i * 1.55
+        card(s, 0.85, top, 11.6, 1.35)
+        bar(s, 0.85, top, 0.14, 1.35, col)
+        textbox(s, 1.15, top + 0.18, 11.0, 1.1, [
+            [(h, 15, col, True)],
+            [(body, 12, RGBColor(0x33, 0x3A, 0x45), False)],
+        ])
+
+    # 8) Estimate
+    s = blank(prs)
+    header(s, "ESTIMATE", "예상 견적 (사전 추정 범위)")
+    if EST:
+        items = EST.get("line_items", [])
+        rows = min(len(items) + 1, 9)
+        tbl = s.shapes.add_table(rows, 3, Inches(0.85), Inches(2.0), Inches(11.6), Inches(0.45 * rows)).table
+        tbl.columns[0].width = Inches(6.0)
+        tbl.columns[1].width = Inches(2.0)
+        tbl.columns[2].width = Inches(3.6)
+        for j, htxt in enumerate(["항목", "단위", "금액(범위)"]):
+            c = tbl.cell(0, j)
+            c.text = htxt
+            c.fill.solid()
+            c.fill.fore_color.rgb = NAVY
+            for para in c.text_frame.paragraphs:
+                for r in para.runs:
+                    _style(r, 12, WHITE, True)
+        unit_ko = {"one_time": "1회", "project": "프로젝트", "monthly": "월"}
+        for i, it in enumerate(items[:rows - 1], 1):
+            amt = f"{it['amount_min']:,}~{it['amount_max']:,}원"
+            for j, v in enumerate([it["label"], unit_ko.get(it["unit"], it["unit"]), amt]):
+                c = tbl.cell(i, j)
+                c.text = v
+                for para in c.text_frame.paragraphs:
+                    for r in para.runs:
+                        _style(r, 11, NAVY, False)
+        tot = EST.get("totals", {})
+        textbox(s, 0.85, 2.0 + 0.45 * rows + 0.2, 11.6, 1.2, [
+            [("총계(범위): ", 14, NAVY, True),
+             (f"{tot.get('grand_min', 0):,} ~ {tot.get('grand_max', 0):,}원", 14, RED, True)],
+            [(EST.get("disclaimer", ""), 10, GREY, False)],
+        ])
+    else:
+        textbox(s, 0.85, 2.2, 11.6, 1.0, [[("견적 데이터(estimate.json) 미연결 — estimate.py 실행 후 재생성", 13, GREY, False)]])
+
+    # 9) Next steps
+    s = blank(prs)
+    fill_bg(s, NAVY)
+    bar(s, 0.9, 1.0, 1.6, 0.14, ACCENT)
+    textbox(s, 0.9, 1.2, 11.5, 1.2, [
+        [("NEXT STEPS", 13, RGBColor(0x7F, 0xA8, 0xCF), True)],
+        [("다음 단계", 30, WHITE, True)],
+    ])
+    steps = [
+        ("1.  30분 미팅", "진단 결과 공유 및 우선순위 논의"),
+        ("2.  정밀 진단", "Search Console·Analytics 권한 확보 후 색인·트래픽·키워드 정량 분석"),
+        ("3.  단기 파일럿", "긴급 기술 복구(사이트맵·CWV)부터 빠른 가시 성과"),
+    ]
+    for i, (h, body) in enumerate(steps):
+        top = 2.8 + i * 1.2
+        textbox(s, 1.1, top, 11.0, 1.1, [
+            [(h, 17, WHITE, True)],
+            [(body, 12, RGBColor(0xCF, 0xDD, 0xEE), False)],
+        ])
+    textbox(s, 1.1, 6.7, 11.0, 0.5, [[("OurDigital · andrew.yim@ourdigital.org", 11, RGBColor(0x9F, 0xB4, 0xCC), False)]])
+
+    prs.save(args.out)
+    print(f"Wrote {args.out} ({len(prs.slides)} slides)")
+
+
+if __name__ == "__main__":
+    main()

custom-skills/95-ourdigital-presales-seo/scripts/estimate.py

@@ -0,0 +1,203 @@
+#!/usr/bin/env python3
+"""Generate a ranged 견적 (estimate) from findings.json using the OurDigital rate card.
+
+Part of the ourdigital-presales-seo skill (Stage 5). Maps detected findings to
+rate-card service lines (see references/findings_to_service.md) and emits:
+  - 05_estimate_ko.md   (Korean line-item quote)
+  - data/estimate.json  (consumed by build_deck.py)
+  - 05_estimate.xlsx    (spreadsheet quote)
+
+Usage:
+  python estimate.py --findings findings.json --rate-card ../references/rate_card.yaml \
+    --out-dir ./audits/2026-05-27-presales --seq 1
+"""
+import argparse
+import datetime
+import json
+import os
+
+import yaml
+from openpyxl import Workbook
+from openpyxl.styles import Alignment, Font, PatternFill
+
+
+def won(n):
+    return f"{n:,}원"
+
+
+def select_services(f):
+    """Return {service_key: [reasons]} based on findings signals."""
+    chosen = {}
+    d = f.get("discovery", {})
+    t = f.get("technical", {})
+    e = f.get("entity", {})
+    m = f.get("measurement", {})
+
+    def need(key, reason):
+        chosen.setdefault(key, [])
+        if reason not in chosen[key]:
+            chosen[key].append(reason)
+
+    # Crawlability / indexation
+    if d.get("sitemap_status", 200) != 200 or d.get("robots_sitemap_declared", True) is False:
+        need("technical_audit", "sitemap/robots 색인 이슈")
+        need("technical_remediation", "sitemap 복구·크롤성 개선")
+    # Core Web Vitals
+    cwv = t.get("cwv", {})
+    if (cwv.get("perf", 1) < 0.5 or cwv.get("cls", 0) > 0.1
+            or cwv.get("lcp_ms", 0) > 2500 or cwv.get("ttfb_ms", 0) > 600):
+        need("technical_audit", "Core Web Vitals 취약")
+        need("technical_remediation", "CWV(CLS/LCP/TTFB) 개선")
+    # Schema / entity
+    if (t.get("schema", {}).get("org") in ("bare", "none") or e.get("panel") != "hotel"
+            or e.get("name_split") or e.get("legacy_contamination")
+            or (e.get("subbrands_with_entity", 0) == 0 and e.get("subbrands_total", 0) > 0)):
+        need("schema_build", "Organization/Hotel schema·브랜드 표기 정합")
+        need("onpage_entity", "엔티티·서브브랜드 최적화")
+    # Local
+    hygiene = " ".join(d.get("url_hygiene", [])).lower()
+    if ((e.get("properties_with_entity", 0) == 0 and e.get("properties_total", 0) > 0)
+            or "local" in hygiene or "gbp" in hygiene or "dup_path" in hygiene):
+        need("local_seo", "프로퍼티 로컬·GBP 정합")
+    # Measurement
+    if m.get("gsc_access") is False or m.get("ga4_access") is False:
+        need("ga4_impl", "측정 환경(GA4) 구축")
+        need("dashboard", "리포팅 대시보드 구축")
+    if m.get("tag_gaps"):
+        need("gtm_setup", "태그 관리(GTM) 구축")
+    # On-page hygiene
+    if t.get("meta_dupe") or t.get("title_i18n_mismatch") or t.get("hreflang") == "incomplete":
+        need("onpage_entity", "Meta/Title/hreflang 정리")
+    return chosen
+
+
+def build_line_items(chosen, rate):
+    months = rate["defaults"]["retainer_months"]
+    order = {"one_time": 0, "project": 1, "monthly": 2}
+    items = []
+    for key, reasons in chosen.items():
+        svc = rate["services"][key]
+        unit = svc["unit"]
+        qty = months if unit == "monthly" else 1
+        items.append({
+            "key": key, "label": svc["label_ko"], "unit": unit, "qty": qty,
+            "unit_min": svc["min"], "unit_max": svc["max"],
+            "amount_min": svc["min"] * qty, "amount_max": svc["max"] * qty,
+            "reason": "; ".join(reasons),
+        })
+    items.sort(key=lambda x: order.get(x["unit"], 9))
+    return items, months
+
+
+def totals(items):
+    one = [i for i in items if i["unit"] != "monthly"]
+    mon = [i for i in items if i["unit"] == "monthly"]
+    return {
+        "one_time_min": sum(i["amount_min"] for i in one),
+        "one_time_max": sum(i["amount_max"] for i in one),
+        "monthly_min": sum(i["amount_min"] for i in mon),
+        "monthly_max": sum(i["amount_max"] for i in mon),
+        "grand_min": sum(i["amount_min"] for i in items),
+        "grand_max": sum(i["amount_max"] for i in items),
+    }
+
+
+UNIT_KO = {"one_time": "1회", "project": "프로젝트", "monthly": "월"}
+
+
+def write_md(path, quote_no, date, prospect, items, tot, months, disclaimer):
+    L = [f"# 견적서 (Pre-sales 추정) — {prospect}",
+         "", f"- **견적번호**: {quote_no}", f"- **작성일**: {date}",
+         f"- **대상**: {prospect}", f"- **공급자**: OurDigital (andrew.yim@ourdigital.org)",
+         "", "## 견적 내역", "",
+         "| 항목 | 근거 | 단위 | 수량 | 단가(범위) | 금액(범위) |",
+         "|---|---|---|---:|---|---|"]
+    for i in items:
+        L.append(f"| {i['label']} | {i['reason']} | {UNIT_KO.get(i['unit'], i['unit'])} | {i['qty']} | "
+                 f"{won(i['unit_min'])}~{won(i['unit_max'])} | {won(i['amount_min'])}~{won(i['amount_max'])} |")
+    L += ["", "## 합계 (범위)", "",
+          f"- 일회성/프로젝트: **{won(tot['one_time_min'])} ~ {won(tot['one_time_max'])}**",
+          f"- 월 운영({months}개월 기준): **{won(tot['monthly_min'])} ~ {won(tot['monthly_max'])}**",
+          f"- 총계: **{won(tot['grand_min'])} ~ {won(tot['grand_max'])}**",
+          "", f"> {disclaimer}"]
+    with open(path, "w", encoding="utf-8") as fh:
+        fh.write("\n".join(L) + "\n")
+
+
+def write_xlsx(path, quote_no, date, prospect, items, tot, months, disclaimer):
+    wb = Workbook()
+    ws = wb.active
+    ws.title = "견적"
+    hdr = PatternFill("solid", fgColor="11243D")
+    hf = Font(color="FFFFFF", bold=True)
+    ws.append([f"견적서 (Pre-sales 추정) — {prospect}"])
+    ws.append([f"견적번호 {quote_no}", f"작성일 {date}", "공급자 OurDigital"])
+    ws.append([])
+    cols = ["항목", "근거", "단위", "수량", "단가 min", "단가 max", "금액 min", "금액 max"]
+    ws.append(cols)
+    for c in range(1, len(cols) + 1):
+        cell = ws.cell(row=ws.max_row, column=c)
+        cell.fill = hdr
+        cell.font = hf
+    for i in items:
+        ws.append([i["label"], i["reason"], UNIT_KO.get(i["unit"], i["unit"]), i["qty"],
+                   i["unit_min"], i["unit_max"], i["amount_min"], i["amount_max"]])
+    ws.append([])
+    ws.append(["일회성/프로젝트 합계", "", "", "", "", "", tot["one_time_min"], tot["one_time_max"]])
+    ws.append([f"월 운영 합계 ({months}개월)", "", "", "", "", "", tot["monthly_min"], tot["monthly_max"]])
+    ws.append(["총계", "", "", "", "", "", tot["grand_min"], tot["grand_max"]])
+    ws.cell(row=ws.max_row, column=1).font = Font(bold=True)
+    ws.append([])
+    ws.append([disclaimer])
+    widths = [34, 30, 8, 6, 12, 12, 14, 14]
+    for idx, w in enumerate(widths, 1):
+        ws.column_dimensions[chr(64 + idx)].width = w
+    wb.save(path)
+
+
+def main():
+    ap = argparse.ArgumentParser(description="Generate ranged 견적 from findings.json")
+    ap.add_argument("--findings", required=True)
+    ap.add_argument("--rate-card", required=True)
+    ap.add_argument("--out-dir", default=".")
+    ap.add_argument("--seq", type=int, default=1, help="quote sequence number (NNN)")
+    args = ap.parse_args()
+
+    with open(args.findings, encoding="utf-8") as fh:
+        f = json.load(fh)
+    with open(args.rate_card, encoding="utf-8") as fh:
+        rate = yaml.safe_load(fh)
+
+    prospect = f.get("prospect", {}).get("name", "(prospect)")
+    date = f.get("prospect", {}).get("audit_date") or datetime.date.today().isoformat()
+    year = date[:4]
+    quote_no = f"{rate.get('quote_prefix', 'OD')}-{year}-{args.seq:03d}"
+    disclaimer = rate["defaults"]["disclaimer_ko"]
+
+    chosen = select_services(f)
+    items, months = build_line_items(chosen, rate)
+    tot = totals(items)
+
+    os.makedirs(args.out_dir, exist_ok=True)
+    data_dir = os.path.join(args.out_dir, "data")
+    os.makedirs(data_dir, exist_ok=True)
+
+    md_path = os.path.join(args.out_dir, "05_estimate_ko.md")
+    xlsx_path = os.path.join(args.out_dir, "05_estimate.xlsx")
+    json_path = os.path.join(data_dir, "estimate.json")
+
+    write_md(md_path, quote_no, date, prospect, items, tot, months, disclaimer)
+    write_xlsx(xlsx_path, quote_no, date, prospect, items, tot, months, disclaimer)
+    with open(json_path, "w", encoding="utf-8") as fh:
+        json.dump({"quote_no": quote_no, "date": date, "prospect": prospect,
+                   "line_items": items, "totals": tot, "retainer_months": months,
+                   "disclaimer": disclaimer}, fh, ensure_ascii=False, indent=2)
+
+    print(f"견적 {quote_no}: {len(items)} line items | "
+          f"one-time {won(tot['one_time_min'])}~{won(tot['one_time_max'])} | "
+          f"monthly {won(tot['monthly_min'])}~{won(tot['monthly_max'])}/{months}mo")
+    print(f"Wrote: {md_path}\n       {xlsx_path}\n       {json_path}")
+
+
+if __name__ == "__main__":
+    main()

custom-skills/95-ourdigital-presales-seo/scripts/kg_query.py

@@ -0,0 +1,141 @@
+#!/usr/bin/env python3
+"""Query Google Knowledge Graph (Korean) for a prospect's brand ecosystem + competitors.
+
+Part of the ourdigital-presales-seo skill (Stage 3). Generalized from the
+Sono Hotels & Resorts pre-sales script: entities are built from CLI args, not
+hardcoded. Read-only GET to kgsearch.googleapis.com.
+
+Key resolution: env GOOGLE_KG_API_KEY -> GOOGLE_API_KEY.
+
+Example:
+  python kg_query.py --brand "소노호텔앤리조트" \
+    --aliases "소노호텔&리조트,SONO Hotels & Resorts" \
+    --parent "소노인터내셔널" --legacy "대명소노그룹,대명리조트" \
+    --subbrands "소노벨,소노캄,소노펠리체,쏠비치,소노문" \
+    --properties "소노벨 비발디파크,소노캄 제주,쏠비치 양양" \
+    --competitors "롯데호텔,신라호텔,조선호텔앤리조트,한화리조트,켄싱턴리조트" \
+    --out-dir ./data
+"""
+import argparse
+import json
+import os
+import sys
+import time
+import urllib.parse
+import urllib.request
+
+API_KEY = os.environ.get("GOOGLE_KG_API_KEY") or os.environ.get("GOOGLE_API_KEY")
+ENDPOINT = "https://kgsearch.googleapis.com/v1/entities:search"
+LODGING = {"Hotel", "LodgingBusiness", "Resort", "Place", "TouristAttraction"}
+
+
+def query_kg(q, lang, limit):
+    params = {"query": q, "key": API_KEY, "languages": lang, "limit": limit, "indent": "true"}
+    url = ENDPOINT + "?" + urllib.parse.urlencode(params)
+    req = urllib.request.Request(url, headers={"User-Agent": "OurDigital-SEO-Audit/1.0"})
+    with urllib.request.urlopen(req, timeout=30) as resp:
+        return json.loads(resp.read().decode("utf-8"))
+
+
+def flatten(label, group, data):
+    rows = []
+    for item in data.get("itemListElement", []):
+        r = item.get("result", {})
+        detail = r.get("detailedDescription", {}) or {}
+        rows.append({
+            "group": group, "input_label": label, "kg_id": r.get("@id"),
+            "name": r.get("name"), "types": r.get("@type"), "description": r.get("description"),
+            "result_score": item.get("resultScore"), "has_detailed_desc": bool(detail.get("articleBody")),
+            "detailed_source": detail.get("url"), "image": (r.get("image") or {}).get("contentUrl"),
+            "url": r.get("url"),
+        })
+    if not rows:
+        rows.append({"group": group, "input_label": label, "kg_id": None, "name": None,
+                     "types": None, "description": "NO KG ENTITY FOUND", "result_score": 0,
+                     "has_detailed_desc": False, "detailed_source": None, "image": None, "url": None})
+    return rows
+
+
+def build_entities(args):
+    ents = []
+
+    def add(group, raw):
+        for it in (raw or "").split(","):
+            it = it.strip()
+            if it:
+                ents.append((group, it, it))
+
+    add("01_master", args.brand)
+    add("01_master", args.aliases)
+    add("02_corporate", args.parent)
+    add("03_legacy", args.legacy)
+    add("04_membership", args.membership)
+    add("05_subbrand", args.subbrands)
+    add("06_property", args.properties)
+    add("09_competitor", args.competitors)
+    return ents
+
+
+def main():
+    ap = argparse.ArgumentParser(description="KG entity examination for pre-sales SEO")
+    ap.add_argument("--brand", required=True, help="Master brand (comma-separated allowed)")
+    ap.add_argument("--aliases", default="", help="Brand name variants (& vs 앤, EN)")
+    ap.add_argument("--parent", default="", help="Parent / corporate entity")
+    ap.add_argument("--legacy", default="", help="Former / legacy names")
+    ap.add_argument("--membership", default="", help="Membership / sales-rep units")
+    ap.add_argument("--subbrands", default="", help="Sub-brands")
+    ap.add_argument("--properties", default="", help="Flagship properties")
+    ap.add_argument("--competitors", default="", help="Competitor benchmarks")
+    ap.add_argument("--lang", default="ko")
+    ap.add_argument("--limit", type=int, default=30)
+    ap.add_argument("--out-dir", default=".")
+    args = ap.parse_args()
+
+    if not API_KEY:
+        sys.exit("ERROR: set GOOGLE_KG_API_KEY or GOOGLE_API_KEY in the environment.")
+
+    ents = build_entities(args)
+    raw, flat = {}, []
+    for group, label, q in ents:
+        try:
+            data = query_kg(q, args.lang, args.limit)
+            raw[label] = data
+            flat.extend(flatten(label, group, data))
+        except Exception as e:  # network/quota — record, continue
+            raw[label] = {"error": str(e)}
+            flat.append({"group": group, "input_label": label, "kg_id": None, "name": None,
+                         "types": None, "description": f"ERROR: {e}", "result_score": 0,
+                         "has_detailed_desc": False, "detailed_source": None, "image": None, "url": None})
+        time.sleep(0.3)
+
+    os.makedirs(args.out_dir, exist_ok=True)
+    with open(os.path.join(args.out_dir, "kg_korean_raw.json"), "w", encoding="utf-8") as f:
+        json.dump(raw, f, ensure_ascii=False, indent=2)
+    with open(os.path.join(args.out_dir, "kg_korean_flat.json"), "w", encoding="utf-8") as f:
+        json.dump(flat, f, ensure_ascii=False, indent=2)
+
+    # Console summary: top match per input label + lodging-type flag
+    by_label = {}
+    for r in flat:
+        e = by_label.setdefault(r["input_label"], {"group": r["group"], "n": 0, "lodging": False, "top": r})
+        e["group"] = r["group"]
+        if r.get("kg_id"):
+            e["n"] += 1
+        if set(r.get("types") or []) & LODGING:
+            e["lodging"] = True
+        if (r.get("result_score") or 0) > (e["top"].get("result_score") or 0):
+            e["top"] = r
+
+    print(f"{'GROUP':<14}{'SCORE':>8} {'#':>3} {'LODG':<5} {'TOP TYPE':<22} {'DESC':<5} INPUT -> TOP KG NAME")
+    print("-" * 120)
+    for lbl, e in sorted(by_label.items(), key=lambda kv: kv[1]["group"]):
+        top = e["top"]
+        ttype = ",".join((top.get("types") or [])[:2]) or "-"
+        print(f"{e['group']:<14}{top.get('result_score') or 0:>8.0f} {e['n']:>3} "
+              f"{('YES' if e['lodging'] else '-'):<5} {ttype[:22]:<22} "
+              f"{('yes' if top.get('has_detailed_desc') else 'no'):<5} {lbl[:40]} -> {top.get('name') or '(NONE)'}")
+    print(f"\nWrote kg_korean_raw.json + kg_korean_flat.json to {args.out_dir}")
+
+
+if __name__ == "__main__":
+    main()

custom-skills/95-ourdigital-presales-seo/scripts/render_pdf.sh

@@ -0,0 +1,18 @@
+#!/usr/bin/env bash
+# Render an HTML brief to PDF via headless Chrome (uses system fonts → Korean OK).
+# Part of ourdigital-presales-seo (Stage 6).
+# Usage: render_pdf.sh <input.html> [output.pdf]
+set -euo pipefail
+HTML="${1:?usage: render_pdf.sh <input.html> [output.pdf]}"
+OUT="${2:-${HTML%.html}.pdf}"
+
+CHROME="/Applications/Google Chrome.app/Contents/MacOS/Google Chrome"
+if [ ! -x "$CHROME" ]; then CHROME="/Applications/Brave Browser.app/Contents/MacOS/Brave Browser"; fi
+if [ ! -x "$CHROME" ]; then CHROME="/Applications/Microsoft Edge.app/Contents/MacOS/Microsoft Edge"; fi
+if [ ! -x "$CHROME" ]; then echo "ERROR: no Chromium-based browser found for PDF rendering" >&2; exit 1; fi
+
+DIR="$(cd "$(dirname "$HTML")" && pwd)"
+BASE="$(basename "$HTML")"
+"$CHROME" --headless --disable-gpu --no-pdf-header-footer \
+  --print-to-pdf="$OUT" "file://$DIR/$BASE" 2>/dev/null
+echo "Wrote $OUT"

custom-skills/95-ourdigital-presales-seo/templates/client_brief.html

@@ -0,0 +1,69 @@
+<!DOCTYPE html>
+<!--
+  Client-facing pre-sales brief template (Korean). Stage 6.
+  HOW TO USE: copy this file into the engagement output folder, then fill the
+  {{TOKENS}} (and the four finding blocks) with the engagement's findings — keep
+  the CSS as-is. Render to PDF with: bash scripts/render_pdf.sh <thisfile>.html
+  Keep it ~1 page. Sanitize: no internal pricing strategy; tasteful competitor note only.
+-->
+<html lang="ko">
+<head>
+<meta charset="UTF-8">
+<title>{{PROSPECT}} 검색 가시성 사전 진단</title>
+<style>
+  @page { size: A4; margin: 16mm 15mm 14mm 15mm; }
+  * { box-sizing: border-box; }
+  html, body { margin: 0; padding: 0; }
+  body { font-family: "Apple SD Gothic Neo", "AppleGothic", "Noto Sans KR", sans-serif;
+         color: #1f2733; font-size: 10.6pt; line-height: 1.6; -webkit-print-color-adjust: exact; }
+  .accent { color: #1b6fb3; }
+  header { border-bottom: 3px solid #1b6fb3; padding-bottom: 10px; margin-bottom: 14px; }
+  header .kicker { font-size: 8.5pt; letter-spacing: .14em; color: #1b6fb3; font-weight: 700; text-transform: uppercase; }
+  header h1 { font-size: 19pt; margin: 4px 0 2px; color: #11243d; }
+  header .meta { font-size: 8.6pt; color: #6b7787; }
+  .disclaimer { font-size: 8pt; color: #8a93a0; font-style: italic; margin-top: 4px; }
+  h2 { font-size: 12.5pt; color: #11243d; margin: 18px 0 8px; padding-left: 9px; border-left: 4px solid #1b6fb3; }
+  .lead { background: #f3f7fb; border: 1px solid #dce7f1; border-radius: 7px; padding: 11px 14px; font-size: 10.4pt; }
+  .card { border: 1px solid #e2e8f0; border-radius: 7px; padding: 10px 13px; margin: 9px 0; page-break-inside: avoid; }
+  .card .n { display: inline-block; min-width: 20px; height: 20px; line-height: 20px; text-align: center;
+            background: #1b6fb3; color: #fff; border-radius: 50%; font-size: 9pt; font-weight: 700; margin-right: 7px; }
+  .card h3 { display: inline; font-size: 11pt; color: #11243d; }
+  .card ul { margin: 7px 0 6px; padding-left: 20px; }
+  .why { font-size: 9.4pt; color: #334; background: #fbf6ec; border-left: 3px solid #e0a73c; padding: 5px 9px; border-radius: 3px; }
+  .why b { color: #9a6a12; }
+  .num { color: #c0392b; font-weight: 700; }
+  .two { display: flex; gap: 14px; }
+  .two > div { flex: 1; }
+  .box { border: 1px solid #e2e8f0; border-radius: 7px; padding: 10px 13px; }
+  ol.next { margin: 4px 0; padding-left: 18px; }
+  footer { margin-top: 16px; border-top: 1px solid #e2e8f0; padding-top: 7px; font-size: 8.2pt; color: #8a93a0; }
+</style>
+</head>
+<body>
+<header>
+  <div class="kicker">SEO Pre-sales Brief · OurDigital</div>
+  <h1>{{PROSPECT}} <span class="accent">검색 가시성 사전 진단</span></h1>
+  <div class="meta">작성: OurDigital · {{DATE}} · 대상: {{DOMAIN}}</div>
+  <div class="disclaimer">* 본 자료는 공개 데이터만으로 수행한 사전 스냅샷이며, Search Console 등 권한 확보 후 정밀 진단으로 보완됩니다.</div>
+</header>
+
+<div class="lead">{{ONE_LINER — 자산은 최상급이나 검색 가시성이 규모에 미치지 못한다는 핵심 메시지}}</div>
+
+<h2>핵심 발견</h2>
+<!-- Repeat this card for each headline finding (recommended 3-4). -->
+<div class="card">
+  <span class="n">1</span><h3>{{FINDING_TITLE}}</h3>
+  <ul><li>{{EVIDENCE_BULLET}} <span class="num">{{KEY_METRIC}}</span></li></ul>
+  <div class="why"><b>왜 중요한가</b> — {{WHY_IT_MATTERS}}</div>
+</div>
+
+<div class="two">
+  <div class="box"><h2 style="margin-top:0;">기대 효과</h2>{{EXPECTED_IMPACT}}</div>
+  <div class="box"><h2 style="margin-top:0;">다음 단계 제안</h2>
+    <ol class="next"><li><b>30분 미팅</b></li><li><b>정밀 진단</b> (권한 확보 후)</li><li><b>단기 파일럿</b></li></ol>
+  </div>
+</div>
+
+<footer>OurDigital · andrew.yim@ourdigital.org · 공개 데이터 기준 사전 진단 ({{DATE}})</footer>
+</body>
+</html>