Add SEO skills 33-34 and fix bugs in skills 19-34

New skills:
- Skill 33: Site migration planner with redirect mapping and monitoring
- Skill 34: Reporting dashboard with HTML charts and Korean executive reports

Bug fixes (Skill 34 - report_aggregator.py):
- Add audit_type fallback for skill identification (was only using audit_id prefix)
- Extract health scores from nested data dict (technical_score, onpage_score, etc.)
- Support subdomain matching in domain filter (blog.ourdigital.org matches ourdigital.org)
- Skip self-referencing DASH- aggregated reports

Bug fixes (Skill 20 - naver_serp_analyzer.py):
- Remove VIEW tab selectors (removed by Naver in 2026)
- Add new section detectors: books (도서), shortform (숏폼), influencer (인플루언서)

Improvements (Skill 34 - dashboard/executive report):
- Add Korean category labels for Chart.js charts (기술 SEO, 온페이지, etc.)
- Add Korean trend labels (개선 중 ↑, 안정 →, 하락 중 ↓)
- Add English→Korean issue description translation layer (20 common patterns)

Documentation improvements:
- Add Korean triggers to 4 skill descriptions (19, 25, 28, 31)
- Expand Skill 32 SKILL.md from 40→143 lines (was 6/10, added workflow, output format, limitations)
- Add output format examples to Skills 27 and 28 SKILL.md
- Add limitations sections to Skills 27 and 28
- Update README.md, CLAUDE.md, AGENTS.md for skills 33-34

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

custom-skills/27-seo-ai-visibility/desktop/SKILL.md

@@ -57,6 +57,55 @@ All reports are saved to the OurDigital SEO Audit Log:
 - **Audit ID Format**: AI-YYYYMMDD-NNN
 - **Language**: Korean (technical terms in English)
 
+## Output Format
+
+```json
+{
+  "domain": "example.com",
+  "impressions": {
+    "total": 15000,
+    "trend": "increasing",
+    "period": "30d"
+  },
+  "mentions": {
+    "total": 450,
+    "positive": 320,
+    "neutral": 100,
+    "negative": 30,
+    "sentiment_score": 0.72
+  },
+  "share_of_voice": {
+    "domain_sov": 12.5,
+    "competitors": {
+      "competitor1.com": 18.3,
+      "competitor2.com": 15.1
+    }
+  },
+  "cited_pages": [
+    {"url": "https://example.com/guide", "citations": 45},
+    {"url": "https://example.com/faq", "citations": 28}
+  ],
+  "cited_domains": [
+    {"domain": "example.com", "citations": 120},
+    {"domain": "competitor1.com", "citations": 95}
+  ],
+  "recommendations": [
+    "Create more FAQ-style content for AI citation capture",
+    "Add structured data to improve AI answer extraction"
+  ],
+  "audit_id": "AI-20250115-001",
+  "timestamp": "2025-01-15T14:30:00"
+}
+```
+
+## Limitations
+
+- Requires Ahrefs Brand Radar API access (not available in basic plans)
+- AI search landscape changes rapidly; data may not reflect real-time state
+- Share of Voice metrics are relative to tracked competitor set only
+- Sentiment analysis based on AI-generated text, not user perception
+- Cannot distinguish between different AI engines (ChatGPT, Gemini, Perplexity) without Brand Radar
+
 ## Example Queries
 
 - "example.com의 AI 검색 가시성을 분석해줘"