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/20-seo-serp-analysis/code/CLAUDE.md

@@ -59,11 +59,11 @@ python scripts/naver_serp_analyzer.py --keywords-file keywords.txt --json
 ```
 
 **Capabilities**:
-- Naver section detection (블로그, 카페, 지식iN, 스마트스토어, 브랜드존, VIEW탭)
+- Naver section detection (블로그, 카페, 지식iN, 스마트스토어, 브랜드존, 도서, 숏폼, 인플루언서)
 - Section priority mapping (which sections appear above fold)
 - Content type distribution per section
 - Brand zone presence detection
-- VIEW tab content analysis
+- Shortform/influencer content analysis
 
 ## Ahrefs MCP Tools Used
 

custom-skills/20-seo-serp-analysis/code/scripts/naver_serp_analyzer.py

@@ -80,13 +80,6 @@ NAVER_SECTION_SELECTORS: dict[str, list[str]] = {
         "type_brand",
         "sc_new.sp_brand",
     ],
-    "view_tab": [
-        "sp_view",
-        "view_widget",
-        "sc_new.sp_view",
-        "type_view",
-        "api_subject_view",
-    ],
     "news": [
         "sp_nnews",
         "news_widget",
@@ -132,6 +125,26 @@ NAVER_SECTION_SELECTORS: dict[str, list[str]] = {
         "type_ad",
         "nx_ad",
     ],
+    "books": [
+        "sp_book",
+        "sc_new.sp_book",
+        "type_book",
+        "api_subject_book",
+        "nx_book",
+    ],
+    "shortform": [
+        "sp_shortform",
+        "sc_new.sp_shortform",
+        "type_shortform",
+        "sp_shorts",
+        "type_shorts",
+    ],
+    "influencer": [
+        "sp_influencer",
+        "sc_new.sp_influencer",
+        "type_influencer",
+        "api_subject_influencer",
+    ],
 }
 
 # Section display names in Korean
@@ -141,13 +154,15 @@ SECTION_DISPLAY_NAMES: dict[str, str] = {
     "knowledge_in": "지식iN",
     "smart_store": "스마트스토어",
     "brand_zone": "브랜드존",
-    "view_tab": "VIEW",
     "news": "뉴스",
     "encyclopedia": "백과사전",
     "image": "이미지",
     "video": "동영상",
     "place": "플레이스",
     "ad": "광고",
+    "books": "도서",
+    "shortform": "숏폼",
+    "influencer": "인플루언서",
 }
 
 # Default headers for Naver requests
@@ -199,7 +214,6 @@ class NaverSerpResult:
     above_fold_sections: list[str] = field(default_factory=list)
     ad_count: int = 0
     dominant_section: str = ""
-    has_view_tab: bool = False
     has_place_section: bool = False
     timestamp: str = ""
 
@@ -485,7 +499,6 @@ class NaverSerpAnalyzer:
         ad_count = sum(s.item_count for s in ad_sections) if ad_sections else 0
 
         # Check special sections
-        has_view = any(s.section_type == "view_tab" for s in sections)
         has_place = any(s.section_type == "place" for s in sections)
         dominant = self._find_dominant_section(sections)
 
@@ -499,7 +512,6 @@ class NaverSerpAnalyzer:
             above_fold_sections=above_fold,
             ad_count=ad_count,
             dominant_section=dominant,
-            has_view_tab=has_view,
             has_place_section=has_place,
         )
         return result
@@ -534,7 +546,6 @@ def print_rich_report(result: NaverSerpResult) -> None:
     summary_table.add_row("Brand Zone", "Yes" if result.brand_zone_present else "No")
     if result.brand_zone_brand:
         summary_table.add_row("Brand Name", result.brand_zone_brand)
-    summary_table.add_row("VIEW Tab", "Yes" if result.has_view_tab else "No")
     summary_table.add_row("Place Section", "Yes" if result.has_place_section else "No")
     summary_table.add_row("Dominant Section", result.dominant_section or "N/A")
     console.print(summary_table)

custom-skills/20-seo-serp-analysis/desktop/SKILL.md

@@ -17,7 +17,7 @@ Analyze search engine result page composition for Google and Naver. Detect SERP
 2. **Competitor Position Mapping** - Extract domains, positions, content types for top organic results
 3. **Opportunity Scoring** - Score SERP opportunity (0-100) based on feature landscape and competition
 4. **Search Intent Validation** - Infer intent (informational, navigational, commercial, transactional, local) from SERP composition
-5. **Naver SERP Composition** - Detect sections (blog, cafe, knowledge iN, Smart Store, brand zone, VIEW tab), map section priority, analyze brand zone presence
+5. **Naver SERP Composition** - Detect sections (blog, cafe, knowledge iN, Smart Store, brand zone, books, shortform, influencer), map section priority, analyze brand zone presence
 
 ## MCP Tool Usage
 
@@ -53,7 +53,7 @@ WebFetch: Fetch Naver SERP HTML for section analysis
 
 ### 2. Naver SERP Analysis
 1. Fetch Naver search page for the target keyword
-2. Detect SERP sections (blog, cafe, knowledge iN, Smart Store, brand zone, VIEW tab, news, encyclopedia)
+2. Detect SERP sections (blog, cafe, knowledge iN, Smart Store, brand zone, news, encyclopedia, books, shortform, influencer)
 3. Map section priority (above-fold order)
 4. Check brand zone presence and extract brand name
 5. Count items per section