Fix SEO skill 34 bugs, Korean labels, and transition Ahrefs refs to our-seo-agent (#2)

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

@@ -21,11 +21,10 @@ Analyze search engine result page composition for Google and Naver. Detect SERP
 
 ## MCP Tool Usage
 
-### Ahrefs for SERP Data
+### SEO Data
 ```
-mcp__ahrefs__serp-overview: Get SERP results and features for a keyword
-mcp__ahrefs__keywords-explorer-overview: Get keyword metrics, volume, difficulty, and SERP feature flags
-mcp__ahrefs__site-explorer-organic-keywords: Map competitor keyword positions
+our-seo-agent CLI: Primary data source (future); use --input for pre-fetched JSON
+WebSearch / WebFetch: Live SERP data and keyword metrics
 ```
 
 ### Notion for Report Storage
@@ -43,7 +42,7 @@ WebFetch: Fetch Naver SERP HTML for section analysis
 ## Workflow
 
 ### 1. Google SERP Analysis
-1. Fetch SERP data via `mcp__ahrefs__serp-overview` for the target keyword and country
+1. Fetch SERP data via `our-seo-agent` CLI, `--input` JSON, or WebSearch for the target keyword and country
 2. Detect SERP features (featured snippet, PAA, local pack, knowledge panel, video, ads, images, shopping)
 3. Map competitor positions from organic results (domain, URL, title, position)
 4. Classify content type for each result (blog, product, service, news, video)
@@ -107,7 +106,7 @@ WebFetch: Fetch Naver SERP HTML for section analysis
 
 ## Limitations
 
-- Ahrefs SERP data may have a delay (not real-time)
+- SERP data may have a delay depending on data source (not real-time)
 - Naver SERP HTML structure changes periodically
 - Brand zone detection depends on HTML class patterns
 - Cannot detect personalized SERP results