Add 11-seo-comprehensive-audit orchestrator skill

New skill that runs a 6-stage SEO audit pipeline (Technical, On-Page, Core Web Vitals, Schema, Local SEO, Search Console) and produces a unified health score (0-100) with weighted categories. Includes Python orchestrator script, slash command, and Notion integration for Korean audit reports. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-13 02:37:51 +09:00
parent 7c5efea817
commit 930167dbbe
7 changed files with 777 additions and 0 deletions
--- a/custom-skills/11-seo-comprehensive-audit/README.md
+++ b/custom-skills/11-seo-comprehensive-audit/README.md
@@ -0,0 +1,75 @@
+# SEO Comprehensive Audit
+
+종합 SEO 감사 도구 - 6단계 파이프라인을 통한 통합 SEO 진단 및 건강 점수 산출.
+
+## Overview
+
+Orchestrates a unified 6-stage SEO audit by calling sub-skill scripts, merging results, computing a weighted health score (0-100), and pushing a summary report to Notion.
+
+## Pipeline Stages
+
+| # | Stage | Sub-Skill | Weight |
+|---|-------|-----------|--------|
+| 1 | Technical SEO | `12-seo-technical-audit` | 20% |
+| 2 | On-Page SEO | `13-seo-on-page-audit` | 20% |
+| 3 | Core Web Vitals | `14-seo-core-web-vitals` | 25% |
+| 4 | Schema Validation | `16-seo-schema-validator` | 15% |
+| 5 | Local SEO | `18-seo-local-audit` | 10% |
+| 6 | Search Console | `15-seo-search-console` | 10% |
+
+## Dual-Platform Structure
+
+```
+11-seo-comprehensive-audit/
+├── code/                           # Claude Code version
+│   ├── CLAUDE.md                   # Action-oriented directive
+│   ├── commands/
+│   │   └── seo-comprehensive-audit.md  # Slash command
+│   └── scripts/
+│       ├── seo_audit_orchestrator.py   # Python orchestrator
+│       └── requirements.txt
+│
+├── desktop/                        # Claude Desktop version
+│   ├── SKILL.md                    # MCP-based workflow
+│   └── skill.yaml                  # Extended metadata
+│
+└── README.md
+```
+
+## Quick Start
+
+### Claude Code
+```bash
+/seo-comprehensive-audit https://example.com
+/seo-comprehensive-audit https://example.com --skip-local --skip-gsc
+```
+
+### Python Script
+```bash
+pip install -r code/scripts/requirements.txt
+python code/scripts/seo_audit_orchestrator.py --url https://example.com
+```
+
+## Health Score Grading
+
+| Score | Grade | Status |
+|-------|-------|--------|
+| 90-100 | A | Excellent |
+| 80-89 | B+ | Good |
+| 70-79 | B | Above Average |
+| 60-69 | C | Needs Improvement |
+| 40-59 | D | Poor |
+| 0-39 | F | Critical |
+
+## Notion Output
+
+Summary reports are saved to the OurDigital SEO Audit Log database:
+- **Title**: `종합 SEO 감사 보고서 - [domain] - YYYY-MM-DD`
+- **Database ID**: `2c8581e5-8a1e-8035-880b-e38cefc2f3ef`
+- Individual pages created for Critical/High findings
+
+## Triggers
+
+- comprehensive SEO, full SEO audit
+- 종합 SEO 감사, 사이트 감사
+- SEO health check, SEO 건강 점수
--- a/custom-skills/11-seo-comprehensive-audit/code/CLAUDE.md
+++ b/custom-skills/11-seo-comprehensive-audit/code/CLAUDE.md
@@ -0,0 +1,77 @@
+# CLAUDE.md
+
+## Overview
+
+Comprehensive SEO audit orchestrator. Runs 6 sub-skill audits (Technical, On-Page, CWV, Schema, Local, GSC), merges results into a unified report with weighted health score (0-100), and pushes to Notion.
+
+## Quick Start
+
+```bash
+# Install dependencies
+pip install -r scripts/requirements.txt
+
+# Run full audit
+python scripts/seo_audit_orchestrator.py --url https://example.com
+
+# Skip optional stages
+python scripts/seo_audit_orchestrator.py --url https://example.com --skip-local --skip-gsc
+
+# JSON output only (no Notion push)
+python scripts/seo_audit_orchestrator.py --url https://example.com --json
+```
+
+## Scripts
+
+| Script | Purpose |
+|--------|---------|
+| `seo_audit_orchestrator.py` | Orchestrate all 6 audit stages and compute health score |
+
+## Pipeline
+
+| Stage | Audit | Script |
+|-------|-------|--------|
+| 1 | Technical SEO | `12-seo-technical-audit/code/scripts/robots_checker.py`, `sitemap_validator.py` |
+| 2 | On-Page SEO | `13-seo-on-page-audit/code/scripts/page_analyzer.py` |
+| 3 | Core Web Vitals | `14-seo-core-web-vitals/code/scripts/pagespeed_client.py` |
+| 4 | Schema Validation | `16-seo-schema-validator/code/scripts/schema_validator.py` |
+| 5 | Local SEO | `18-seo-local-audit/` (prompt-driven) |
+| 6 | Search Console | `15-seo-search-console/code/scripts/gsc_client.py` |
+
+## Health Score Weights
+
+| Category | Weight |
+|----------|--------|
+| Technical SEO | 20% |
+| On-Page SEO | 20% |
+| Core Web Vitals | 25% |
+| Schema | 15% |
+| Local SEO | 10% |
+| Search Console | 10% |
+
+## Notion Output (Required)
+
+**IMPORTANT**: All audit reports MUST be saved to the OurDigital SEO Audit Log database.
+
+### Database Configuration
+
+| Field | Value |
+|-------|-------|
+| Database ID | `2c8581e5-8a1e-8035-880b-e38cefc2f3ef` |
+| URL | https://www.notion.so/dintelligence/2c8581e58a1e8035880be38cefc2f3ef |
+
+### Required Properties
+
+| Property | Type | Description |
+|----------|------|-------------|
+| Issue | Title | `종합 SEO 감사 보고서 - [domain] - YYYY-MM-DD` |
+| Site | URL | Audited website URL |
+| Category | Select | Comprehensive Audit |
+| Priority | Select | Based on health score |
+| Found Date | Date | Audit date (YYYY-MM-DD) |
+| Audit ID | Rich Text | Format: COMP-YYYYMMDD-NNN |
+
+### Language Guidelines
+
+- Report content in Korean (한국어)
+- Keep technical English terms as-is (e.g., SEO Audit, Core Web Vitals, Schema Markup)
+- URLs and code remain unchanged
--- a/custom-skills/11-seo-comprehensive-audit/code/commands/seo-comprehensive-audit.md
+++ b/custom-skills/11-seo-comprehensive-audit/code/commands/seo-comprehensive-audit.md
@@ -0,0 +1,151 @@
+---
+description: "Comprehensive SEO audit: technical, on-page, schema, CWV, local, and GSC in one unified report"
+argument-hint: <url> [--skip-local] [--skip-gsc] [--skip-notion] [--json]
+allowed-tools: Read, Write, Edit, Bash, Glob, Grep, WebFetch, WebSearch, Task
+---
+
+# Comprehensive SEO Audit
+
+## Overview
+
+Orchestrates a unified 6-stage SEO audit by calling sub-skill scripts sequentially, merging results, computing a weighted health score (0-100), and optionally pushing a summary to Notion.
+
+## Usage
+
+```bash
+/seo-comprehensive-audit https://example.com
+/seo-comprehensive-audit https://example.com --skip-local --skip-gsc
+/seo-comprehensive-audit https://example.com --json
+/seo-comprehensive-audit https://example.com --skip-notion
+```
+
+## Pipeline Stages
+
+| # | Stage | Sub-Skill | Skip Flag |
+|---|-------|-----------|-----------|
+| 1 | Technical SEO | `12-seo-technical-audit` | — |
+| 2 | On-Page SEO | `13-seo-on-page-audit` | — |
+| 3 | Core Web Vitals | `14-seo-core-web-vitals` | — |
+| 4 | Schema Validation | `16-seo-schema-validator` | — |
+| 5 | Local SEO | `18-seo-local-audit` | `--skip-local` |
+| 6 | Search Console | `15-seo-search-console` | `--skip-gsc` |
+
+## Execution
+
+### Option A: Python Orchestrator (Recommended)
+
+```bash
+# Find repo root
+REPO_ROOT=$(git -C /path/to/our-claude-skills rev-parse --show-toplevel)
+SKILLS="$REPO_ROOT/custom-skills"
+
+# Run orchestrator
+python "$SKILLS/11-seo-comprehensive-audit/code/scripts/seo_audit_orchestrator.py" \
+  --url https://example.com \
+  --skills-dir "$SKILLS"
+```
+
+### Option B: Manual Stage-by-Stage
+
+Run each sub-skill script with `--json` flag, then synthesize:
+
+```bash
+# Stage 1: Technical SEO
+python "$SKILLS/12-seo-technical-audit/code/scripts/robots_checker.py" --url $URL --json
+python "$SKILLS/12-seo-technical-audit/code/scripts/sitemap_validator.py" --url "$URL/sitemap.xml" --json
+
+# Stage 2: On-Page SEO
+python "$SKILLS/13-seo-on-page-audit/code/scripts/page_analyzer.py" --url $URL --json
+
+# Stage 3: Core Web Vitals
+python "$SKILLS/14-seo-core-web-vitals/code/scripts/pagespeed_client.py" --url $URL --json
+
+# Stage 4: Schema Validation
+python "$SKILLS/16-seo-schema-validator/code/scripts/schema_validator.py" --url $URL --json
+
+# Stage 5: Local SEO (prompt-driven, use WebFetch + WebSearch)
+# Stage 6: Search Console (requires GSC API credentials)
+```
+
+## Health Score (Weighted 0-100)
+
+| Category | Weight |
+|----------|--------|
+| Technical SEO | 20% |
+| On-Page SEO | 20% |
+| Core Web Vitals | 25% |
+| Schema | 15% |
+| Local SEO | 10% |
+| Search Console | 10% |
+
+Scores per category are normalized to 0-100. Skipped stages redistribute their weight proportionally.
+
+## Output Format
+
+```json
+{
+  "url": "https://example.com",
+  "audit_date": "2025-01-15",
+  "health_score": 72,
+  "grade": "B",
+  "stages": {
+    "technical": {"score": 85, "issues": [], "weight": 0.20},
+    "on_page": {"score": 70, "issues": [], "weight": 0.20},
+    "core_web_vitals": {"score": 60, "issues": [], "weight": 0.25},
+    "schema": {"score": 80, "issues": [], "weight": 0.15},
+    "local_seo": {"score": 65, "issues": [], "weight": 0.10},
+    "search_console": {"score": 75, "issues": [], "weight": 0.10}
+  },
+  "critical_issues": [],
+  "recommendations": []
+}
+```
+
+## Grading Scale
+
+| Score | Grade | Status |
+|-------|-------|--------|
+| 90-100 | A | Excellent |
+| 80-89 | B+ | Good |
+| 70-79 | B | Above Average |
+| 60-69 | C | Needs Improvement |
+| 40-59 | D | Poor |
+| 0-39 | F | Critical |
+
+## Notion Output (Required)
+
+**IMPORTANT**: Summary report MUST be saved to the OurDigital SEO Audit Log database.
+
+### Database Configuration
+
+| Field | Value |
+|-------|-------|
+| Database ID | `2c8581e5-8a1e-8035-880b-e38cefc2f3ef` |
+
+### Summary Page Title
+
+`종합 SEO 감사 보고서 - [domain] - YYYY-MM-DD`
+
+### Required Properties
+
+| Property | Type | Value |
+|----------|------|-------|
+| Issue | Title | `종합 SEO 감사 보고서 - [domain] - YYYY-MM-DD` |
+| Site | URL | Audited website URL |
+| Category | Select | `Comprehensive Audit` |
+| Priority | Select | Based on health score (Critical if <40, High if <60, Medium if <80, Low if ≥80) |
+| Found Date | Date | Audit date (YYYY-MM-DD) |
+| Audit ID | Rich Text | `COMP-YYYYMMDD-001` |
+
+### Individual Issues
+
+Create one Notion page per Critical/High finding with:
+- Appropriate Category (Technical SEO, On-page SEO, Performance, Schema/Structured Data, Local SEO)
+- Priority matching the finding severity
+- Audit ID linking back to the comprehensive audit
+
+### Language Guidelines
+
+- Report content in Korean (한국어)
+- Keep technical English terms as-is (e.g., SEO Audit, Core Web Vitals, Schema Markup)
+- URLs and code remain unchanged
--- a/custom-skills/11-seo-comprehensive-audit/code/scripts/requirements.txt
+++ b/custom-skills/11-seo-comprehensive-audit/code/scripts/requirements.txt
@@ -0,0 +1,5 @@
+# 11-seo-comprehensive-audit dependencies
+# Sub-skill dependencies are managed in their own requirements.txt files
+requests>=2.31.0
+python-dotenv>=1.0.0
+rich>=13.7.0
--- a/custom-skills/11-seo-comprehensive-audit/code/scripts/seo_audit_orchestrator.py
+++ b/custom-skills/11-seo-comprehensive-audit/code/scripts/seo_audit_orchestrator.py
@@ -0,0 +1,348 @@
+#!/usr/bin/env python3
+"""
+SEO Comprehensive Audit Orchestrator
+
+Runs 6 sub-skill audits sequentially, merges results, and computes a weighted
+health score (0-100).
+
+Usage:
+    python seo_audit_orchestrator.py --url https://example.com
+    python seo_audit_orchestrator.py --url https://example.com --skip-local --skip-gsc
+    python seo_audit_orchestrator.py --url https://example.com --json
+"""
+
+import argparse
+import json
+import subprocess
+import sys
+from datetime import datetime
+from pathlib import Path
+from urllib.parse import urlparse
+
+
+# Health score weights (must sum to 1.0)
+WEIGHTS = {
+    "technical": 0.20,
+    "on_page": 0.20,
+    "core_web_vitals": 0.25,
+    "schema": 0.15,
+    "local_seo": 0.10,
+    "search_console": 0.10,
+}
+
+GRADE_THRESHOLDS = [
+    (90, "A", "Excellent"),
+    (80, "B+", "Good"),
+    (70, "B", "Above Average"),
+    (60, "C", "Needs Improvement"),
+    (40, "D", "Poor"),
+    (0, "F", "Critical"),
+]
+
+
+def get_repo_root():
+    """Find the git repository root."""
+    try:
+        result = subprocess.run(
+            ["git", "rev-parse", "--show-toplevel"],
+            capture_output=True, text=True, check=True
+        )
+        return Path(result.stdout.strip())
+    except subprocess.CalledProcessError:
+        # Fallback: walk up from this script's location
+        current = Path(__file__).resolve().parent
+        while current != current.parent:
+            if (current / ".git").exists():
+                return current
+            current = current.parent
+        print("Error: Could not find git repository root.", file=sys.stderr)
+        sys.exit(1)
+
+
+def run_script(script_path, args, stage_name):
+    """Run a sub-skill script and return parsed JSON output."""
+    if not script_path.exists():
+        return {
+            "status": "skipped",
+            "reason": f"Script not found: {script_path}",
+            "score": None,
+            "issues": [],
+        }
+
+    cmd = [sys.executable, str(script_path)] + args + ["--json"]
+    try:
+        result = subprocess.run(
+            cmd, capture_output=True, text=True, timeout=120
+        )
+        if result.returncode == 0 and result.stdout.strip():
+            return json.loads(result.stdout.strip())
+        else:
+            return {
+                "status": "error",
+                "reason": result.stderr.strip() or f"Exit code {result.returncode}",
+                "score": None,
+                "issues": [],
+            }
+    except subprocess.TimeoutExpired:
+        return {
+            "status": "timeout",
+            "reason": f"{stage_name} timed out after 120s",
+            "score": None,
+            "issues": [],
+        }
+    except json.JSONDecodeError as e:
+        return {
+            "status": "error",
+            "reason": f"Invalid JSON output: {e}",
+            "score": None,
+            "issues": [],
+        }
+    except Exception as e:
+        return {
+            "status": "error",
+            "reason": str(e),
+            "score": None,
+            "issues": [],
+        }
+
+
+def extract_score(result):
+    """Extract a 0-100 score from a sub-skill result."""
+    if isinstance(result, dict):
+        # Try common score fields
+        for key in ("score", "health_score", "overall_score"):
+            if key in result and isinstance(result[key], (int, float)):
+                return min(100, max(0, result[key]))
+        # Try nested core_web_vitals score
+        if "core_web_vitals" in result:
+            cwv = result["core_web_vitals"]
+            if isinstance(cwv, dict) and "score" in cwv:
+                return min(100, max(0, cwv["score"]))
+    return None
+
+
+def extract_issues(result):
+    """Extract issues list from a sub-skill result."""
+    if isinstance(result, dict):
+        issues = result.get("issues", [])
+        if isinstance(issues, list):
+            return issues
+    return []
+
+
+def compute_health_score(stages, skipped):
+    """Compute weighted health score, redistributing skipped stage weights."""
+    active_weights = {k: v for k, v in WEIGHTS.items() if k not in skipped}
+    total_active_weight = sum(active_weights.values())
+
+    if total_active_weight == 0:
+        return 0
+
+    weighted_sum = 0
+    for stage_name, weight in active_weights.items():
+        stage_data = stages.get(stage_name, {})
+        score = stage_data.get("score")
+        if score is not None:
+            normalized_weight = weight / total_active_weight
+            weighted_sum += score * normalized_weight
+
+    return round(weighted_sum, 1)
+
+
+def get_grade(score):
+    """Return grade and status for a given score."""
+    for threshold, grade, status in GRADE_THRESHOLDS:
+        if score >= threshold:
+            return grade, status
+    return "F", "Critical"
+
+
+def get_priority(score):
+    """Return Notion priority based on health score."""
+    if score < 40:
+        return "Critical"
+    elif score < 60:
+        return "High"
+    elif score < 80:
+        return "Medium"
+    return "Low"
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Comprehensive SEO Audit Orchestrator")
+    parser.add_argument("--url", required=True, help="URL to audit")
+    parser.add_argument("--skip-local", action="store_true", help="Skip Local SEO stage")
+    parser.add_argument("--skip-gsc", action="store_true", help="Skip Search Console stage")
+    parser.add_argument("--json", action="store_true", help="Output JSON only")
+    parser.add_argument("--skills-dir", help="Path to custom-skills directory")
+    args = parser.parse_args()
+
+    url = args.url
+    domain = urlparse(url).netloc or url
+    audit_date = datetime.now().strftime("%Y-%m-%d")
+    audit_id = f"COMP-{datetime.now().strftime('%Y%m%d')}-001"
+
+    # Resolve skills directory
+    if args.skills_dir:
+        skills_dir = Path(args.skills_dir)
+    else:
+        repo_root = get_repo_root()
+        skills_dir = repo_root / "custom-skills"
+
+    skipped = set()
+    if args.skip_local:
+        skipped.add("local_seo")
+    if args.skip_gsc:
+        skipped.add("search_console")
+
+    stages = {}
+
+    # Stage 1: Technical SEO
+    if not args.json:
+        print("[1/6] Running Technical SEO audit...")
+    robots_result = run_script(
+        skills_dir / "12-seo-technical-audit/code/scripts/robots_checker.py",
+        ["--url", url], "robots_checker"
+    )
+    sitemap_url = f"{url.rstrip('/')}/sitemap.xml"
+    sitemap_result = run_script(
+        skills_dir / "12-seo-technical-audit/code/scripts/sitemap_validator.py",
+        ["--url", sitemap_url], "sitemap_validator"
+    )
+    tech_score = extract_score(robots_result)
+    sitemap_score = extract_score(sitemap_result)
+    if tech_score is not None and sitemap_score is not None:
+        combined_tech_score = round((tech_score + sitemap_score) / 2)
+    elif tech_score is not None:
+        combined_tech_score = tech_score
+    elif sitemap_score is not None:
+        combined_tech_score = sitemap_score
+    else:
+        combined_tech_score = None
+    stages["technical"] = {
+        "score": combined_tech_score,
+        "weight": WEIGHTS["technical"],
+        "issues": extract_issues(robots_result) + extract_issues(sitemap_result),
+        "raw": {"robots": robots_result, "sitemap": sitemap_result},
+    }
+
+    # Stage 2: On-Page SEO
+    if not args.json:
+        print("[2/6] Running On-Page SEO audit...")
+    on_page_result = run_script(
+        skills_dir / "13-seo-on-page-audit/code/scripts/page_analyzer.py",
+        ["--url", url], "page_analyzer"
+    )
+    stages["on_page"] = {
+        "score": extract_score(on_page_result),
+        "weight": WEIGHTS["on_page"],
+        "issues": extract_issues(on_page_result),
+        "raw": on_page_result,
+    }
+
+    # Stage 3: Core Web Vitals
+    if not args.json:
+        print("[3/6] Running Core Web Vitals audit...")
+    cwv_result = run_script(
+        skills_dir / "14-seo-core-web-vitals/code/scripts/pagespeed_client.py",
+        ["--url", url], "pagespeed_client"
+    )
+    stages["core_web_vitals"] = {
+        "score": extract_score(cwv_result),
+        "weight": WEIGHTS["core_web_vitals"],
+        "issues": extract_issues(cwv_result),
+        "raw": cwv_result,
+    }
+
+    # Stage 4: Schema Validation
+    if not args.json:
+        print("[4/6] Running Schema validation...")
+    schema_result = run_script(
+        skills_dir / "16-seo-schema-validator/code/scripts/schema_validator.py",
+        ["--url", url], "schema_validator"
+    )
+    stages["schema"] = {
+        "score": extract_score(schema_result),
+        "weight": WEIGHTS["schema"],
+        "issues": extract_issues(schema_result),
+        "raw": schema_result,
+    }
+
+    # Stage 5: Local SEO
+    if "local_seo" not in skipped:
+        if not args.json:
+            print("[5/6] Local SEO stage (prompt-driven, skipping in script mode)...")
+        stages["local_seo"] = {
+            "score": None,
+            "weight": WEIGHTS["local_seo"],
+            "issues": [],
+            "raw": {"status": "prompt_driven", "note": "Local SEO requires interactive analysis via 18-seo-local-audit"},
+        }
+    else:
+        if not args.json:
+            print("[5/6] Skipping Local SEO...")
+
+    # Stage 6: Search Console
+    if "search_console" not in skipped:
+        if not args.json:
+            print("[6/6] Running Search Console analysis...")
+        gsc_result = run_script(
+            skills_dir / "15-seo-search-console/code/scripts/gsc_client.py",
+            ["--url", url], "gsc_client"
+        )
+        stages["search_console"] = {
+            "score": extract_score(gsc_result),
+            "weight": WEIGHTS["search_console"],
+            "issues": extract_issues(gsc_result),
+            "raw": gsc_result,
+        }
+    else:
+        if not args.json:
+            print("[6/6] Skipping Search Console...")
+
+    # Compute health score
+    health_score = compute_health_score(stages, skipped)
+    grade, status = get_grade(health_score)
+    priority = get_priority(health_score)
+
+    # Collect critical issues
+    critical_issues = []
+    for stage_name, stage_data in stages.items():
+        for issue in stage_data.get("issues", []):
+            if isinstance(issue, dict) and issue.get("type") in ("error", "critical"):
+                critical_issues.append({**issue, "stage": stage_name})
+
+    # Build output
+    output = {
+        "url": url,
+        "domain": domain,
+        "audit_date": audit_date,
+        "audit_id": audit_id,
+        "health_score": health_score,
+        "grade": grade,
+        "status": status,
+        "priority": priority,
+        "skipped_stages": list(skipped),
+        "stages": {
+            k: {
+                "score": v.get("score"),
+                "weight": v.get("weight"),
+                "issues": v.get("issues", []),
+            }
+            for k, v in stages.items()
+        },
+        "critical_issues": critical_issues,
+        "notion": {
+            "database_id": "2c8581e5-8a1e-8035-880b-e38cefc2f3ef",
+            "title": f"종합 SEO 감사 보고서 - {domain} - {audit_date}",
+            "category": "Comprehensive Audit",
+            "priority": priority,
+            "audit_id": audit_id,
+        },
+    }
+
+    print(json.dumps(output, ensure_ascii=False, indent=2))
+
+
+if __name__ == "__main__":
+    main()
--- a/custom-skills/11-seo-comprehensive-audit/desktop/SKILL.md
+++ b/custom-skills/11-seo-comprehensive-audit/desktop/SKILL.md
@@ -0,0 +1,109 @@
+---
+name: seo-comprehensive-audit
+description: |
+  Comprehensive SEO audit orchestrator. Runs 6-stage audit pipeline (Technical, On-Page, CWV, Schema, Local, GSC) and produces a unified report with weighted health score.
+  Triggers: comprehensive SEO, full SEO audit, 종합 SEO 감사, site audit, SEO health check.
+---
+
+# Comprehensive SEO Audit
+
+## Purpose
+
+Orchestrate a full-spectrum SEO audit by running 6 specialized analyses and synthesizing results into a unified health score and actionable report.
+
+## Pipeline Stages
+
+| # | Stage | Source Skill | Default |
+|---|-------|-------------|---------|
+| 1 | Technical SEO | 12-seo-technical-audit | Always |
+| 2 | On-Page SEO | 13-seo-on-page-audit | Always |
+| 3 | Core Web Vitals | 14-seo-core-web-vitals | Always |
+| 4 | Schema Validation | 16-seo-schema-validator | Always |
+| 5 | Local SEO | 18-seo-local-audit | Skippable |
+| 6 | Search Console | 15-seo-search-console | Skippable |
+
+## Workflow
+
+### 1. Initialization
+1. Receive target URL from user
+2. Confirm which stages to run (all 6 by default)
+3. Set up audit tracking ID: `COMP-YYYYMMDD-NNN`
+
+### 2. Execute Stages (Sequential)
+For each active stage:
+1. Run the sub-skill analysis
+2. Collect JSON results
+3. Extract score and issues
+
+### 3. Synthesis
+1. Compute weighted health score (0-100)
+2. Assign grade (A/B+/B/C/D/F)
+3. Prioritize critical and high-severity findings
+4. Generate recommendations
+
+### 4. Notion Report
+1. Create summary page: `종합 SEO 감사 보고서 - [domain] - YYYY-MM-DD`
+2. Create individual pages for Critical/High findings
+3. Database: `2c8581e5-8a1e-8035-880b-e38cefc2f3ef`
+
+## Health Score Weights
+
+| Category | Weight |
+|----------|--------|
+| Technical SEO | 20% |
+| On-Page SEO | 20% |
+| Core Web Vitals | 25% |
+| Schema | 15% |
+| Local SEO | 10% |
+| Search Console | 10% |
+
+Skipped stages redistribute weight proportionally.
+
+## Output Format
+
+```markdown
+## 종합 SEO 감사 보고서: [domain]
+
+**Health Score**: [score]/100 ([grade])
+**Date**: YYYY-MM-DD
+**Audit ID**: COMP-YYYYMMDD-NNN
+
+### Stage Results
+| Stage | Score | Issues |
+|-------|-------|--------|
+| Technical SEO | XX/100 | N issues |
+| On-Page SEO | XX/100 | N issues |
+| Core Web Vitals | XX/100 | N issues |
+| Schema | XX/100 | N issues |
+| Local SEO | XX/100 | N issues |
+| Search Console | XX/100 | N issues |
+
+### Critical Findings
+1. [Finding with recommendation]
+
+### Recommendations (Priority Order)
+1. [Action item]
+```
+
+## MCP Tool Usage
+
+### Firecrawl
+```
+mcp__firecrawl__scrape: Fetch page content for on-page and schema analysis
+```
+
+### Notion
+```
+mcp__notion__*: Create audit report pages in SEO database
+```
+
+### Perplexity
+```
+mcp__perplexity__search: Research best practices for recommendations
+```
+
+## Limitations
+
+- Local SEO stage requires manual input for NAP/GBP data
+- Search Console stage requires GSC API credentials
+- Health score accuracy improves when all 6 stages are active
--- a/custom-skills/11-seo-comprehensive-audit/desktop/skill.yaml
+++ b/custom-skills/11-seo-comprehensive-audit/desktop/skill.yaml
@@ -0,0 +1,12 @@
+# Skill metadata (extracted from SKILL.md frontmatter)
+
+name: seo-comprehensive-audit
+description: |
+  Comprehensive SEO audit orchestrator. Runs 6-stage pipeline (Technical, On-Page, CWV, Schema, Local, GSC) and produces a unified report with weighted health score (0-100).
+  Triggers: comprehensive SEO, full SEO audit, 종합 SEO 감사, site audit, SEO health check.
+
+# Optional fields
+allowed-tools:
+  - mcp__firecrawl__*
+  - mcp__perplexity__*
+  - mcp__notion__*