Add SEO skills 19-28, 31-32 with full Python implementations

12 new skills: Keyword Strategy, SERP Analysis, Position Tracking, Link Building, Content Strategy, E-Commerce SEO, KPI Framework, International SEO, AI Visibility, Knowledge Graph, Competitor Intel, and Crawl Budget. ~20K lines of Python across 25 domain scripts. Updated skill 11 pipeline table and repo CLAUDE.md. Enhanced skill 18 local SEO workflow from jamie.clinic audit. Note: Skill 26 hreflang_validator.py pending (content filter block). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-13 12:05:59 +09:00
parent 159f7ec3f7
commit a3ff965b87
125 changed files with 25948 additions and 173 deletions
--- a/custom-skills/21-seo-position-tracking/code/CLAUDE.md
+++ b/custom-skills/21-seo-position-tracking/code/CLAUDE.md
@@ -0,0 +1,148 @@
+# CLAUDE.md
+
+## Overview
+
+Position tracking tool for monitoring keyword rankings via Ahrefs Rank Tracker. Monitors ranking positions, detects position changes with threshold alerts, calculates visibility scores weighted by search volume, compares against competitors, and segments by brand/non-brand keywords.
+
+## Quick Start
+
+```bash
+pip install -r scripts/requirements.txt
+
+# Track positions for a project
+python scripts/position_tracker.py --target https://example.com --json
+
+# Generate ranking report
+python scripts/ranking_reporter.py --target https://example.com --period 30 --json
+```
+
+## Scripts
+
+| Script | Purpose | Key Output |
+|--------|---------|------------|
+| `position_tracker.py` | Monitor keyword ranking positions and detect changes | Position data, change alerts, visibility scores |
+| `ranking_reporter.py` | Generate ranking performance reports with trends | Trend analysis, segment reports, competitor comparison |
+| `base_client.py` | Shared utilities | RateLimiter, ConfigManager, BaseAsyncClient |
+
+## Position Tracker
+
+```bash
+# Get current positions
+python scripts/position_tracker.py --target https://example.com --json
+
+# With change threshold alerts (flag positions that moved +-5 or more)
+python scripts/position_tracker.py --target https://example.com --threshold 5 --json
+
+# Filter by keyword segment
+python scripts/position_tracker.py --target https://example.com --segment brand --json
+
+# Compare with competitors
+python scripts/position_tracker.py --target https://example.com --competitor https://comp1.com --json
+```
+
+**Capabilities**:
+- Current ranking position retrieval via Ahrefs Rank Tracker
+- Position change detection with configurable threshold alerts
+- Visibility score calculation (weighted by search volume)
+- Brand vs non-brand keyword segmentation
+- Competitor rank comparison
+- Keyword segment grouping (by intent, cluster, landing page)
+
+## Ranking Reporter
+
+```bash
+# 30-day ranking report
+python scripts/ranking_reporter.py --target https://example.com --period 30 --json
+
+# Quarterly comparison
+python scripts/ranking_reporter.py --target https://example.com --period 90 --json
+
+# Export with competitor comparison
+python scripts/ranking_reporter.py --target https://example.com --competitor https://comp1.com --period 30 --json
+```
+
+**Capabilities**:
+- Period-over-period ranking trends (improved/declined/stable)
+- Top movers (biggest position gains/losses)
+- Visibility score trend over time
+- Segment-level performance breakdown
+- Competitor overlap and position comparison
+- Average position by keyword group
+
+## Ahrefs MCP Tools Used
+
+| Tool | Purpose |
+|------|---------|
+| `rank-tracker-overview` | Get rank tracking overview for project |
+| `rank-tracker-competitors-overview` | Compare against competitors |
+| `rank-tracker-competitors-pages` | Competitor page-level rankings |
+| `rank-tracker-competitors-stats` | Competitor ranking statistics |
+| `rank-tracker-serp-overview` | SERP details for tracked keywords |
+| `management-projects` | List Ahrefs projects |
+| `management-project-keywords` | Get tracked keywords for project |
+
+## Output Format
+
+```json
+{
+  "target": "https://example.com",
+  "total_keywords": 250,
+  "visibility_score": 68.5,
+  "positions": {
+    "top3": 15,
+    "top10": 48,
+    "top20": 92,
+    "top50": 180,
+    "top100": 230
+  },
+  "changes": {
+    "improved": 45,
+    "declined": 30,
+    "stable": 155,
+    "new": 12,
+    "lost": 8
+  },
+  "alerts": [
+    {
+      "keyword": "치과 임플란트 가격",
+      "old_position": 5,
+      "new_position": 15,
+      "change": -10,
+      "volume": 5400
+    }
+  ],
+  "segments": {
+    "brand": {"keywords": 30, "avg_position": 2.1},
+    "non_brand": {"keywords": 220, "avg_position": 24.5}
+  },
+  "timestamp": "2025-01-01T00:00:00"
+}
+```
+
+## 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 | Report title (Korean + date) |
+| Site | URL | Tracked website URL |
+| Category | Select | Position Tracking |
+| Priority | Select | Based on visibility trend |
+| Found Date | Date | Tracking date (YYYY-MM-DD) |
+| Audit ID | Rich Text | Format: RANK-YYYYMMDD-NNN |
+
+### Language Guidelines
+
+- Report content in Korean (한국어)
+- Keep technical English terms as-is (e.g., Visibility Score, SERP, Rank Tracker)
+- URLs and code remain unchanged
--- a/custom-skills/21-seo-position-tracking/code/scripts/base_client.py
+++ b/custom-skills/21-seo-position-tracking/code/scripts/base_client.py
@@ -0,0 +1,207 @@
+"""
+Base Client - Shared async client utilities
+===========================================
+Purpose: Rate-limited async operations for API clients
+Python: 3.10+
+"""
+
+import asyncio
+import logging
+import os
+from asyncio import Semaphore
+from datetime import datetime
+from typing import Any, Callable, TypeVar
+
+from dotenv import load_dotenv
+from tenacity import (
+    retry,
+    stop_after_attempt,
+    wait_exponential,
+    retry_if_exception_type,
+)
+
+# Load environment variables
+load_dotenv()
+
+# Logging setup
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s - %(levelname)s - %(message)s",
+)
+
+T = TypeVar("T")
+
+
+class RateLimiter:
+    """Rate limiter using token bucket algorithm."""
+
+    def __init__(self, rate: float, per: float = 1.0):
+        """
+        Initialize rate limiter.
+
+        Args:
+            rate: Number of requests allowed
+            per: Time period in seconds (default: 1 second)
+        """
+        self.rate = rate
+        self.per = per
+        self.tokens = rate
+        self.last_update = datetime.now()
+        self._lock = asyncio.Lock()
+
+    async def acquire(self) -> None:
+        """Acquire a token, waiting if necessary."""
+        async with self._lock:
+            now = datetime.now()
+            elapsed = (now - self.last_update).total_seconds()
+            self.tokens = min(self.rate, self.tokens + elapsed * (self.rate / self.per))
+            self.last_update = now
+
+            if self.tokens < 1:
+                wait_time = (1 - self.tokens) * (self.per / self.rate)
+                await asyncio.sleep(wait_time)
+                self.tokens = 0
+            else:
+                self.tokens -= 1
+
+
+class BaseAsyncClient:
+    """Base class for async API clients with rate limiting."""
+
+    def __init__(
+        self,
+        max_concurrent: int = 5,
+        requests_per_second: float = 3.0,
+        logger: logging.Logger | None = None,
+    ):
+        """
+        Initialize base client.
+
+        Args:
+            max_concurrent: Maximum concurrent requests
+            requests_per_second: Rate limit
+            logger: Logger instance
+        """
+        self.semaphore = Semaphore(max_concurrent)
+        self.rate_limiter = RateLimiter(requests_per_second)
+        self.logger = logger or logging.getLogger(self.__class__.__name__)
+        self.stats = {
+            "requests": 0,
+            "success": 0,
+            "errors": 0,
+            "retries": 0,
+        }
+
+    @retry(
+        stop=stop_after_attempt(3),
+        wait=wait_exponential(multiplier=1, min=2, max=10),
+        retry=retry_if_exception_type(Exception),
+    )
+    async def _rate_limited_request(
+        self,
+        coro: Callable[[], Any],
+    ) -> Any:
+        """Execute a request with rate limiting and retry."""
+        async with self.semaphore:
+            await self.rate_limiter.acquire()
+            self.stats["requests"] += 1
+            try:
+                result = await coro()
+                self.stats["success"] += 1
+                return result
+            except Exception as e:
+                self.stats["errors"] += 1
+                self.logger.error(f"Request failed: {e}")
+                raise
+
+    async def batch_requests(
+        self,
+        requests: list[Callable[[], Any]],
+        desc: str = "Processing",
+    ) -> list[Any]:
+        """Execute multiple requests concurrently."""
+        try:
+            from tqdm.asyncio import tqdm
+            has_tqdm = True
+        except ImportError:
+            has_tqdm = False
+
+        async def execute(req: Callable) -> Any:
+            try:
+                return await self._rate_limited_request(req)
+            except Exception as e:
+                return {"error": str(e)}
+
+        tasks = [execute(req) for req in requests]
+
+        if has_tqdm:
+            results = []
+            for coro in tqdm.as_completed(tasks, total=len(tasks), desc=desc):
+                result = await coro
+                results.append(result)
+            return results
+        else:
+            return await asyncio.gather(*tasks, return_exceptions=True)
+
+    def print_stats(self) -> None:
+        """Print request statistics."""
+        self.logger.info("=" * 40)
+        self.logger.info("Request Statistics:")
+        self.logger.info(f"  Total Requests: {self.stats['requests']}")
+        self.logger.info(f"  Successful: {self.stats['success']}")
+        self.logger.info(f"  Errors: {self.stats['errors']}")
+        self.logger.info("=" * 40)
+
+
+class ConfigManager:
+    """Manage API configuration and credentials."""
+
+    def __init__(self):
+        load_dotenv()
+
+    @property
+    def google_credentials_path(self) -> str | None:
+        """Get Google service account credentials path."""
+        # Prefer SEO-specific credentials, fallback to general credentials
+        seo_creds = os.path.expanduser("~/.credential/ourdigital-seo-agent.json")
+        if os.path.exists(seo_creds):
+            return seo_creds
+        return os.getenv("GOOGLE_APPLICATION_CREDENTIALS")
+
+    @property
+    def pagespeed_api_key(self) -> str | None:
+        """Get PageSpeed Insights API key."""
+        return os.getenv("PAGESPEED_API_KEY")
+
+    @property
+    def custom_search_api_key(self) -> str | None:
+        """Get Custom Search API key."""
+        return os.getenv("CUSTOM_SEARCH_API_KEY")
+
+    @property
+    def custom_search_engine_id(self) -> str | None:
+        """Get Custom Search Engine ID."""
+        return os.getenv("CUSTOM_SEARCH_ENGINE_ID")
+
+    @property
+    def notion_token(self) -> str | None:
+        """Get Notion API token."""
+        return os.getenv("NOTION_TOKEN") or os.getenv("NOTION_API_KEY")
+
+    def validate_google_credentials(self) -> bool:
+        """Validate Google credentials are configured."""
+        creds_path = self.google_credentials_path
+        if not creds_path:
+            return False
+        return os.path.exists(creds_path)
+
+    def get_required(self, key: str) -> str:
+        """Get required environment variable or raise error."""
+        value = os.getenv(key)
+        if not value:
+            raise ValueError(f"Missing required environment variable: {key}")
+        return value
+
+
+# Singleton config instance
+config = ConfigManager()
--- a/custom-skills/21-seo-position-tracking/code/scripts/position_tracker.py
+++ b/custom-skills/21-seo-position-tracking/code/scripts/position_tracker.py
@@ -0,0 +1,786 @@
+"""
+Position Tracker - Keyword Ranking Monitor via Ahrefs Rank Tracker
+==================================================================
+Purpose: Monitor keyword positions, detect changes, calculate visibility scores
+Python: 3.10+
+
+Usage:
+    python position_tracker.py --target https://example.com --json
+    python position_tracker.py --target https://example.com --threshold 5 --json
+    python position_tracker.py --target https://example.com --segment brand --json
+    python position_tracker.py --target https://example.com --competitor https://comp1.com --json
+"""
+
+import argparse
+import asyncio
+import json
+import logging
+import math
+import sys
+from dataclasses import dataclass, field, asdict
+from datetime import datetime
+from typing import Optional
+from urllib.parse import urlparse
+
+from base_client import BaseAsyncClient, config
+
+logger = logging.getLogger(__name__)
+
+# ---------------------------------------------------------------------------
+# CTR curve weights for visibility score (position 1-100)
+# Based on industry-standard organic CTR curves
+# ---------------------------------------------------------------------------
+CTR_WEIGHTS: dict[int, float] = {
+    1: 0.300,
+    2: 0.150,
+    3: 0.100,
+    4: 0.070,
+    5: 0.050,
+    6: 0.038,
+    7: 0.030,
+    8: 0.025,
+    9: 0.020,
+    10: 0.018,
+}
+
+# Positions 11-20 get diminishing CTR
+for _p in range(11, 21):
+    CTR_WEIGHTS[_p] = round(0.015 - (_p - 11) * 0.001, 4)
+
+# Positions 21-50 get minimal CTR
+for _p in range(21, 51):
+    CTR_WEIGHTS[_p] = round(max(0.005 - (_p - 21) * 0.0001, 0.001), 4)
+
+# Positions 51-100 get near-zero CTR
+for _p in range(51, 101):
+    CTR_WEIGHTS[_p] = 0.0005
+
+
+# ---------------------------------------------------------------------------
+# Data classes
+# ---------------------------------------------------------------------------
+@dataclass
+class KeywordPosition:
+    """Single keyword ranking position."""
+    keyword: str
+    position: int
+    previous_position: Optional[int] = None
+    change: int = 0
+    volume: int = 0
+    url: str = ""
+    intent: str = "informational"
+    is_brand: bool = False
+
+    def __post_init__(self):
+        if self.previous_position is not None:
+            self.change = self.previous_position - self.position
+
+
+@dataclass
+class VisibilityScore:
+    """Weighted visibility score based on CTR curve."""
+    score: float = 0.0
+    top3: int = 0
+    top10: int = 0
+    top20: int = 0
+    top50: int = 0
+    top100: int = 0
+    total_keywords: int = 0
+
+    @property
+    def distribution(self) -> dict:
+        return {
+            "top3": self.top3,
+            "top10": self.top10,
+            "top20": self.top20,
+            "top50": self.top50,
+            "top100": self.top100,
+        }
+
+
+@dataclass
+class PositionAlert:
+    """Alert for significant position change."""
+    keyword: str
+    old_position: int
+    new_position: int
+    change: int
+    volume: int = 0
+    severity: str = "medium"
+
+    def __post_init__(self):
+        abs_change = abs(self.change)
+        if abs_change >= 20:
+            self.severity = "critical"
+        elif abs_change >= 10:
+            self.severity = "high"
+        elif abs_change >= 5:
+            self.severity = "medium"
+        else:
+            self.severity = "low"
+
+
+@dataclass
+class CompetitorComparison:
+    """Competitor ranking comparison result."""
+    competitor: str
+    overlap_keywords: int = 0
+    competitor_better: int = 0
+    target_better: int = 0
+    avg_position_gap: float = 0.0
+    top_gaps: list = field(default_factory=list)
+
+
+@dataclass
+class SegmentData:
+    """Keyword segment aggregation."""
+    name: str
+    keywords: int = 0
+    avg_position: float = 0.0
+    visibility: float = 0.0
+    improved: int = 0
+    declined: int = 0
+    stable: int = 0
+
+
+@dataclass
+class TrackingResult:
+    """Complete position tracking result."""
+    target: str
+    total_keywords: int = 0
+    visibility_score: float = 0.0
+    visibility: Optional[VisibilityScore] = None
+    positions: list[KeywordPosition] = field(default_factory=list)
+    changes: dict = field(default_factory=lambda: {
+        "improved": 0, "declined": 0, "stable": 0, "new": 0, "lost": 0,
+    })
+    alerts: list[PositionAlert] = field(default_factory=list)
+    segments: dict[str, SegmentData] = field(default_factory=dict)
+    competitors: list[CompetitorComparison] = field(default_factory=list)
+    timestamp: str = ""
+
+    def __post_init__(self):
+        if not self.timestamp:
+            self.timestamp = datetime.now().isoformat()
+
+    def to_dict(self) -> dict:
+        """Convert to JSON-serializable dictionary."""
+        result = {
+            "target": self.target,
+            "total_keywords": self.total_keywords,
+            "visibility_score": round(self.visibility_score, 2),
+            "positions": self.visibility.distribution if self.visibility else {},
+            "changes": self.changes,
+            "alerts": [asdict(a) for a in self.alerts],
+            "segments": {
+                k: asdict(v) for k, v in self.segments.items()
+            },
+            "competitors": [asdict(c) for c in self.competitors],
+            "keyword_details": [asdict(p) for p in self.positions],
+            "timestamp": self.timestamp,
+        }
+        return result
+
+
+# ---------------------------------------------------------------------------
+# Position Tracker
+# ---------------------------------------------------------------------------
+class PositionTracker(BaseAsyncClient):
+    """Track keyword ranking positions via Ahrefs Rank Tracker."""
+
+    def __init__(self):
+        super().__init__(
+            max_concurrent=5,
+            requests_per_second=2.0,
+            logger=logger,
+        )
+        self.brand_terms: list[str] = []
+
+    def _extract_domain_brand(self, target: str) -> list[str]:
+        """Extract brand terms from the target domain name."""
+        parsed = urlparse(target)
+        hostname = parsed.hostname or target
+        # Remove TLD and www prefix
+        parts = hostname.replace("www.", "").split(".")
+        brand_parts = []
+        for part in parts:
+            if part not in ("com", "co", "kr", "net", "org", "io", "ai", "www"):
+                brand_parts.append(part.lower())
+                # Also split camelCase and hyphenated forms
+                if "-" in part:
+                    brand_parts.extend(part.lower().split("-"))
+        return list(set(brand_parts))
+
+    async def get_project_keywords(self, target: str) -> list[dict]:
+        """
+        Fetch tracked keywords from Ahrefs management-project-keywords.
+
+        Uses Ahrefs MCP tool: management-project-keywords
+        Returns list of keyword dicts with keyword, volume, intent info.
+        """
+        logger.info(f"Fetching project keywords for: {target}")
+
+        # Step 1: Get project list to find matching project
+        projects = await self._call_ahrefs_projects(target)
+        if not projects:
+            logger.warning(f"No Ahrefs project found for {target}. Using rank-tracker-overview directly.")
+            return []
+
+        project_id = projects[0].get("id", "")
+
+        # Step 2: Fetch keywords for the project
+        keywords_data = await self._call_ahrefs_project_keywords(project_id)
+        return keywords_data
+
+    async def _call_ahrefs_projects(self, target: str) -> list[dict]:
+        """
+        Call Ahrefs management-projects MCP tool.
+        In production, this calls the MCP tool. For standalone, reads from config/cache.
+        """
+        # Simulated MCP call structure - in production this calls:
+        # mcp__ahrefs__management-projects
+        logger.info("Calling Ahrefs management-projects...")
+        try:
+            import subprocess
+            result = subprocess.run(
+                ["mcp-cli", "call", "ahrefs/management-projects", json.dumps({})],
+                capture_output=True, text=True, timeout=30,
+            )
+            if result.returncode == 0:
+                return json.loads(result.stdout).get("projects", [])
+        except (FileNotFoundError, subprocess.TimeoutExpired, json.JSONDecodeError):
+            pass
+        # Return empty if MCP not available - caller handles gracefully
+        return []
+
+    async def _call_ahrefs_project_keywords(self, project_id: str) -> list[dict]:
+        """
+        Call Ahrefs management-project-keywords MCP tool.
+        """
+        logger.info(f"Calling Ahrefs management-project-keywords for project: {project_id}")
+        try:
+            import subprocess
+            result = subprocess.run(
+                ["mcp-cli", "call", "ahrefs/management-project-keywords",
+                 json.dumps({"project_id": project_id})],
+                capture_output=True, text=True, timeout=30,
+            )
+            if result.returncode == 0:
+                return json.loads(result.stdout).get("keywords", [])
+        except (FileNotFoundError, subprocess.TimeoutExpired, json.JSONDecodeError):
+            pass
+        return []
+
+    async def get_current_positions(self, target: str) -> list[KeywordPosition]:
+        """
+        Fetch current keyword positions via Ahrefs rank-tracker-overview.
+
+        Returns list of KeywordPosition objects with current and previous positions.
+        """
+        logger.info(f"Fetching current positions for: {target}")
+        self.brand_terms = self._extract_domain_brand(target)
+
+        raw_data = await self._call_rank_tracker_overview(target)
+        positions: list[KeywordPosition] = []
+
+        for item in raw_data:
+            keyword = item.get("keyword", "")
+            current_pos = item.get("position", 0)
+            prev_pos = item.get("previous_position")
+            volume = item.get("volume", 0)
+            url = item.get("url", "")
+            intent = item.get("intent", "informational")
+
+            # Determine if brand keyword
+            is_brand = self._is_brand_keyword(keyword)
+
+            kp = KeywordPosition(
+                keyword=keyword,
+                position=current_pos,
+                previous_position=prev_pos,
+                volume=volume,
+                url=url,
+                intent=intent,
+                is_brand=is_brand,
+            )
+            positions.append(kp)
+
+        logger.info(f"Retrieved {len(positions)} keyword positions")
+        return positions
+
+    async def _call_rank_tracker_overview(self, target: str) -> list[dict]:
+        """
+        Call Ahrefs rank-tracker-overview MCP tool.
+        """
+        logger.info(f"Calling Ahrefs rank-tracker-overview for: {target}")
+        try:
+            import subprocess
+            result = subprocess.run(
+                ["mcp-cli", "call", "ahrefs/rank-tracker-overview",
+                 json.dumps({"target": target})],
+                capture_output=True, text=True, timeout=60,
+            )
+            if result.returncode == 0:
+                data = json.loads(result.stdout)
+                return data.get("keywords", data.get("results", []))
+        except (FileNotFoundError, subprocess.TimeoutExpired, json.JSONDecodeError):
+            pass
+        return []
+
+    def _is_brand_keyword(self, keyword: str) -> bool:
+        """Check if a keyword is brand-related based on domain name."""
+        keyword_lower = keyword.lower()
+        for term in self.brand_terms:
+            if term in keyword_lower:
+                return True
+        return False
+
+    def detect_changes(
+        self,
+        positions: list[KeywordPosition],
+        threshold: int = 3,
+    ) -> tuple[dict, list[PositionAlert]]:
+        """
+        Detect significant position changes and generate alerts.
+
+        Args:
+            positions: List of current keyword positions with previous data
+            threshold: Minimum position change to trigger an alert
+
+        Returns:
+            Tuple of (change_summary_dict, list_of_alerts)
+        """
+        changes = {
+            "improved": 0,
+            "declined": 0,
+            "stable": 0,
+            "new": 0,
+            "lost": 0,
+        }
+        alerts: list[PositionAlert] = []
+
+        for kp in positions:
+            if kp.previous_position is None:
+                changes["new"] += 1
+                continue
+
+            if kp.position == 0 and kp.previous_position > 0:
+                changes["lost"] += 1
+                alert = PositionAlert(
+                    keyword=kp.keyword,
+                    old_position=kp.previous_position,
+                    new_position=0,
+                    change=-kp.previous_position,
+                    volume=kp.volume,
+                )
+                alerts.append(alert)
+                continue
+
+            change = kp.change  # positive = improved, negative = declined
+            if change > 0:
+                changes["improved"] += 1
+            elif change < 0:
+                changes["declined"] += 1
+            else:
+                changes["stable"] += 1
+
+            # Generate alert if change exceeds threshold
+            if abs(change) >= threshold:
+                alert = PositionAlert(
+                    keyword=kp.keyword,
+                    old_position=kp.previous_position,
+                    new_position=kp.position,
+                    change=change,
+                    volume=kp.volume,
+                )
+                alerts.append(alert)
+
+        # Sort alerts by severity (critical first) then by volume (high first)
+        severity_order = {"critical": 0, "high": 1, "medium": 2, "low": 3}
+        alerts.sort(key=lambda a: (severity_order.get(a.severity, 4), -a.volume))
+
+        logger.info(
+            f"Changes detected - improved: {changes['improved']}, "
+            f"declined: {changes['declined']}, stable: {changes['stable']}, "
+            f"new: {changes['new']}, lost: {changes['lost']}"
+        )
+        logger.info(f"Alerts generated: {len(alerts)} (threshold: {threshold})")
+
+        return changes, alerts
+
+    def calculate_visibility(self, positions: list[KeywordPosition]) -> VisibilityScore:
+        """
+        Calculate weighted visibility score based on CTR curve.
+
+        Visibility = sum(keyword_volume * ctr_weight_for_position) / sum(keyword_volume)
+        Score normalized to 0-100 scale.
+        """
+        vis = VisibilityScore()
+        total_weighted = 0.0
+        total_volume = 0
+
+        for kp in positions:
+            if kp.position <= 0 or kp.position > 100:
+                continue
+
+            vis.total_keywords += 1
+            volume = max(kp.volume, 1)  # Avoid zero volume
+            total_volume += volume
+
+            # Position bucket counting
+            if kp.position <= 3:
+                vis.top3 += 1
+            if kp.position <= 10:
+                vis.top10 += 1
+            if kp.position <= 20:
+                vis.top20 += 1
+            if kp.position <= 50:
+                vis.top50 += 1
+            if kp.position <= 100:
+                vis.top100 += 1
+
+            # Weighted visibility
+            ctr = CTR_WEIGHTS.get(kp.position, 0.0005)
+            total_weighted += volume * ctr
+
+        if total_volume > 0:
+            # Normalize: max possible is if all keywords were position 1
+            max_possible = total_volume * CTR_WEIGHTS[1]
+            vis.score = (total_weighted / max_possible) * 100.0
+        else:
+            vis.score = 0.0
+
+        logger.info(
+            f"Visibility score: {vis.score:.2f} | "
+            f"Top3: {vis.top3}, Top10: {vis.top10}, Top20: {vis.top20}"
+        )
+
+        return vis
+
+    def segment_keywords(
+        self,
+        positions: list[KeywordPosition],
+        filter_segment: Optional[str] = None,
+    ) -> dict[str, SegmentData]:
+        """
+        Segment keywords into brand/non-brand and by intent type.
+
+        Args:
+            positions: List of keyword positions
+            filter_segment: Optional filter - 'brand', 'non_brand', or intent type
+
+        Returns:
+            Dictionary of segment name to SegmentData
+        """
+        segments: dict[str, list[KeywordPosition]] = {
+            "brand": [],
+            "non_brand": [],
+        }
+        intent_segments: dict[str, list[KeywordPosition]] = {}
+
+        for kp in positions:
+            # Brand segmentation
+            if kp.is_brand:
+                segments["brand"].append(kp)
+            else:
+                segments["non_brand"].append(kp)
+
+            # Intent segmentation
+            intent_key = kp.intent.lower() if kp.intent else "informational"
+            if intent_key not in intent_segments:
+                intent_segments[intent_key] = []
+            intent_segments[intent_key].append(kp)
+
+        # Merge intent segments into main segments
+        for intent_key, kps in intent_segments.items():
+            segments[f"intent_{intent_key}"] = kps
+
+        # Calculate segment stats
+        result: dict[str, SegmentData] = {}
+        for seg_name, kps in segments.items():
+            if filter_segment and seg_name != filter_segment:
+                continue
+
+            if not kps:
+                continue
+
+            active_positions = [kp for kp in kps if kp.position > 0]
+            avg_pos = (
+                sum(kp.position for kp in active_positions) / len(active_positions)
+                if active_positions else 0.0
+            )
+
+            vis = self.calculate_visibility(kps)
+
+            improved = sum(1 for kp in kps if kp.change > 0)
+            declined = sum(1 for kp in kps if kp.change < 0)
+            stable = sum(1 for kp in kps if kp.change == 0 and kp.previous_position is not None)
+
+            result[seg_name] = SegmentData(
+                name=seg_name,
+                keywords=len(kps),
+                avg_position=round(avg_pos, 1),
+                visibility=round(vis.score, 2),
+                improved=improved,
+                declined=declined,
+                stable=stable,
+            )
+
+        return result
+
+    async def compare_competitors(
+        self,
+        target: str,
+        competitors: list[str],
+    ) -> list[CompetitorComparison]:
+        """
+        Compare ranking positions against competitors.
+
+        Uses Ahrefs rank-tracker-competitors-overview MCP tool.
+        """
+        comparisons: list[CompetitorComparison] = []
+
+        for competitor in competitors:
+            logger.info(f"Comparing with competitor: {competitor}")
+            comp_data = await self._call_competitors_overview(target, competitor)
+
+            comparison = CompetitorComparison(competitor=competitor)
+
+            if comp_data:
+                comparison.overlap_keywords = comp_data.get("overlap_keywords", 0)
+                comparison.competitor_better = comp_data.get("competitor_better", 0)
+                comparison.target_better = comp_data.get("target_better", 0)
+                comparison.avg_position_gap = comp_data.get("avg_position_gap", 0.0)
+
+                # Extract top gaps (keywords where competitor outranks us most)
+                top_gaps = comp_data.get("top_gaps", [])
+                comparison.top_gaps = top_gaps[:10]
+
+            comparisons.append(comparison)
+
+        return comparisons
+
+    async def _call_competitors_overview(self, target: str, competitor: str) -> dict:
+        """
+        Call Ahrefs rank-tracker-competitors-overview MCP tool.
+        """
+        logger.info(f"Calling Ahrefs rank-tracker-competitors-overview...")
+        try:
+            import subprocess
+            result = subprocess.run(
+                ["mcp-cli", "call", "ahrefs/rank-tracker-competitors-overview",
+                 json.dumps({"target": target, "competitor": competitor})],
+                capture_output=True, text=True, timeout=60,
+            )
+            if result.returncode == 0:
+                return json.loads(result.stdout)
+        except (FileNotFoundError, subprocess.TimeoutExpired, json.JSONDecodeError):
+            pass
+        return {}
+
+    async def analyze(
+        self,
+        target: str,
+        threshold: int = 3,
+        competitors: Optional[list[str]] = None,
+        segment_filter: Optional[str] = None,
+    ) -> TrackingResult:
+        """
+        Orchestrate full position tracking analysis.
+
+        Args:
+            target: Target website URL
+            threshold: Position change threshold for alerts
+            competitors: List of competitor URLs to compare
+            segment_filter: Optional segment filter (brand, non_brand, intent_*)
+
+        Returns:
+            Complete TrackingResult with all analysis data
+        """
+        logger.info(f"Starting position tracking analysis for: {target}")
+        logger.info(f"Threshold: {threshold}, Competitors: {competitors or 'none'}")
+
+        result = TrackingResult(target=target)
+
+        # Step 1: Fetch current positions
+        positions = await self.get_current_positions(target)
+
+        if not positions:
+            logger.warning("No position data retrieved. Check Ahrefs project configuration.")
+            return result
+
+        result.positions = positions
+        result.total_keywords = len(positions)
+
+        # Step 2: Detect changes and generate alerts
+        changes, alerts = self.detect_changes(positions, threshold)
+        result.changes = changes
+        result.alerts = alerts
+
+        # Step 3: Calculate visibility score
+        visibility = self.calculate_visibility(positions)
+        result.visibility = visibility
+        result.visibility_score = visibility.score
+
+        # Step 4: Segment keywords
+        segments = self.segment_keywords(positions, segment_filter)
+        result.segments = segments
+
+        # Step 5: Compare with competitors (if provided)
+        if competitors:
+            comp_results = await self.compare_competitors(target, competitors)
+            result.competitors = comp_results
+
+        logger.info(f"Analysis complete. Total keywords: {result.total_keywords}")
+        logger.info(f"Visibility score: {result.visibility_score:.2f}")
+
+        return result
+
+
+# ---------------------------------------------------------------------------
+# Output formatters
+# ---------------------------------------------------------------------------
+def format_text_report(result: TrackingResult) -> str:
+    """Format tracking result as human-readable text report."""
+    lines = []
+    lines.append("=" * 60)
+    lines.append(f"Position Tracking Report: {result.target}")
+    lines.append(f"Timestamp: {result.timestamp}")
+    lines.append("=" * 60)
+
+    # Visibility overview
+    lines.append(f"\nVisibility Score: {result.visibility_score:.2f}/100")
+    lines.append(f"Total Keywords Tracked: {result.total_keywords}")
+
+    if result.visibility:
+        vis = result.visibility
+        lines.append(f"\nPosition Distribution:")
+        lines.append(f"  Top 3:   {vis.top3}")
+        lines.append(f"  Top 10:  {vis.top10}")
+        lines.append(f"  Top 20:  {vis.top20}")
+        lines.append(f"  Top 50:  {vis.top50}")
+        lines.append(f"  Top 100: {vis.top100}")
+
+    # Changes summary
+    ch = result.changes
+    lines.append(f"\nPosition Changes:")
+    lines.append(f"  Improved: {ch.get('improved', 0)}")
+    lines.append(f"  Declined: {ch.get('declined', 0)}")
+    lines.append(f"  Stable:   {ch.get('stable', 0)}")
+    lines.append(f"  New:      {ch.get('new', 0)}")
+    lines.append(f"  Lost:     {ch.get('lost', 0)}")
+
+    # Alerts
+    if result.alerts:
+        lines.append(f"\nAlerts ({len(result.alerts)}):")
+        lines.append("-" * 60)
+        for alert in result.alerts[:20]:
+            direction = "UP" if alert.change > 0 else "DOWN"
+            lines.append(
+                f"  [{alert.severity.upper()}] {alert.keyword}: "
+                f"{alert.old_position} -> {alert.new_position} "
+                f"({direction} {abs(alert.change)}) | Vol: {alert.volume}"
+            )
+
+    # Segments
+    if result.segments:
+        lines.append(f"\nSegments:")
+        lines.append("-" * 60)
+        for name, seg in result.segments.items():
+            lines.append(
+                f"  {name}: {seg.keywords} keywords, "
+                f"avg pos {seg.avg_position}, "
+                f"vis {seg.visibility}"
+            )
+
+    # Competitors
+    if result.competitors:
+        lines.append(f"\nCompetitor Comparison:")
+        lines.append("-" * 60)
+        for comp in result.competitors:
+            lines.append(f"  vs {comp.competitor}:")
+            lines.append(f"    Overlap: {comp.overlap_keywords} keywords")
+            lines.append(f"    We win: {comp.target_better}")
+            lines.append(f"    They win: {comp.competitor_better}")
+            lines.append(f"    Avg gap: {comp.avg_position_gap:.1f}")
+
+    lines.append("\n" + "=" * 60)
+    return "\n".join(lines)
+
+
+# ---------------------------------------------------------------------------
+# CLI
+# ---------------------------------------------------------------------------
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(
+        description="Position Tracker - Monitor keyword rankings via Ahrefs Rank Tracker",
+    )
+    parser.add_argument(
+        "--target",
+        required=True,
+        help="Target website URL (e.g., https://example.com)",
+    )
+    parser.add_argument(
+        "--threshold",
+        type=int,
+        default=3,
+        help="Position change threshold for alerts (default: 3)",
+    )
+    parser.add_argument(
+        "--segment",
+        choices=["brand", "non_brand", "intent_informational",
+                 "intent_commercial", "intent_transactional", "intent_navigational"],
+        default=None,
+        help="Filter results by keyword segment",
+    )
+    parser.add_argument(
+        "--competitor",
+        action="append",
+        dest="competitors",
+        default=[],
+        help="Competitor URL to compare (repeatable)",
+    )
+    parser.add_argument(
+        "--json",
+        action="store_true",
+        dest="json_output",
+        help="Output in JSON format",
+    )
+    parser.add_argument(
+        "--output",
+        type=str,
+        default=None,
+        help="Save output to file path",
+    )
+    return parser.parse_args()
+
+
+async def main():
+    args = parse_args()
+
+    tracker = PositionTracker()
+
+    result = await tracker.analyze(
+        target=args.target,
+        threshold=args.threshold,
+        competitors=args.competitors,
+        segment_filter=args.segment,
+    )
+
+    if args.json_output:
+        output = json.dumps(result.to_dict(), ensure_ascii=False, indent=2)
+    else:
+        output = format_text_report(result)
+
+    if args.output:
+        with open(args.output, "w", encoding="utf-8") as f:
+            f.write(output)
+        logger.info(f"Output saved to: {args.output}")
+    else:
+        print(output)
+
+    tracker.print_stats()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())
--- a/custom-skills/21-seo-position-tracking/code/scripts/ranking_reporter.py
+++ b/custom-skills/21-seo-position-tracking/code/scripts/ranking_reporter.py
@@ -0,0 +1,728 @@
+"""
+Ranking Reporter - Ranking Performance Reports with Trends
+==========================================================
+Purpose: Generate ranking reports with trend analysis, top movers, and competitor comparison
+Python: 3.10+
+
+Usage:
+    python ranking_reporter.py --target https://example.com --period 30 --json
+    python ranking_reporter.py --target https://example.com --period 90 --json
+    python ranking_reporter.py --target https://example.com --competitor https://comp1.com --period 30 --json
+"""
+
+import argparse
+import asyncio
+import json
+import logging
+import sys
+from dataclasses import dataclass, field, asdict
+from datetime import datetime, timedelta
+from typing import Optional
+from urllib.parse import urlparse
+
+from base_client import BaseAsyncClient, config
+
+logger = logging.getLogger(__name__)
+
+# CTR weights for impact scoring (same as position_tracker)
+CTR_WEIGHTS: dict[int, float] = {
+    1: 0.300, 2: 0.150, 3: 0.100, 4: 0.070, 5: 0.050,
+    6: 0.038, 7: 0.030, 8: 0.025, 9: 0.020, 10: 0.018,
+}
+for _p in range(11, 21):
+    CTR_WEIGHTS[_p] = round(0.015 - (_p - 11) * 0.001, 4)
+for _p in range(21, 51):
+    CTR_WEIGHTS[_p] = round(max(0.005 - (_p - 21) * 0.0001, 0.001), 4)
+for _p in range(51, 101):
+    CTR_WEIGHTS[_p] = 0.0005
+
+
+# ---------------------------------------------------------------------------
+# Data classes
+# ---------------------------------------------------------------------------
+@dataclass
+class PositionSnapshot:
+    """A single position measurement at a point in time."""
+    date: str
+    position: int
+    volume: int = 0
+    url: str = ""
+
+
+@dataclass
+class RankingTrend:
+    """Keyword ranking trend over time."""
+    keyword: str
+    positions_over_time: list[PositionSnapshot] = field(default_factory=list)
+    trend_direction: str = "stable"  # improved, declined, stable, new, lost
+    avg_position: float = 0.0
+    current_position: int = 0
+    start_position: int = 0
+    total_change: int = 0
+    volume: int = 0
+    intent: str = "informational"
+    is_brand: bool = False
+
+    def compute_trend(self):
+        """Compute trend direction and average from position history."""
+        if not self.positions_over_time:
+            self.trend_direction = "stable"
+            return
+
+        positions = [s.position for s in self.positions_over_time if s.position > 0]
+        if not positions:
+            self.trend_direction = "lost"
+            return
+
+        self.avg_position = sum(positions) / len(positions)
+        self.current_position = positions[-1]
+        self.start_position = positions[0]
+        self.total_change = self.start_position - self.current_position
+
+        # Determine trend using linear regression direction
+        if len(positions) >= 2:
+            n = len(positions)
+            x_mean = (n - 1) / 2.0
+            y_mean = sum(positions) / n
+            numerator = sum((i - x_mean) * (p - y_mean) for i, p in enumerate(positions))
+            denominator = sum((i - x_mean) ** 2 for i in range(n))
+
+            if denominator > 0:
+                slope = numerator / denominator
+                # Negative slope means position number decreasing = improving
+                if slope < -0.5:
+                    self.trend_direction = "improved"
+                elif slope > 0.5:
+                    self.trend_direction = "declined"
+                else:
+                    self.trend_direction = "stable"
+            else:
+                self.trend_direction = "stable"
+
+        if self.volume == 0 and self.positions_over_time:
+            self.volume = self.positions_over_time[-1].volume
+
+
+@dataclass
+class TopMover:
+    """Keyword with significant position change."""
+    keyword: str
+    position_change: int
+    current_position: int = 0
+    previous_position: int = 0
+    volume: int = 0
+    impact_score: float = 0.0
+    direction: str = "improved"
+
+    def calculate_impact(self):
+        """Calculate impact score: volume * CTR delta."""
+        old_ctr = CTR_WEIGHTS.get(self.previous_position, 0.0005) if self.previous_position > 0 else 0.0
+        new_ctr = CTR_WEIGHTS.get(self.current_position, 0.0005) if self.current_position > 0 else 0.0
+        ctr_delta = abs(new_ctr - old_ctr)
+        self.impact_score = round(self.volume * ctr_delta, 2)
+        self.direction = "improved" if self.position_change > 0 else "declined"
+
+
+@dataclass
+class SegmentReport:
+    """Performance breakdown for a keyword segment."""
+    segment_name: str
+    total_keywords: int = 0
+    avg_position: float = 0.0
+    avg_position_change: float = 0.0
+    visibility_score: float = 0.0
+    improved_count: int = 0
+    declined_count: int = 0
+    stable_count: int = 0
+    top_gainers: list[TopMover] = field(default_factory=list)
+    top_losers: list[TopMover] = field(default_factory=list)
+
+
+@dataclass
+class CompetitorReport:
+    """Competitor comparison for a reporting period."""
+    competitor: str
+    our_visibility: float = 0.0
+    their_visibility: float = 0.0
+    overlap_keywords: int = 0
+    keywords_we_lead: int = 0
+    keywords_they_lead: int = 0
+    notable_gaps: list[dict] = field(default_factory=list)
+
+
+@dataclass
+class RankingReport:
+    """Complete ranking performance report."""
+    target: str
+    period_days: int = 30
+    period_start: str = ""
+    period_end: str = ""
+    total_keywords: int = 0
+    current_visibility: float = 0.0
+    previous_visibility: float = 0.0
+    visibility_change: float = 0.0
+    trend_summary: dict = field(default_factory=lambda: {
+        "improved": 0, "declined": 0, "stable": 0, "new": 0, "lost": 0,
+    })
+    top_gainers: list[TopMover] = field(default_factory=list)
+    top_losers: list[TopMover] = field(default_factory=list)
+    segments: list[SegmentReport] = field(default_factory=list)
+    competitors: list[CompetitorReport] = field(default_factory=list)
+    keyword_trends: list[RankingTrend] = field(default_factory=list)
+    timestamp: str = ""
+
+    def __post_init__(self):
+        if not self.timestamp:
+            self.timestamp = datetime.now().isoformat()
+        if not self.period_end:
+            self.period_end = datetime.now().strftime("%Y-%m-%d")
+        if not self.period_start:
+            start = datetime.now() - timedelta(days=self.period_days)
+            self.period_start = start.strftime("%Y-%m-%d")
+
+    def to_dict(self) -> dict:
+        """Convert to JSON-serializable dictionary."""
+        return {
+            "target": self.target,
+            "period": {
+                "days": self.period_days,
+                "start": self.period_start,
+                "end": self.period_end,
+            },
+            "total_keywords": self.total_keywords,
+            "visibility": {
+                "current": round(self.current_visibility, 2),
+                "previous": round(self.previous_visibility, 2),
+                "change": round(self.visibility_change, 2),
+            },
+            "trend_summary": self.trend_summary,
+            "top_gainers": [asdict(m) for m in self.top_gainers],
+            "top_losers": [asdict(m) for m in self.top_losers],
+            "segments": [asdict(s) for s in self.segments],
+            "competitors": [asdict(c) for c in self.competitors],
+            "keyword_trends": [
+                {
+                    "keyword": t.keyword,
+                    "trend_direction": t.trend_direction,
+                    "avg_position": round(t.avg_position, 1),
+                    "current_position": t.current_position,
+                    "start_position": t.start_position,
+                    "total_change": t.total_change,
+                    "volume": t.volume,
+                }
+                for t in self.keyword_trends
+            ],
+            "timestamp": self.timestamp,
+        }
+
+
+# ---------------------------------------------------------------------------
+# Ranking Reporter
+# ---------------------------------------------------------------------------
+class RankingReporter(BaseAsyncClient):
+    """Generate ranking performance reports with trend analysis."""
+
+    def __init__(self):
+        super().__init__(
+            max_concurrent=5,
+            requests_per_second=2.0,
+            logger=logger,
+        )
+
+    def _extract_domain_brand(self, target: str) -> list[str]:
+        """Extract brand terms from the target domain name."""
+        parsed = urlparse(target)
+        hostname = parsed.hostname or target
+        parts = hostname.replace("www.", "").split(".")
+        brand_parts = []
+        for part in parts:
+            if part not in ("com", "co", "kr", "net", "org", "io", "ai", "www"):
+                brand_parts.append(part.lower())
+                if "-" in part:
+                    brand_parts.extend(part.lower().split("-"))
+        return list(set(brand_parts))
+
+    async def get_historical_positions(
+        self,
+        target: str,
+        period_days: int = 30,
+    ) -> list[RankingTrend]:
+        """
+        Fetch historical position data from Ahrefs rank-tracker-overview
+        with date range parameters.
+
+        Returns list of RankingTrend objects with position snapshots over time.
+        """
+        logger.info(f"Fetching historical positions for {target} ({period_days} days)")
+        brand_terms = self._extract_domain_brand(target)
+
+        end_date = datetime.now().strftime("%Y-%m-%d")
+        start_date = (datetime.now() - timedelta(days=period_days)).strftime("%Y-%m-%d")
+
+        raw_data = await self._call_rank_tracker_historical(target, start_date, end_date)
+
+        trends: dict[str, RankingTrend] = {}
+        for item in raw_data:
+            keyword = item.get("keyword", "")
+            if keyword not in trends:
+                is_brand = any(term in keyword.lower() for term in brand_terms)
+                trends[keyword] = RankingTrend(
+                    keyword=keyword,
+                    volume=item.get("volume", 0),
+                    intent=item.get("intent", "informational"),
+                    is_brand=is_brand,
+                )
+
+            snapshot = PositionSnapshot(
+                date=item.get("date", end_date),
+                position=item.get("position", 0),
+                volume=item.get("volume", 0),
+                url=item.get("url", ""),
+            )
+            trends[keyword].positions_over_time.append(snapshot)
+
+        # Sort snapshots by date and compute trends
+        for trend in trends.values():
+            trend.positions_over_time.sort(key=lambda s: s.date)
+            trend.compute_trend()
+
+        logger.info(f"Retrieved trends for {len(trends)} keywords")
+        return list(trends.values())
+
+    async def _call_rank_tracker_historical(
+        self, target: str, start_date: str, end_date: str,
+    ) -> list[dict]:
+        """Call Ahrefs rank-tracker-overview with date range."""
+        logger.info(f"Calling Ahrefs rank-tracker-overview ({start_date} to {end_date})...")
+        try:
+            import subprocess
+            result = subprocess.run(
+                ["mcp-cli", "call", "ahrefs/rank-tracker-overview",
+                 json.dumps({
+                     "target": target,
+                     "date_from": start_date,
+                     "date_to": end_date,
+                 })],
+                capture_output=True, text=True, timeout=60,
+            )
+            if result.returncode == 0:
+                data = json.loads(result.stdout)
+                return data.get("keywords", data.get("results", []))
+        except (FileNotFoundError, subprocess.TimeoutExpired, json.JSONDecodeError):
+            pass
+        return []
+
+    def calculate_trends(self, trends: list[RankingTrend]) -> dict:
+        """
+        Compute overall trend summary from keyword trends.
+
+        Returns dict with improved/declined/stable/new/lost counts.
+        """
+        summary = {
+            "improved": 0,
+            "declined": 0,
+            "stable": 0,
+            "new": 0,
+            "lost": 0,
+        }
+        for trend in trends:
+            direction = trend.trend_direction
+            if direction in summary:
+                summary[direction] += 1
+            else:
+                summary["stable"] += 1
+
+        logger.info(
+            f"Trend summary: improved={summary['improved']}, "
+            f"declined={summary['declined']}, stable={summary['stable']}"
+        )
+        return summary
+
+    def find_top_movers(
+        self,
+        trends: list[RankingTrend],
+        limit: int = 10,
+    ) -> tuple[list[TopMover], list[TopMover]]:
+        """
+        Find keywords with biggest position gains and losses.
+
+        Returns tuple of (top_gainers, top_losers) sorted by impact score.
+        """
+        gainers: list[TopMover] = []
+        losers: list[TopMover] = []
+
+        for trend in trends:
+            if not trend.positions_over_time or len(trend.positions_over_time) < 2:
+                continue
+
+            first_pos = trend.start_position
+            last_pos = trend.current_position
+
+            if first_pos <= 0 or last_pos <= 0:
+                continue
+
+            change = first_pos - last_pos  # positive = improved
+
+            mover = TopMover(
+                keyword=trend.keyword,
+                position_change=change,
+                current_position=last_pos,
+                previous_position=first_pos,
+                volume=trend.volume,
+            )
+            mover.calculate_impact()
+
+            if change > 0:
+                gainers.append(mover)
+            elif change < 0:
+                losers.append(mover)
+
+        # Sort by impact score descending
+        gainers.sort(key=lambda m: m.impact_score, reverse=True)
+        losers.sort(key=lambda m: m.impact_score, reverse=True)
+
+        logger.info(f"Top movers: {len(gainers)} gainers, {len(losers)} losers")
+        return gainers[:limit], losers[:limit]
+
+    def _calculate_visibility_score(self, trends: list[RankingTrend], use_start: bool = False) -> float:
+        """Calculate visibility score from trends (current or start positions)."""
+        total_weighted = 0.0
+        total_volume = 0
+
+        for trend in trends:
+            pos = trend.start_position if use_start else trend.current_position
+            if pos <= 0 or pos > 100:
+                continue
+            volume = max(trend.volume, 1)
+            total_volume += volume
+            ctr = CTR_WEIGHTS.get(pos, 0.0005)
+            total_weighted += volume * ctr
+
+        if total_volume > 0:
+            max_possible = total_volume * CTR_WEIGHTS[1]
+            return (total_weighted / max_possible) * 100.0
+        return 0.0
+
+    def generate_segment_report(self, trends: list[RankingTrend]) -> list[SegmentReport]:
+        """
+        Generate performance breakdown by keyword segment.
+
+        Segments include: brand, non_brand, and by intent type.
+        """
+        segment_map: dict[str, list[RankingTrend]] = {}
+
+        for trend in trends:
+            # Brand segment
+            brand_key = "brand" if trend.is_brand else "non_brand"
+            if brand_key not in segment_map:
+                segment_map[brand_key] = []
+            segment_map[brand_key].append(trend)
+
+            # Intent segment
+            intent_key = f"intent_{trend.intent.lower()}" if trend.intent else "intent_informational"
+            if intent_key not in segment_map:
+                segment_map[intent_key] = []
+            segment_map[intent_key].append(trend)
+
+        reports: list[SegmentReport] = []
+        for seg_name, seg_trends in sorted(segment_map.items()):
+            if not seg_trends:
+                continue
+
+            active = [t for t in seg_trends if t.current_position > 0]
+            avg_pos = sum(t.current_position for t in active) / len(active) if active else 0.0
+            avg_change = sum(t.total_change for t in seg_trends) / len(seg_trends) if seg_trends else 0.0
+
+            vis = self._calculate_visibility_score(seg_trends, use_start=False)
+
+            improved = sum(1 for t in seg_trends if t.trend_direction == "improved")
+            declined = sum(1 for t in seg_trends if t.trend_direction == "declined")
+            stable = sum(1 for t in seg_trends if t.trend_direction == "stable")
+
+            # Get top movers within segment
+            seg_gainers, seg_losers = self.find_top_movers(seg_trends, limit=5)
+
+            report = SegmentReport(
+                segment_name=seg_name,
+                total_keywords=len(seg_trends),
+                avg_position=round(avg_pos, 1),
+                avg_position_change=round(avg_change, 1),
+                visibility_score=round(vis, 2),
+                improved_count=improved,
+                declined_count=declined,
+                stable_count=stable,
+                top_gainers=seg_gainers,
+                top_losers=seg_losers,
+            )
+            reports.append(report)
+
+        return reports
+
+    async def compare_with_competitor(
+        self,
+        target: str,
+        competitor: str,
+        period_days: int = 30,
+    ) -> CompetitorReport:
+        """
+        Period-over-period comparison with a competitor.
+
+        Uses Ahrefs rank-tracker-competitors-stats for detailed comparison.
+        """
+        logger.info(f"Comparing {target} vs {competitor} over {period_days} days")
+
+        comp_data = await self._call_competitors_stats(target, competitor)
+
+        report = CompetitorReport(competitor=competitor)
+
+        if comp_data:
+            report.our_visibility = comp_data.get("target_visibility", 0.0)
+            report.their_visibility = comp_data.get("competitor_visibility", 0.0)
+            report.overlap_keywords = comp_data.get("overlap_keywords", 0)
+            report.keywords_we_lead = comp_data.get("target_better", 0)
+            report.keywords_they_lead = comp_data.get("competitor_better", 0)
+
+            # Extract notable gaps
+            gaps = comp_data.get("keyword_gaps", [])
+            report.notable_gaps = [
+                {
+                    "keyword": g.get("keyword", ""),
+                    "our_position": g.get("target_position", 0),
+                    "their_position": g.get("competitor_position", 0),
+                    "volume": g.get("volume", 0),
+                }
+                for g in gaps[:15]
+            ]
+
+        return report
+
+    async def _call_competitors_stats(self, target: str, competitor: str) -> dict:
+        """Call Ahrefs rank-tracker-competitors-stats MCP tool."""
+        logger.info("Calling Ahrefs rank-tracker-competitors-stats...")
+        try:
+            import subprocess
+            result = subprocess.run(
+                ["mcp-cli", "call", "ahrefs/rank-tracker-competitors-stats",
+                 json.dumps({"target": target, "competitor": competitor})],
+                capture_output=True, text=True, timeout=60,
+            )
+            if result.returncode == 0:
+                return json.loads(result.stdout)
+        except (FileNotFoundError, subprocess.TimeoutExpired, json.JSONDecodeError):
+            pass
+        return {}
+
+    async def generate_report(
+        self,
+        target: str,
+        period_days: int = 30,
+        competitors: Optional[list[str]] = None,
+    ) -> RankingReport:
+        """
+        Orchestrate full ranking performance report generation.
+
+        Args:
+            target: Target website URL
+            period_days: Reporting period in days
+            competitors: List of competitor URLs to compare
+
+        Returns:
+            Complete RankingReport with trends, movers, segments, and comparisons
+        """
+        logger.info(f"Generating ranking report for: {target} ({period_days} days)")
+
+        report = RankingReport(target=target, period_days=period_days)
+
+        # Step 1: Fetch historical position data
+        trends = await self.get_historical_positions(target, period_days)
+
+        if not trends:
+            logger.warning("No historical data retrieved. Check Ahrefs project configuration.")
+            return report
+
+        report.keyword_trends = trends
+        report.total_keywords = len(trends)
+
+        # Step 2: Calculate trend summary
+        report.trend_summary = self.calculate_trends(trends)
+
+        # Step 3: Calculate visibility scores (current vs period start)
+        report.current_visibility = self._calculate_visibility_score(trends, use_start=False)
+        report.previous_visibility = self._calculate_visibility_score(trends, use_start=True)
+        report.visibility_change = report.current_visibility - report.previous_visibility
+
+        # Step 4: Find top movers
+        gainers, losers = self.find_top_movers(trends, limit=10)
+        report.top_gainers = gainers
+        report.top_losers = losers
+
+        # Step 5: Generate segment reports
+        report.segments = self.generate_segment_report(trends)
+
+        # Step 6: Compare with competitors
+        if competitors:
+            for competitor in competitors:
+                comp_report = await self.compare_with_competitor(
+                    target, competitor, period_days,
+                )
+                report.competitors.append(comp_report)
+
+        logger.info(f"Report complete. Keywords: {report.total_keywords}")
+        logger.info(
+            f"Visibility: {report.previous_visibility:.2f} -> "
+            f"{report.current_visibility:.2f} ({report.visibility_change:+.2f})"
+        )
+
+        return report
+
+
+# ---------------------------------------------------------------------------
+# Output formatters
+# ---------------------------------------------------------------------------
+def format_text_report(report: RankingReport) -> str:
+    """Format ranking report as human-readable text."""
+    lines = []
+    lines.append("=" * 60)
+    lines.append(f"Ranking Performance Report: {report.target}")
+    lines.append(f"Period: {report.period_start} ~ {report.period_end} ({report.period_days} days)")
+    lines.append(f"Generated: {report.timestamp}")
+    lines.append("=" * 60)
+
+    # Visibility trend
+    lines.append(f"\nVisibility Score:")
+    lines.append(f"  Current:  {report.current_visibility:.2f}")
+    lines.append(f"  Previous: {report.previous_visibility:.2f}")
+    change_sign = "+" if report.visibility_change >= 0 else ""
+    lines.append(f"  Change:   {change_sign}{report.visibility_change:.2f}")
+
+    # Trend summary
+    ts = report.trend_summary
+    lines.append(f"\nKeyword Trends ({report.total_keywords} total):")
+    lines.append(f"  Improved: {ts.get('improved', 0)}")
+    lines.append(f"  Declined: {ts.get('declined', 0)}")
+    lines.append(f"  Stable:   {ts.get('stable', 0)}")
+    lines.append(f"  New:      {ts.get('new', 0)}")
+    lines.append(f"  Lost:     {ts.get('lost', 0)}")
+
+    # Top gainers
+    if report.top_gainers:
+        lines.append(f"\nTop Gainers:")
+        lines.append("-" * 60)
+        for m in report.top_gainers:
+            lines.append(
+                f"  {m.keyword}: {m.previous_position} -> {m.current_position} "
+                f"(+{m.position_change}) | Vol: {m.volume} | Impact: {m.impact_score}"
+            )
+
+    # Top losers
+    if report.top_losers:
+        lines.append(f"\nTop Losers:")
+        lines.append("-" * 60)
+        for m in report.top_losers:
+            lines.append(
+                f"  {m.keyword}: {m.previous_position} -> {m.current_position} "
+                f"({m.position_change}) | Vol: {m.volume} | Impact: {m.impact_score}"
+            )
+
+    # Segments
+    if report.segments:
+        lines.append(f"\nSegment Breakdown:")
+        lines.append("-" * 60)
+        for seg in report.segments:
+            lines.append(
+                f"  {seg.segment_name}: {seg.total_keywords} kw, "
+                f"avg pos {seg.avg_position}, vis {seg.visibility_score}, "
+                f"improved {seg.improved_count} / declined {seg.declined_count}"
+            )
+
+    # Competitors
+    if report.competitors:
+        lines.append(f"\nCompetitor Comparison:")
+        lines.append("-" * 60)
+        for comp in report.competitors:
+            lines.append(f"  vs {comp.competitor}:")
+            lines.append(f"    Our visibility:   {comp.our_visibility:.2f}")
+            lines.append(f"    Their visibility: {comp.their_visibility:.2f}")
+            lines.append(f"    Overlap: {comp.overlap_keywords} keywords")
+            lines.append(f"    We lead: {comp.keywords_we_lead}")
+            lines.append(f"    They lead: {comp.keywords_they_lead}")
+            if comp.notable_gaps:
+                lines.append(f"    Notable gaps:")
+                for gap in comp.notable_gaps[:5]:
+                    lines.append(
+                        f"      {gap['keyword']}: us #{gap['our_position']} "
+                        f"vs them #{gap['their_position']} (vol: {gap['volume']})"
+                    )
+
+    lines.append("\n" + "=" * 60)
+    return "\n".join(lines)
+
+
+# ---------------------------------------------------------------------------
+# CLI
+# ---------------------------------------------------------------------------
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(
+        description="Ranking Reporter - Generate ranking performance reports with trends",
+    )
+    parser.add_argument(
+        "--target",
+        required=True,
+        help="Target website URL (e.g., https://example.com)",
+    )
+    parser.add_argument(
+        "--period",
+        type=int,
+        default=30,
+        help="Reporting period in days (default: 30)",
+    )
+    parser.add_argument(
+        "--competitor",
+        action="append",
+        dest="competitors",
+        default=[],
+        help="Competitor URL to compare (repeatable)",
+    )
+    parser.add_argument(
+        "--json",
+        action="store_true",
+        dest="json_output",
+        help="Output in JSON format",
+    )
+    parser.add_argument(
+        "--output",
+        type=str,
+        default=None,
+        help="Save output to file path",
+    )
+    return parser.parse_args()
+
+
+async def main():
+    args = parse_args()
+
+    reporter = RankingReporter()
+
+    report = await reporter.generate_report(
+        target=args.target,
+        period_days=args.period,
+        competitors=args.competitors,
+    )
+
+    if args.json_output:
+        output = json.dumps(report.to_dict(), ensure_ascii=False, indent=2)
+    else:
+        output = format_text_report(report)
+
+    if args.output:
+        with open(args.output, "w", encoding="utf-8") as f:
+            f.write(output)
+        logger.info(f"Output saved to: {args.output}")
+    else:
+        print(output)
+
+    reporter.print_stats()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())
--- a/custom-skills/21-seo-position-tracking/code/scripts/requirements.txt
+++ b/custom-skills/21-seo-position-tracking/code/scripts/requirements.txt
@@ -0,0 +1,8 @@
+# 21-seo-position-tracking dependencies
+requests>=2.31.0
+aiohttp>=3.9.0
+pandas>=2.1.0
+tenacity>=8.2.0
+tqdm>=4.66.0
+python-dotenv>=1.0.0
+rich>=13.7.0
--- a/custom-skills/21-seo-position-tracking/desktop/SKILL.md
+++ b/custom-skills/21-seo-position-tracking/desktop/SKILL.md
@@ -0,0 +1,107 @@
+---
+name: seo-position-tracking
+description: |
+  Keyword position tracking and ranking monitoring via Ahrefs Rank Tracker.
+  Triggers: rank tracking, position monitoring, keyword rankings, visibility score, ranking report, 키워드 순위, 순위 추적.
+---
+
+# SEO Position Tracking
+
+## Purpose
+
+Monitor keyword ranking positions, detect significant changes, calculate visibility scores, and compare against competitors using Ahrefs Rank Tracker data. Provides actionable alerts for ranking drops and segment-level performance breakdown.
+
+## Core Capabilities
+
+1. **Position Monitoring** - Retrieve current keyword ranking positions from Ahrefs Rank Tracker projects
+2. **Change Detection** - Detect significant position changes with configurable threshold alerts (severity: critical/high/medium/low)
+3. **Visibility Scoring** - Calculate weighted visibility scores using CTR-curve model (position 1 = 30%, position 2 = 15%, etc.)
+4. **Brand/Non-brand Segmentation** - Automatically classify keywords by brand relevance and search intent type
+5. **Competitor Comparison** - Compare keyword overlap, position gaps, and visibility scores against competitors
+
+## MCP Tool Usage
+
+### Ahrefs Rank Tracker Tools
+```
+mcp__ahrefs__rank-tracker-overview: Get rank tracking overview with current positions
+mcp__ahrefs__rank-tracker-competitors-overview: Compare rankings against competitors
+mcp__ahrefs__rank-tracker-competitors-pages: Competitor page-level ranking data
+mcp__ahrefs__rank-tracker-competitors-stats: Detailed competitor ranking statistics
+mcp__ahrefs__rank-tracker-serp-overview: SERP details for tracked keywords
+mcp__ahrefs__management-projects: List available Ahrefs projects
+mcp__ahrefs__management-project-keywords: Get tracked keywords for a project
+```
+
+### Notion for Report Storage
+```
+mcp__notion__notion-create-pages: Save tracking reports to SEO Audit Log
+mcp__notion__notion-update-page: Update existing tracking entries
+```
+
+## Workflow
+
+### Phase 1: Data Collection
+1. Identify Ahrefs project via `management-projects`
+2. Retrieve tracked keywords via `management-project-keywords`
+3. Fetch current positions via `rank-tracker-overview`
+4. Fetch competitor data via `rank-tracker-competitors-overview` (if requested)
+
+### Phase 2: Analysis
+1. Detect position changes against previous period
+2. Generate alerts for changes exceeding threshold
+3. Calculate visibility score weighted by search volume and CTR curve
+4. Segment keywords into brand/non-brand and by intent type
+5. Compare positions against each competitor
+
+### Phase 3: Reporting
+1. Compile position distribution (top3/top10/top20/top50/top100)
+2. Summarize changes (improved/declined/stable/new/lost)
+3. List alerts sorted by severity and search volume
+4. Generate segment-level breakdown
+5. Save report to Notion SEO Audit Log database
+
+## Output Format
+
+```json
+{
+  "target": "https://example.com",
+  "total_keywords": 250,
+  "visibility_score": 68.5,
+  "positions": {
+    "top3": 15,
+    "top10": 48,
+    "top20": 92,
+    "top50": 180,
+    "top100": 230
+  },
+  "changes": {
+    "improved": 45,
+    "declined": 30,
+    "stable": 155,
+    "new": 12,
+    "lost": 8
+  },
+  "alerts": [
+    {
+      "keyword": "example keyword",
+      "old_position": 5,
+      "new_position": 15,
+      "change": -10,
+      "volume": 5400,
+      "severity": "high"
+    }
+  ],
+  "segments": {
+    "brand": {"keywords": 30, "avg_position": 2.1},
+    "non_brand": {"keywords": 220, "avg_position": 24.5}
+  }
+}
+```
+
+## Notion Output (Required)
+
+All tracking reports MUST be saved to OurDigital SEO Audit Log:
+- **Database ID**: `2c8581e5-8a1e-8035-880b-e38cefc2f3ef`
+- **Properties**: Issue (title), Site (url), Category (Position Tracking), Priority, Found Date, Audit ID
+- **Language**: Korean with English technical terms
+- **Audit ID Format**: RANK-YYYYMMDD-NNN
--- a/custom-skills/21-seo-position-tracking/desktop/skill.yaml
+++ b/custom-skills/21-seo-position-tracking/desktop/skill.yaml
@@ -0,0 +1,8 @@
+name: seo-position-tracking
+description: |
+  Keyword position tracking and ranking monitoring. Triggers: rank tracking, position monitoring, keyword rankings, visibility score, ranking report.
+allowed-tools:
+  - mcp__ahrefs__*
+  - mcp__notion__*
+  - WebSearch
+  - WebFetch
--- a/custom-skills/21-seo-position-tracking/desktop/tools/ahrefs.md
+++ b/custom-skills/21-seo-position-tracking/desktop/tools/ahrefs.md
@@ -0,0 +1,15 @@
+# Ahrefs
+
+> TODO: Document tool usage for this skill
+
+## Available Commands
+
+- [ ] List commands
+
+## Configuration
+
+- [ ] Add configuration details
+
+## Examples
+
+- [ ] Add usage examples
--- a/custom-skills/21-seo-position-tracking/desktop/tools/notion.md
+++ b/custom-skills/21-seo-position-tracking/desktop/tools/notion.md
@@ -0,0 +1,15 @@
+# Notion
+
+> TODO: Document tool usage for this skill
+
+## Available Commands
+
+- [ ] List commands
+
+## Configuration
+
+- [ ] Add configuration details
+
+## Examples
+
+- [ ] Add usage examples
--- a/custom-skills/21-seo-position-tracking/desktop/tools/websearch.md
+++ b/custom-skills/21-seo-position-tracking/desktop/tools/websearch.md
@@ -0,0 +1,15 @@
+# WebSearch
+
+> TODO: Document tool usage for this skill
+
+## Available Commands
+
+- [ ] List commands
+
+## Configuration
+
+- [ ] Add configuration details
+
+## Examples
+
+- [ ] Add usage examples