diff --git a/.claude/commands/multi-agent-guide.md b/.claude/commands/multi-agent-guide.md
new file mode 100644
index 0000000..3fbe61a
--- /dev/null
+++ b/.claude/commands/multi-agent-guide.md
@@ -0,0 +1,71 @@
+---
+description: Set up multi-agent collaboration framework (Claude, Gemini, Codex) with guardrails
+argument-hint: [--quick] [--full]
+---
+
+# Multi-Agent Guide
+
+Set up multi-agent collaboration framework for projects where multiple AI agents work together.
+
+## Triggers
+- "set up multi-agent", "agent guardrails", "multi-agent collaboration"
+
+## Quick Setup (Recommended)
+
+Rapid deployment with minimal questions:
+
+1. Assess project structure
+2. Ask which agents participate (Claude/Gemini/Codex/Human)
+3. Create framework files
+4. Customize ownership matrix
+
+## Files Created
+
+```
+your-project/
+├── .agent-state/
+│   ├── tasks.yaml          # Task registry
+│   └── locks.yaml          # Lock registry
+├── tools/
+│   └── check-ownership.py  # Ownership verification
+├── MULTI_AGENT_FRAMEWORK.md  # Consolidated rules
+├── GEMINI.md               # Sub-agent directive (if selected)
+└── CODEX.md                # Sub-agent directive (if selected)
+```
+
+## Agent Hierarchy
+
+```
+            ┌─────────────────┐
+            │   Claude Code   │
+            │  (Lead Agent)   │
+            └────────┬────────┘
+                     │
+      ┌──────────────┼──────────────┐
+      v              v              v
+┌──────────┐  ┌──────────┐  ┌──────────┐
+│  Gemini  │  │  Codex   │  │  Human   │
+│(Research)│  │ (Speed)  │  │ (Review) │
+└──────────┘  └──────────┘  └──────────┘
+```
+
+## Commit Message Format
+
+```
+[Agent] type(scope): description
+
+Examples:
+[Claude] feat(core): implement new feature
+[Gemini] docs(api): update API documentation
+[Codex] test(models): add unit tests
+```
+
+## Post-Setup
+
+1. Set agent identity: `export AGENT_AUTHOR=claude`
+2. Review ownership matrix in `MULTI_AGENT_FRAMEWORK.md`
+3. Install pre-commit hooks: `pre-commit install` (optional)
+
+## Source
+Full details: `custom-skills/91-multi-agent-guide/README.md`
+Related commands: `custom-skills/91-multi-agent-guide/commands/`
diff --git a/.claude/commands/notebooklm-agent.md b/.claude/commands/notebooklm-agent.md
new file mode 100644
index 0000000..13a8f6e
--- /dev/null
+++ b/.claude/commands/notebooklm-agent.md
@@ -0,0 +1,62 @@
+---
+description: Q&A agent using NotebookLM's Gemini-powered analysis with source citations
+---
+
+# NotebookLM Agent
+
+Q&A agent that answers questions using NotebookLM's Gemini-powered analysis with source citations.
+
+## Prerequisites
+
+```bash
+pip install notebooklm-py
+playwright install chromium
+notebooklm login  # One-time auth
+```
+
+## Commands
+
+```bash
+# List notebooks
+notebooklm list
+
+# Set context
+notebooklm use <notebook_id>
+
+# Ask questions
+notebooklm ask "What are the key findings?"
+notebooklm ask "Elaborate on point 2"  # continues conversation
+notebooklm ask "New topic" --new       # new conversation
+
+# With citations (JSON output)
+notebooklm ask "Summarize" --json
+
+# Query specific sources
+notebooklm ask "Compare" -s source1 -s source2
+```
+
+## Autonomy
+
+**Auto-run:** `list`, `status`, `source list`, `ask`
+**Ask first:** `delete`, `source add`
+
+## JSON Output Format
+
+```json
+{
+  "answer": "Response with [1] [2] citations",
+  "references": [
+    {"source_id": "...", "citation_number": 1, "cited_text": "..."}
+  ]
+}
+```
+
+## Error Recovery
+
+| Error | Fix |
+|-------|-----|
+| No context | `notebooklm use <id>` |
+| Auth error | `notebooklm login` |
+
+## Source
+Full details: `custom-skills/50-notebooklm-agent/code/CLAUDE.md`
diff --git a/.claude/commands/notebooklm-automation.md b/.claude/commands/notebooklm-automation.md
new file mode 100644
index 0000000..6a75731
--- /dev/null
+++ b/.claude/commands/notebooklm-automation.md
@@ -0,0 +1,57 @@
+---
+description: Programmatic control over NotebookLM notebooks, sources, and artifacts
+---
+
+# NotebookLM Automation
+
+Complete programmatic control over NotebookLM notebooks, sources, and artifacts.
+
+## Prerequisites
+
+```bash
+pip install notebooklm-py
+playwright install chromium
+notebooklm login
+```
+
+## Commands
+
+### Notebooks
+```bash
+notebooklm list [--json]
+notebooklm create "Title" [--json]
+notebooklm rename <id> "New Name"
+notebooklm delete <id>
+notebooklm use <id>
+```
+
+### Sources
+```bash
+notebooklm source add "https://..." [--json]
+notebooklm source add ./file.pdf
+notebooklm source list [--json]
+notebooklm source delete <id>
+notebooklm source wait <id>
+```
+
+### Artifacts
+```bash
+notebooklm artifact list [--json]
+notebooklm artifact wait <id>
+notebooklm artifact delete <id>
+```
+
+## Environment Variables
+
+| Variable | Purpose |
+|----------|---------|
+| `NOTEBOOKLM_HOME` | Custom config dir |
+| `NOTEBOOKLM_AUTH_JSON` | Inline auth (CI/CD) |
+
+## Autonomy
+
+**Auto-run:** `list`, `status`, `create`, `use`, `source add`
+**Ask first:** `delete`, `rename`
+
+## Source
+Full details: `custom-skills/51-notebooklm-automation/code/CLAUDE.md`
diff --git a/.claude/commands/notebooklm-research.md b/.claude/commands/notebooklm-research.md
new file mode 100644
index 0000000..eb93111
--- /dev/null
+++ b/.claude/commands/notebooklm-research.md
@@ -0,0 +1,66 @@
+---
+description: NotebookLM research workflows - web research, Drive search, auto-import, source extraction
+---
+
+# NotebookLM Research
+
+Research workflows: web research, Drive search, auto-import, source extraction.
+
+## Prerequisites
+
+```bash
+pip install notebooklm-py
+playwright install chromium
+notebooklm login
+```
+
+## Research Commands
+
+```bash
+# Web research
+notebooklm source add-research "topic"
+notebooklm source add-research "topic" --mode deep --import-all
+notebooklm source add-research "topic" --mode deep --no-wait
+
+# Drive research
+notebooklm source add-research "topic" --from drive
+
+# Status and wait
+notebooklm research status
+notebooklm research wait --import-all
+```
+
+## Source Extraction
+
+```bash
+notebooklm source fulltext <id>
+notebooklm source guide <id>
+```
+
+## Research Modes
+
+| Mode | Sources | Time |
+|------|---------|------|
+| `fast` | 5-10 | seconds |
+| `deep` | 20+ | 2-5 min |
+
+## Subagent Pattern
+
+```python
+# Non-blocking deep research
+notebooklm source add-research "topic" --mode deep --no-wait
+
+# Spawn subagent to wait
+Task(
+  prompt="Wait for research and import: notebooklm research wait -n {id} --import-all",
+  subagent_type="general-purpose"
+)
+```
+
+## Autonomy
+
+**Auto-run:** `research status`, `source fulltext`, `source guide`
+**Ask first:** `source add-research`, `research wait --import-all`
+
+## Source
+Full details: `custom-skills/53-notebooklm-research/code/CLAUDE.md`
diff --git a/.claude/commands/notebooklm-studio.md b/.claude/commands/notebooklm-studio.md
new file mode 100644
index 0000000..287845b
--- /dev/null
+++ b/.claude/commands/notebooklm-studio.md
@@ -0,0 +1,73 @@
+---
+description: Generate NotebookLM Studio content - audio, video, quizzes, flashcards, slides, mind maps
+---
+
+# NotebookLM Studio
+
+Generate NotebookLM Studio content: audio, video, quizzes, flashcards, slides, infographics, mind maps.
+
+## Prerequisites
+
+```bash
+pip install notebooklm-py
+playwright install chromium
+notebooklm login
+```
+
+## Generate Commands
+
+```bash
+# Audio
+notebooklm generate audio "instructions"
+notebooklm generate audio --format debate --length longer
+
+# Video
+notebooklm generate video --style whiteboard
+
+# Quiz & Flashcards
+notebooklm generate quiz --difficulty hard
+notebooklm generate flashcards --quantity more
+
+# Visual
+notebooklm generate slide-deck --format detailed
+notebooklm generate infographic --orientation portrait
+notebooklm generate mind-map
+
+# Data
+notebooklm generate data-table "description"
+notebooklm generate report --format study_guide
+```
+
+## Download Commands
+
+```bash
+notebooklm artifact list  # Check status
+notebooklm download audio ./podcast.mp3
+notebooklm download video ./video.mp4
+notebooklm download quiz --format markdown ./quiz.md
+notebooklm download flashcards --format json ./cards.json
+notebooklm download slide-deck ./slides.pdf
+notebooklm download mind-map ./mindmap.json
+```
+
+## Styles & Formats
+
+**Video:** `classic`, `whiteboard`, `kawaii`, `anime`, `pixel`, `watercolor`, `neon`, `paper`, `sketch`
+**Audio:** `deep-dive`, `brief`, `critique`, `debate`
+
+## Timing
+
+| Type | Time |
+|------|------|
+| Mind map | Instant |
+| Quiz | 5-15 min |
+| Audio | 10-20 min |
+| Video | 15-45 min |
+
+## Autonomy
+
+**Auto-run:** `artifact list`
+**Ask first:** `generate *`, `download *`
+
+## Source
+Full details: `custom-skills/52-notebooklm-studio/code/CLAUDE.md`
diff --git a/.claude/commands/notion-writer.md b/.claude/commands/notion-writer.md
new file mode 100644
index 0000000..f8af2bd
--- /dev/null
+++ b/.claude/commands/notion-writer.md
@@ -0,0 +1,63 @@
+---
+description: Push markdown content to Notion pages or databases
+---
+
+# Notion Writer
+
+Push markdown content to Notion pages or databases via the Notion API.
+
+## Triggers
+- "write to Notion", "export to Notion", "노션에 쓰기"
+
+## Capabilities
+
+| Feature | Input | Output |
+|---------|-------|--------|
+| Page Content Append | Markdown + Page URL | Appended blocks |
+| Page Content Replace | Markdown + Page URL | Replaced content |
+| Database Row Create | Markdown + DB URL + Title | New database row |
+| Connection Test | API token | Connection status |
+
+## Environment
+- `NOTION_TOKEN` / `NOTION_API_KEY` - Notion integration token (required)
+
+## Scripts
+
+```bash
+cd ~/Projects/our-claude-skills/custom-skills/32-notion-writer/code/scripts
+
+# Test connection
+python notion_writer.py --test
+
+# Page info
+python notion_writer.py --page PAGE_URL --info
+
+# Write to page (append)
+python notion_writer.py --page PAGE_URL --file content.md
+
+# Replace page content
+python notion_writer.py --page PAGE_URL --file content.md --replace
+
+# Create database row
+python notion_writer.py --database DB_URL --title "New Entry" --file content.md
+
+# From stdin
+cat report.md | python notion_writer.py --page PAGE_URL --stdin
+```
+
+## Markdown Support
+
+Headings, bulleted/numbered lists, to-do items, quotes, code blocks (with language), dividers, paragraphs.
+
+## API Limits
+
+| Limit | Value |
+|-------|-------|
+| Blocks per request | 100 |
+| Text per block | 2,000 chars |
+| Requests/sec | ~3 |
+
+The script automatically batches large content.
+
+## Source
+Full details: `custom-skills/32-notion-writer/code/CLAUDE.md`
diff --git a/.claude/commands/ourdigital-brand-guide.md b/.claude/commands/ourdigital-brand-guide.md
new file mode 100644
index 0000000..a69b60a
--- /dev/null
+++ b/.claude/commands/ourdigital-brand-guide.md
@@ -0,0 +1,69 @@
+---
+description: OurDigital brand standards, writing style, and visual identity reference
+---
+
+# OurDigital Brand Guide
+
+Reference skill for OurDigital brand standards, writing style, and visual identity.
+
+## Triggers
+- "ourdigital brand guide", "our brand guide"
+- "ourdigital style check", "our style check"
+
+## Brand Foundation
+
+| Element | Content |
+|---------|---------|
+| **Brand Name** | OurDigital Clinic |
+| **Tagline** | 우리 디지털 클리닉 \| Your Digital Health Partner |
+| **Mission** | 디지털 마케팅 클리닉 for SMBs, 자영업자, 프리랜서, 비영리단체 |
+| **Promise** | 진단-처방-측정 가능한 성장 |
+
+### Core Values
+
+| 가치 | English | 클리닉 메타포 |
+|------|---------|--------------|
+| 데이터 중심 | Data-driven | 정밀 검사 |
+| 실행 지향 | In-Action | 실행 가능한 처방 |
+| 마케팅 과학 | Marketing Science | 근거 중심 의학 |
+
+## Channel Tone Matrix
+
+| Channel | Domain | Personality | Tone |
+|---------|--------|-------------|------|
+| Main Hub | ourdigital.org | Professional & Confident | Data-driven, Solution-oriented |
+| Blog | blog.ourdigital.org | Analytical & Personal | Educational, Thought-provoking |
+| Journal | journal.ourdigital.org | Conversational & Poetic | Reflective, Cultural Observer |
+| OurStory | ourstory.day | Intimate & Reflective | Authentic, Personal Journey |
+
+## Writing Style
+
+### Korean: 철학-기술 융합체, 역설 활용, 수사적 질문, 우울한 낙관주의
+### English: Philosophical-Technical Hybridization, Paradox as Device, Rhetorical Questions, Melancholic Optimism
+
+**Do's:** Use paradox, ask rhetorical questions, connect tech to human implications, blend Korean/English naturally
+**Don'ts:** Avoid purely declarative tone, don't separate tech from cultural impact, avoid simplistic optimism
+
+## Visual Identity
+
+| Token | Color | HEX | Usage |
+|-------|-------|-----|-------|
+| --d-black | D.Black | #221814 | Footer, dark backgrounds |
+| --d-olive | D.Olive | #cedc00 | Primary accent, CTA buttons |
+| --d-green | D.Green | #287379 | Links hover, secondary accent |
+| --d-blue | D.Blue | #0075c0 | Links |
+| --d-beige | D.Beige | #f2f2de | Light text on dark |
+| --d-gray | D.Gray | #ebebeb | Alt backgrounds |
+
+**Typography:** Korean: Noto Sans KR | English: Noto Sans, Inter | Grid: 12-column responsive
+
+## Brand Compliance Check
+
+1. **Tone Match**: Does it match the channel's personality?
+2. **Value Alignment**: Reflects Data-driven, In-Action, Marketing Science?
+3. **Philosophy Check**: Precision + Empathy + Evidence present?
+4. **Language Style**: Appropriate blend of Korean/English terms?
+5. **Visual Consistency**: Uses approved color palette?
+
+## Source
+Full details: `custom-skills/01-ourdigital-brand-guide/desktop/SKILL.md`
diff --git a/.claude/commands/reference-curator.md b/.claude/commands/reference-curator.md
new file mode 100644
index 0000000..7563838
--- /dev/null
+++ b/.claude/commands/reference-curator.md
@@ -0,0 +1,233 @@
+---
+description: Full reference curation pipeline - discovery, crawl, store, distill, review, export with configurable depth
+argument-hint: <topic|urls|manifest> [--depth light|standard|deep|full] [--output ~/Documents/reference-library/] [--max-sources 100] [--auto-approve] [--export-format project_files]
+allowed-tools: WebSearch, WebFetch, Read, Write, Bash, Grep, Glob, Task
+---
+
+# Reference Curator Pipeline
+
+Full-stack orchestration of the 6-skill reference curation workflow.
+
+## Input Modes
+
+| Mode | Input Example | Pipeline Start |
+|------|---------------|----------------|
+| **Topic** | `"Claude system prompts"` | reference-discovery |
+| **URLs** | `https://docs.anthropic.com/...` | web-crawler (skip discovery) |
+| **Manifest** | `./manifest.json` | web-crawler (resume) |
+
+## Arguments
+
+- `<input>`: Required. Topic string, URL(s), or manifest file path
+- `--depth`: Crawl depth level (default: `standard`). See Depth Levels below
+- `--output`: Output directory path (default: `~/Documents/reference-library/`)
+- `--max-sources`: Max sources to discover (default: 100)
+- `--max-pages`: Max pages per source to crawl (default varies by depth)
+- `--auto-approve`: Auto-approve scores above threshold
+- `--threshold`: Approval threshold (default: 0.85)
+- `--max-iterations`: Max QA loop iterations per document (default: 3)
+- `--export-format`: `project_files`, `fine_tuning`, `jsonl` (default: project_files)
+- `--include-subdomains`: Include subdomains in site mapping (default: false)
+- `--follow-external`: Follow external links found in content (default: false)
+
+## Output Directory
+
+**IMPORTANT: Never store output in any claude-skills, `.claude/`, or skill-related directory.**
+
+The `--output` argument sets the base path for all pipeline output. If omitted, the default is `~/Documents/reference-library/`.
+
+### Directory Structure
+
+```
+{output}/
+├── {topic-slug}/                   # One folder per pipeline run
+│   ├── README.md                   # Index with table of contents
+│   ├── 00-page-name.md             # Individual page files
+│   ├── 01-page-name.md
+│   ├── ...
+│   ├── {topic-slug}-complete.md    # Combined bundle (all pages)
+│   └── manifest.json               # Crawl metadata
+├── pipeline_state/                 # Resume state (auto-managed)
+│   └── run_XXX/state.json
+└── exports/                        # Fine-tuning / JSONL exports
+```
+
+### Resolution Rules
+
+1. If `--output` is provided, use that path exactly
+2. If not provided, use `~/Documents/reference-library/`
+3. **Before writing any files**, check if the output directory exists
+4. If the directory does NOT exist, **ask the user for permission** before creating it:
+   - Show the full resolved path that will be created
+   - Wait for explicit user approval
+   - Only then run `mkdir -p <path>`
+5. The topic slug is derived from the input (URL domain+path or topic string)
+
+### Examples
+
+```bash
+# Uses default: ~/Documents/reference-library/glossary-for-wordpress/
+/reference-curator https://docs.codeat.co/glossary/
+
+# Custom path: /tmp/research/mcp-docs/
+/reference-curator "MCP servers" --output /tmp/research
+
+# Explicit home subfolder: ~/Projects/client-docs/api-reference/
+/reference-curator https://api.example.com/docs --output ~/Projects/client-docs
+```
+
+## Depth Levels
+
+### `--depth light`
+Fast scan for quick reference. Main content only, minimal crawling.
+
+| Parameter | Value |
+|-----------|-------|
+| `onlyMainContent` | `true` |
+| `formats` | `["markdown"]` |
+| `maxDiscoveryDepth` | 1 |
+| `max-pages` default | 20 |
+| Map limit | 50 |
+| `deduplicateSimilarURLs` | `true` |
+| Follow sub-links | No |
+| JS rendering wait | None |
+
+**Best for:** Quick lookups, single-page references, API docs you already know.
+
+### `--depth standard` (default)
+Balanced crawl. Main content with links for cross-referencing.
+
+| Parameter | Value |
+|-----------|-------|
+| `onlyMainContent` | `true` |
+| `formats` | `["markdown", "links"]` |
+| `maxDiscoveryDepth` | 2 |
+| `max-pages` default | 50 |
+| Map limit | 100 |
+| `deduplicateSimilarURLs` | `true` |
+| Follow sub-links | Same-domain only |
+| JS rendering wait | None |
+
+**Best for:** Documentation sites, plugin guides, knowledge bases.
+
+### `--depth deep`
+Thorough crawl. Full page content including sidebars, nav, and related pages.
+
+| Parameter | Value |
+|-----------|-------|
+| `onlyMainContent` | `false` |
+| `formats` | `["markdown", "links", "html"]` |
+| `maxDiscoveryDepth` | 3 |
+| `max-pages` default | 150 |
+| Map limit | 300 |
+| `deduplicateSimilarURLs` | `true` |
+| Follow sub-links | Same-domain + linked resources |
+| JS rendering wait | `waitFor: 3000` |
+| `includeSubdomains` | `true` |
+
+**Best for:** Complete product documentation, research material, sites with sidebars/code samples hidden behind tabs.
+
+### `--depth full`
+Exhaustive crawl. Everything captured including raw HTML, screenshots, and external references.
+
+| Parameter | Value |
+|-----------|-------|
+| `onlyMainContent` | `false` |
+| `formats` | `["markdown", "html", "rawHtml", "links"]` |
+| `maxDiscoveryDepth` | 5 |
+| `max-pages` default | 500 |
+| Map limit | 1000 |
+| `deduplicateSimilarURLs` | `false` |
+| Follow sub-links | All (same-domain + external references) |
+| JS rendering wait | `waitFor: 5000` |
+| `includeSubdomains` | `true` |
+| Screenshots | Capture for JS-heavy pages |
+
+**Best for:** Archival, migration references, preserving sites, training data collection.
+
+## Depth Comparison
+
+```
+light       ████░░░░░░░░░░░░  Speed: fastest   Pages: ~20    Content: main only
+standard    ████████░░░░░░░░  Speed: fast       Pages: ~50    Content: main + links
+deep        ████████████░░░░  Speed: moderate   Pages: ~150   Content: full page + HTML
+full        ████████████████  Speed: slow       Pages: ~500   Content: everything + raw
+```
+
+## Pipeline Stages
+
+```
+1. reference-discovery  (topic mode only)
+2. web-crawler  ← depth controls this stage
+3. content-repository
+4. content-distiller    <--------+
+5. quality-reviewer              |
+   +-- APPROVE -> export         |
+   +-- REFACTOR -----------------+
+   +-- DEEP_RESEARCH -> crawler -+
+   +-- REJECT -> archive
+6. markdown-exporter
+```
+
+## Crawl Execution by Depth
+
+When executing the crawl (Stage 2), apply the depth settings to the Firecrawl tools:
+
+### Site Mapping (`firecrawl_map`)
+```
+firecrawl_map:
+  url: <target>
+  limit: {depth.map_limit}
+  includeSubdomains: {depth.includeSubdomains}
+```
+
+### Page Scraping (`firecrawl_scrape`)
+```
+firecrawl_scrape:
+  url: <page>
+  formats: {depth.formats}
+  onlyMainContent: {depth.onlyMainContent}
+  waitFor: {depth.waitFor}           # deep/full only
+  excludeTags: ["nav", "footer"]     # light/standard only
+```
+
+### Batch Crawling (`firecrawl_crawl`) - for deep/full only
+```
+firecrawl_crawl:
+  url: <target>
+  maxDiscoveryDepth: {depth.maxDiscoveryDepth}
+  limit: {depth.max_pages}
+  deduplicateSimilarURLs: {depth.dedup}
+  scrapeOptions:
+    formats: {depth.formats}
+    onlyMainContent: {depth.onlyMainContent}
+    waitFor: {depth.waitFor}
+```
+
+## Example Usage
+
+```bash
+# Quick scan of a single doc page
+/reference-curator https://docs.example.com/api --depth light
+
+# Standard documentation crawl (default)
+/reference-curator "Glossary for WordPress" --max-sources 5
+
+# Deep crawl capturing full page content and HTML
+/reference-curator https://docs.codeat.co/glossary/ --depth deep
+
+# Full archival crawl with all formats
+/reference-curator https://docs.anthropic.com --depth full --max-pages 300
+
+# Deep crawl with auto-approval and fine-tuning export
+/reference-curator "MCP servers" --depth deep --auto-approve --export-format fine_tuning
+```
+
+## Related Sub-commands
+
+Individual stages available at: `custom-skills/90-reference-curator/commands/`
+- `/reference-discovery`, `/web-crawler`, `/content-repository`
+- `/content-distiller`, `/quality-reviewer`, `/markdown-exporter`
+
+## Source
+Full details: `custom-skills/90-reference-curator/README.md`
diff --git a/.claude/commands/seo-ai-visibility.md b/.claude/commands/seo-ai-visibility.md
new file mode 100644
index 0000000..f18298b
--- /dev/null
+++ b/.claude/commands/seo-ai-visibility.md
@@ -0,0 +1,63 @@
+---
+description: AI search visibility - citations, brand radar, share of voice tracking
+---
+
+# SEO AI Visibility
+
+Track brand visibility in AI-generated search answers with citation analysis and share of voice monitoring.
+
+## Triggers
+- "AI visibility", "AI search", "AI citations", "AI share of voice"
+
+## Capabilities
+
+1. **AI Impressions Tracking** - How often brand appears in AI answers
+2. **AI Mentions Monitoring** - Brand mention frequency across AI engines
+3. **Share of Voice** - AI search SOV vs competitors with trend analysis
+4. **Citation Analysis** - Which domains and pages AI engines cite
+5. **AI Response Analysis** - How the brand appears in AI-generated answers
+6. **Competitor Comparison** - Side-by-side AI visibility benchmarking
+
+## Scripts
+
+```bash
+# AI visibility overview
+python custom-skills/27-seo-ai-visibility/code/scripts/ai_visibility_tracker.py \
+  --target example.com --json
+
+# With competitor comparison
+python custom-skills/27-seo-ai-visibility/code/scripts/ai_visibility_tracker.py \
+  --target example.com --competitor comp1.com --competitor comp2.com --json
+
+# Historical trend (impressions/mentions)
+python custom-skills/27-seo-ai-visibility/code/scripts/ai_visibility_tracker.py \
+  --target example.com --history --json
+
+# Share of voice analysis
+python custom-skills/27-seo-ai-visibility/code/scripts/ai_visibility_tracker.py \
+  --target example.com --sov --json
+
+# AI citation analysis
+python custom-skills/27-seo-ai-visibility/code/scripts/ai_citation_analyzer.py \
+  --target example.com --json
+
+# Cited domains analysis
+python custom-skills/27-seo-ai-visibility/code/scripts/ai_citation_analyzer.py \
+  --target example.com --cited-domains --json
+
+# Cited pages analysis
+python custom-skills/27-seo-ai-visibility/code/scripts/ai_citation_analyzer.py \
+  --target example.com --cited-pages --json
+
+# AI response content analysis
+python custom-skills/27-seo-ai-visibility/code/scripts/ai_citation_analyzer.py \
+  --target example.com --responses --json
+```
+
+## Output
+- AI impressions and mentions with trend indicators
+- Share of voice percentage vs competitors
+- Cited domains and pages ranked by frequency
+- AI response samples showing brand context
+- Recommendations for improving AI visibility
+- Reports saved to Notion SEO Audit Log (Category: AI Search Visibility)
diff --git a/.claude/commands/seo-competitor-intel.md b/.claude/commands/seo-competitor-intel.md
new file mode 100644
index 0000000..5009b69
--- /dev/null
+++ b/.claude/commands/seo-competitor-intel.md
@@ -0,0 +1,53 @@
+---
+description: SEO competitor intelligence and benchmarking
+---
+
+# SEO Competitor Intelligence
+
+Competitor profiling, benchmarking, and threat scoring for comprehensive SEO competitive analysis.
+
+## Triggers
+- "competitor analysis", "competitive intel", "경쟁사 분석"
+
+## Capabilities
+
+1. **Competitor Profiling** - Auto-discover competitors, build profile cards (DR, traffic, keywords, backlinks, content volume)
+2. **Head-to-Head Matrix** - Comparison across all SEO dimensions
+3. **Keyword Overlap** - Shared, unique, and gap keyword analysis
+4. **Threat Scoring** - 0-100 score based on growth trajectory, keyword overlap, DR gap
+5. **Korean Market** - Naver Blog/Cafe presence detection for competitors
+6. **Competitive Monitoring** - Traffic trends, keyword movement, content velocity over time
+7. **Market Share** - Organic traffic-based market share estimation
+
+## Scripts
+
+```bash
+# Auto-discover and profile competitors
+python custom-skills/31-seo-competitor-intel/code/scripts/competitor_profiler.py \
+  --target https://example.com --json
+
+# Specify competitors manually
+python custom-skills/31-seo-competitor-intel/code/scripts/competitor_profiler.py \
+  --target https://example.com --competitor https://comp1.com --competitor https://comp2.com --json
+
+# Include Korean market analysis
+python custom-skills/31-seo-competitor-intel/code/scripts/competitor_profiler.py \
+  --target https://example.com --korean-market --json
+
+# 30-day competitive monitoring
+python custom-skills/31-seo-competitor-intel/code/scripts/competitive_monitor.py \
+  --target https://example.com --period 30 --json
+
+# Traffic trend comparison (90 days)
+python custom-skills/31-seo-competitor-intel/code/scripts/competitive_monitor.py \
+  --target https://example.com --scope traffic --period 90 --json
+```
+
+## Output
+- Competitor profile cards with DR, traffic, keywords, referring domains
+- Head-to-head comparison matrix
+- Keyword overlap analysis (shared/unique/gap)
+- Threat scores (0-100) per competitor
+- Traffic trend and market share charts
+- Alerts for significant competitive movements
+- Saved to Notion SEO Audit Log (Category: Competitor Intelligence, Audit ID: COMP-YYYYMMDD-NNN)
diff --git a/.claude/commands/seo-content-strategy.md b/.claude/commands/seo-content-strategy.md
new file mode 100644
index 0000000..3ae372a
--- /dev/null
+++ b/.claude/commands/seo-content-strategy.md
@@ -0,0 +1,56 @@
+---
+description: Content audit, decay detection, gap analysis, and brief generation
+---
+
+# SEO Content Strategy
+
+Content inventory, performance scoring, decay detection, topic gap analysis, cluster mapping, and SEO content brief generation.
+
+## Triggers
+- "content strategy", "content audit", "콘텐츠 전략"
+
+## Capabilities
+
+1. **Content Audit** - Inventory via sitemap crawl with performance scoring
+2. **Content Decay Detection** - Identify pages losing traffic over time
+3. **Content Type Classification** - Blog, product, service, landing, resource
+4. **Topic Gap Analysis** - Find missing topics vs competitors with cluster mapping
+5. **Editorial Calendar** - Priority-scored publishing calendar from gap analysis
+6. **Content Brief Generation** - SEO briefs with H2/H3 outlines, keyword targets, and word count recommendations
+7. **Korean Content Analysis** - Naver Blog format and review/후기 content patterns
+
+## Scripts
+
+```bash
+# Full content audit
+python custom-skills/23-seo-content-strategy/code/scripts/content_auditor.py \
+  --url https://example.com --json
+
+# Detect decaying content
+python custom-skills/23-seo-content-strategy/code/scripts/content_auditor.py \
+  --url https://example.com --decay --json
+
+# Filter by content type
+python custom-skills/23-seo-content-strategy/code/scripts/content_auditor.py \
+  --url https://example.com --type blog --json
+
+# Content gap analysis with topic clusters
+python custom-skills/23-seo-content-strategy/code/scripts/content_gap_analyzer.py \
+  --target https://example.com --competitor https://comp1.com --clusters --json
+
+# Generate content brief for keyword
+python custom-skills/23-seo-content-strategy/code/scripts/content_brief_generator.py \
+  --keyword "치과 임플란트 비용" --url https://example.com --json
+
+# Brief with competitor analysis
+python custom-skills/23-seo-content-strategy/code/scripts/content_brief_generator.py \
+  --keyword "dental implant cost" --url https://example.com --competitors 5 --json
+```
+
+## Output
+- Content inventory with page count by type and average performance score
+- Decaying content list with traffic trend data
+- Topic gaps and cluster map with pillar/cluster pages
+- Editorial calendar with priority scores
+- Content briefs with outline, keywords, word count targets, and internal link suggestions
+- Reports saved to Notion SEO Audit Log (Category: Content Strategy, ID: CONTENT-YYYYMMDD-NNN)
diff --git a/.claude/commands/seo-crawl-budget.md b/.claude/commands/seo-crawl-budget.md
new file mode 100644
index 0000000..a64ad0f
--- /dev/null
+++ b/.claude/commands/seo-crawl-budget.md
@@ -0,0 +1,54 @@
+---
+description: Crawl budget optimization and log analysis
+---
+
+# SEO Crawl Budget
+
+Server access log analysis, bot profiling, and crawl budget waste identification.
+
+## Triggers
+- "crawl budget", "log analysis", "크롤 예산"
+
+## Capabilities
+
+1. **Log Parsing** - Parse Nginx, Apache, CloudFront access logs (streaming for >1GB files)
+2. **Bot Identification** - Googlebot, Yeti/Naver, Bingbot, Daumoa/Kakao, and others by User-Agent
+3. **Per-Bot Profiling** - Crawl frequency, depth distribution, status codes, crawl patterns
+4. **Waste Detection** - Parameter URLs, low-value pages, redirect chains, soft 404s, duplicate URLs
+5. **Orphan Pages** - Pages in sitemap but never crawled, crawled but not in sitemap
+6. **Optimization Plan** - robots.txt suggestions, URL parameter handling, noindex recommendations
+
+## Scripts
+
+```bash
+# Parse Nginx access log
+python custom-skills/32-seo-crawl-budget/code/scripts/log_parser.py \
+  --log-file /var/log/nginx/access.log --json
+
+# Parse Apache log, filter by Googlebot
+python custom-skills/32-seo-crawl-budget/code/scripts/log_parser.py \
+  --log-file /var/log/apache2/access.log --format apache --bot googlebot --json
+
+# Parse gzipped log in streaming mode
+python custom-skills/32-seo-crawl-budget/code/scripts/log_parser.py \
+  --log-file access.log.gz --streaming --json
+
+# Full crawl budget analysis with sitemap comparison
+python custom-skills/32-seo-crawl-budget/code/scripts/crawl_budget_analyzer.py \
+  --log-file access.log --sitemap https://example.com/sitemap.xml --json
+
+# Waste identification only
+python custom-skills/32-seo-crawl-budget/code/scripts/crawl_budget_analyzer.py \
+  --log-file access.log --scope waste --json
+
+# Orphan page detection
+python custom-skills/32-seo-crawl-budget/code/scripts/crawl_budget_analyzer.py \
+  --log-file access.log --sitemap https://example.com/sitemap.xml --scope orphans --json
+```
+
+## Output
+- Bot request counts, status code distribution, top crawled URLs per bot
+- Crawl waste breakdown (parameter URLs, redirects, soft 404s, duplicates)
+- Orphan page lists (in sitemap not crawled, crawled not in sitemap)
+- Efficiency score (0-100) with optimization recommendations
+- Saved to Notion SEO Audit Log (Category: Crawl Budget, Audit ID: CRAWL-YYYYMMDD-NNN)
diff --git a/.claude/commands/seo-ecommerce.md b/.claude/commands/seo-ecommerce.md
new file mode 100644
index 0000000..37528b8
--- /dev/null
+++ b/.claude/commands/seo-ecommerce.md
@@ -0,0 +1,56 @@
+---
+description: E-commerce SEO audit and product schema validation
+---
+
+# SEO E-Commerce
+
+Product page SEO audit, product schema validation, category taxonomy analysis, and Korean marketplace presence checking.
+
+## Triggers
+- "e-commerce SEO", "product SEO", "이커머스 SEO"
+
+## Capabilities
+
+1. **Product Page Audit** - Titles, meta descriptions, image alt text, H1 structure
+2. **Category Taxonomy Analysis** - Depth, breadcrumb implementation, faceted navigation
+3. **Duplicate Content Detection** - Parameter URLs, product variants, pagination issues
+4. **Pagination SEO** - Validate rel=prev/next, canonical tags, infinite scroll handling
+5. **Product Schema Validation** - Product, Offer, AggregateRating, Review, BreadcrumbList
+6. **Rich Result Eligibility** - Required and optional property completeness checks
+7. **Korean Marketplace Presence** - Naver Smart Store, Coupang, Gmarket, 11번가 detection
+
+## Scripts
+
+```bash
+# Full e-commerce SEO audit
+python custom-skills/24-seo-ecommerce/code/scripts/ecommerce_auditor.py \
+  --url https://example.com --json
+
+# Product page audit only
+python custom-skills/24-seo-ecommerce/code/scripts/ecommerce_auditor.py \
+  --url https://example.com --scope products --json
+
+# Category taxonomy analysis
+python custom-skills/24-seo-ecommerce/code/scripts/ecommerce_auditor.py \
+  --url https://example.com --scope categories --json
+
+# Korean marketplace presence check
+python custom-skills/24-seo-ecommerce/code/scripts/ecommerce_auditor.py \
+  --url https://example.com --korean-marketplaces --json
+
+# Validate product schema on single page
+python custom-skills/24-seo-ecommerce/code/scripts/product_schema_checker.py \
+  --url https://example.com/product/123 --json
+
+# Batch validate from sitemap (sample 50 pages)
+python custom-skills/24-seo-ecommerce/code/scripts/product_schema_checker.py \
+  --sitemap https://example.com/product-sitemap.xml --sample 50 --json
+```
+
+## Output
+- Product page issue list by severity (critical, high, medium, low)
+- Category structure analysis (depth, breadcrumbs, faceted nav issues)
+- Schema validation results (pages with/without schema, common errors)
+- Rich result eligibility assessment
+- Korean marketplace presence status (Naver Smart Store, Coupang, Gmarket)
+- Reports saved to Notion SEO Audit Log (Category: E-Commerce SEO, ID: ECOM-YYYYMMDD-NNN)
diff --git a/.claude/commands/seo-gateway-architect.md b/.claude/commands/seo-gateway-architect.md
index 432021e..bc8817c 100644
--- a/.claude/commands/seo-gateway-architect.md
+++ b/.claude/commands/seo-gateway-architect.md
@@ -20,11 +20,11 @@ Keyword strategy and content architecture for gateway pages.
 
 ```bash
 # Analyze keyword
-python custom-skills/17-seo-gateway-architect/code/scripts/keyword_analyzer.py \
+python custom-skills/29-seo-gateway-architect/code/scripts/keyword_analyzer.py \
   --topic "눈 성형"
 
 # With location targeting
-python custom-skills/17-seo-gateway-architect/code/scripts/keyword_analyzer.py \
+python custom-skills/29-seo-gateway-architect/code/scripts/keyword_analyzer.py \
   --topic "눈 성형" --market "강남" --output strategy.json
 ```
 
diff --git a/.claude/commands/seo-gateway-builder.md b/.claude/commands/seo-gateway-builder.md
index d8f0eb2..855948d 100644
--- a/.claude/commands/seo-gateway-builder.md
+++ b/.claude/commands/seo-gateway-builder.md
@@ -20,10 +20,10 @@ Generate SEO-optimized gateway pages from templates.
 
 ```bash
 # Generate with sample data
-python custom-skills/18-seo-gateway-builder/code/scripts/generate_pages.py
+python custom-skills/30-seo-gateway-builder/code/scripts/generate_pages.py
 
 # Custom configuration
-python custom-skills/18-seo-gateway-builder/code/scripts/generate_pages.py \
+python custom-skills/30-seo-gateway-builder/code/scripts/generate_pages.py \
   --config config/services.json \
   --locations config/locations.json \
   --output ./pages
diff --git a/.claude/commands/seo-gsc.md b/.claude/commands/seo-gsc.md
index 63c72ca..817b69b 100644
--- a/.claude/commands/seo-gsc.md
+++ b/.claude/commands/seo-gsc.md
@@ -20,15 +20,15 @@ Google Search Console data retrieval and analysis.
 
 ```bash
 # Get search performance
-python custom-skills/16-seo-search-console/code/scripts/gsc_client.py \
+python custom-skills/15-seo-search-console/code/scripts/gsc_client.py \
   --site https://example.com --days 28
 
 # Query analysis
-python custom-skills/16-seo-search-console/code/scripts/gsc_client.py \
+python custom-skills/15-seo-search-console/code/scripts/gsc_client.py \
   --site https://example.com --report queries --limit 100
 
 # Page performance
-python custom-skills/16-seo-search-console/code/scripts/gsc_client.py \
+python custom-skills/15-seo-search-console/code/scripts/gsc_client.py \
   --site https://example.com --report pages --output pages_report.json
 ```
 
diff --git a/.claude/commands/seo-international.md b/.claude/commands/seo-international.md
new file mode 100644
index 0000000..48c7e4f
--- /dev/null
+++ b/.claude/commands/seo-international.md
@@ -0,0 +1,59 @@
+---
+description: International SEO - hreflang validation, content parity, multi-language audit
+---
+
+# SEO International Audit
+
+Multi-language and multi-region SEO audit with hreflang validation and content parity analysis.
+
+## Triggers
+- "international SEO", "hreflang", "multi-language SEO", "다국어 SEO"
+
+## Capabilities
+
+1. **Hreflang Validation** - Bidirectional links, self-referencing, x-default, ISO code checks
+2. **URL Structure Analysis** - ccTLD vs subdomain vs subdirectory with recommendations
+3. **Content Parity** - Page count, key page availability, freshness comparison across languages
+4. **Language Detection** - HTML lang attribute, Content-Language header, actual content analysis
+5. **Redirect Logic Audit** - IP-based and Accept-Language redirect behavior
+6. **Korean Expansion** - Priority markets (ko->ja, ko->zh, ko->en), CJK URL encoding, Naver/Baidu considerations
+
+## Scripts
+
+```bash
+# Hreflang validation
+python custom-skills/26-seo-international/code/scripts/hreflang_validator.py \
+  --url https://example.com --json
+
+# With sitemap-based discovery
+python custom-skills/26-seo-international/code/scripts/hreflang_validator.py \
+  --url https://example.com --sitemap https://example.com/sitemap.xml --json
+
+# Check specific pages from file
+python custom-skills/26-seo-international/code/scripts/hreflang_validator.py \
+  --urls-file pages.txt --json
+
+# Full international audit
+python custom-skills/26-seo-international/code/scripts/international_auditor.py \
+  --url https://example.com --json
+
+# URL structure analysis only
+python custom-skills/26-seo-international/code/scripts/international_auditor.py \
+  --url https://example.com --scope structure --json
+
+# Content parity check only
+python custom-skills/26-seo-international/code/scripts/international_auditor.py \
+  --url https://example.com --scope parity --json
+
+# Korean expansion focus
+python custom-skills/26-seo-international/code/scripts/international_auditor.py \
+  --url https://example.com --korean-expansion --json
+```
+
+## Output
+- Hreflang error report (missing bidirectional, self-reference, x-default)
+- URL structure recommendation
+- Content parity matrix across languages (page count, freshness)
+- Redirect logic assessment (forced vs suggested)
+- International SEO score
+- Reports saved to Notion SEO Audit Log (Category: International SEO)
diff --git a/.claude/commands/seo-keyword-strategy.md b/.claude/commands/seo-keyword-strategy.md
new file mode 100644
index 0000000..c3f7f4d
--- /dev/null
+++ b/.claude/commands/seo-keyword-strategy.md
@@ -0,0 +1,50 @@
+---
+description: Keyword strategy and research for SEO campaigns
+---
+
+# SEO Keyword Strategy
+
+Keyword expansion, intent classification, clustering, and competitor gap analysis. Supports Korean market with Naver autocomplete.
+
+## Triggers
+- "keyword research", "keyword strategy", "키워드 리서치"
+
+## Capabilities
+
+1. **Keyword Expansion** - Seed keyword expansion with matching, related, and suggested terms
+2. **Intent Classification** - Classify keywords as informational, navigational, commercial, or transactional
+3. **Topic Clustering** - Group keywords into topic clusters with volume aggregation
+4. **Korean Suffix Expansion** - Expand with Korean suffixes (추천, 가격, 후기, 잘하는곳, 부작용, 전후)
+5. **Volume Comparison** - Compare search volume across Korea vs global markets
+6. **Keyword Gap Analysis** - Find keywords competitors rank for but target does not
+
+## Scripts
+
+```bash
+# Basic keyword research
+python custom-skills/19-seo-keyword-strategy/code/scripts/keyword_researcher.py \
+  --keyword "치과 임플란트" --country kr --json
+
+# Korean market with suffix expansion
+python custom-skills/19-seo-keyword-strategy/code/scripts/keyword_researcher.py \
+  --keyword "치과 임플란트" --country kr --korean-suffixes --json
+
+# Volume comparison Korea vs global
+python custom-skills/19-seo-keyword-strategy/code/scripts/keyword_researcher.py \
+  --keyword "dental implant" --country kr --compare-global --json
+
+# Keyword gap vs competitor
+python custom-skills/19-seo-keyword-strategy/code/scripts/keyword_gap_analyzer.py \
+  --target https://example.com --competitor https://competitor.com --json
+
+# Multiple competitors with minimum volume filter
+python custom-skills/19-seo-keyword-strategy/code/scripts/keyword_gap_analyzer.py \
+  --target https://example.com --competitor https://comp1.com \
+  --competitor https://comp2.com --min-volume 100 --json
+```
+
+## Output
+- Keyword list with volume, KD, CPC, intent, and cluster assignment
+- Topic clusters with aggregated volume
+- Gap keywords with opportunity scores
+- Reports saved to Notion SEO Audit Log (Category: Keyword Research, ID: KW-YYYYMMDD-NNN)
diff --git a/.claude/commands/seo-knowledge-graph.md b/.claude/commands/seo-knowledge-graph.md
new file mode 100644
index 0000000..a995698
--- /dev/null
+++ b/.claude/commands/seo-knowledge-graph.md
@@ -0,0 +1,57 @@
+---
+description: Knowledge Graph & Entity SEO - Knowledge Panel, PAA, FAQ rich results
+---
+
+# SEO Knowledge Graph
+
+Entity SEO analysis for Knowledge Panel presence, People Also Ask monitoring, and FAQ rich results tracking.
+
+## Triggers
+- "knowledge graph", "entity SEO", "Knowledge Panel", "PAA monitoring"
+
+## Capabilities
+
+1. **Knowledge Panel Detection** - Check entity presence in Google Knowledge Graph
+2. **Entity Attribute Analysis** - Name, type, description, logo, social profiles, completeness score
+3. **Wikipedia/Wikidata Check** - Article and QID presence verification
+4. **Naver Presence** - Encyclopedia and knowledge iN (지식iN) coverage
+5. **PAA Monitoring** - People Also Ask tracking for brand queries
+6. **FAQ Rich Results** - FAQPage schema presence and SERP appearance tracking
+7. **Entity Markup Audit** - Organization/Person/LocalBusiness schema and sameAs validation
+
+## Scripts
+
+```bash
+# Knowledge Graph analysis
+python custom-skills/28-seo-knowledge-graph/code/scripts/knowledge_graph_analyzer.py \
+  --entity "Samsung Electronics" --json
+
+# Korean entity check
+python custom-skills/28-seo-knowledge-graph/code/scripts/knowledge_graph_analyzer.py \
+  --entity "삼성전자" --language ko --json
+
+# Include Wikipedia/Wikidata check
+python custom-skills/28-seo-knowledge-graph/code/scripts/knowledge_graph_analyzer.py \
+  --entity "Samsung" --wiki --json
+
+# Full entity SEO audit
+python custom-skills/28-seo-knowledge-graph/code/scripts/entity_auditor.py \
+  --url https://example.com --entity "Brand Name" --json
+
+# PAA monitoring
+python custom-skills/28-seo-knowledge-graph/code/scripts/entity_auditor.py \
+  --url https://example.com --entity "Brand Name" --paa --json
+
+# FAQ rich result tracking
+python custom-skills/28-seo-knowledge-graph/code/scripts/entity_auditor.py \
+  --url https://example.com --entity "Brand Name" --faq --json
+```
+
+## Output
+- Knowledge Panel detection with attribute completeness score
+- Wikipedia/Wikidata presence status
+- Naver encyclopedia and knowledge iN coverage
+- PAA questions list for brand keywords
+- FAQ rich result tracking
+- Entity schema audit (Organization, sameAs links)
+- Reports saved to Notion SEO Audit Log (Category: Knowledge Graph & Entity SEO)
diff --git a/.claude/commands/seo-kpi-framework.md b/.claude/commands/seo-kpi-framework.md
new file mode 100644
index 0000000..0d07b2b
--- /dev/null
+++ b/.claude/commands/seo-kpi-framework.md
@@ -0,0 +1,63 @@
+---
+description: SEO KPI framework - unified metrics, health scores, ROI estimation
+---
+
+# SEO KPI Framework
+
+Unified KPI aggregation across all SEO dimensions with health scores, baselines, and ROI estimation.
+
+## Triggers
+- "SEO KPI", "SEO performance", "health score", "SEO ROI"
+
+## Capabilities
+
+1. **KPI Aggregation** - Unified metrics across 7 dimensions (traffic, rankings, engagement, technical, content, links, local)
+2. **Health Score** - Weighted 0-100 score with trend indicators
+3. **Baseline & Targets** - Establish baselines and set 30/60/90-day targets
+4. **Performance Reporting** - Period-over-period comparison (MoM, QoQ, YoY)
+5. **Executive Summary** - Top wins, concerns, and recommendations
+6. **ROI Estimation** - Organic traffic cost valuation
+
+## Scripts
+
+```bash
+# Aggregate KPIs
+python custom-skills/25-seo-kpi-framework/code/scripts/kpi_aggregator.py \
+  --url https://example.com --json
+
+# Set baseline
+python custom-skills/25-seo-kpi-framework/code/scripts/kpi_aggregator.py \
+  --url https://example.com --set-baseline --json
+
+# Compare against baseline
+python custom-skills/25-seo-kpi-framework/code/scripts/kpi_aggregator.py \
+  --url https://example.com --baseline baseline.json --json
+
+# With ROI estimation
+python custom-skills/25-seo-kpi-framework/code/scripts/kpi_aggregator.py \
+  --url https://example.com --roi --json
+
+# Monthly performance report
+python custom-skills/25-seo-kpi-framework/code/scripts/performance_reporter.py \
+  --url https://example.com --period monthly --json
+
+# Quarterly report
+python custom-skills/25-seo-kpi-framework/code/scripts/performance_reporter.py \
+  --url https://example.com --period quarterly --json
+
+# Custom date range
+python custom-skills/25-seo-kpi-framework/code/scripts/performance_reporter.py \
+  --url https://example.com --from 2025-01-01 --to 2025-03-31 --json
+
+# Executive summary only
+python custom-skills/25-seo-kpi-framework/code/scripts/performance_reporter.py \
+  --url https://example.com --period monthly --executive --json
+```
+
+## Output
+- Unified KPI dashboard with health score (0-100)
+- 7-dimension breakdown (traffic, rankings, engagement, technical, content, links, local)
+- Trend indicators (up/down/stable) per dimension
+- 30/60/90-day targets with progress tracking
+- Executive summary with top wins and concerns
+- Reports saved to Notion SEO Audit Log (Category: SEO KPI & Performance)
diff --git a/.claude/commands/seo-link-building.md b/.claude/commands/seo-link-building.md
new file mode 100644
index 0000000..50df54e
--- /dev/null
+++ b/.claude/commands/seo-link-building.md
@@ -0,0 +1,58 @@
+---
+description: Backlink audit, toxic link detection, and link gap analysis
+---
+
+# SEO Link Building
+
+Backlink profile analysis, toxic link detection, competitor link gap identification, and Korean platform link mapping.
+
+## Triggers
+- "backlink audit", "link building", "링크 분석"
+
+## Capabilities
+
+1. **Backlink Profile Audit** - DR, referring domains, dofollow ratio
+2. **Anchor Text Distribution** - Branded, exact-match, partial-match, generic, naked URL breakdown
+3. **Toxic Link Detection** - PBN patterns, spammy domains, link farm identification
+4. **Link Velocity Tracking** - New and lost referring domains over time
+5. **Broken Backlink Recovery** - Find broken backlinks for reclamation
+6. **Korean Platform Mapping** - Naver Blog, Naver Cafe, Tistory, Brunch link analysis
+7. **Link Gap Analysis** - Find domains linking to competitors but not target
+
+## Scripts
+
+```bash
+# Full backlink audit
+python custom-skills/22-seo-link-building/code/scripts/backlink_auditor.py \
+  --url https://example.com --json
+
+# Check link velocity
+python custom-skills/22-seo-link-building/code/scripts/backlink_auditor.py \
+  --url https://example.com --velocity --json
+
+# Find broken backlinks for recovery
+python custom-skills/22-seo-link-building/code/scripts/backlink_auditor.py \
+  --url https://example.com --broken --json
+
+# Korean platform link analysis
+python custom-skills/22-seo-link-building/code/scripts/backlink_auditor.py \
+  --url https://example.com --korean-platforms --json
+
+# Link gap vs competitor
+python custom-skills/22-seo-link-building/code/scripts/link_gap_finder.py \
+  --target https://example.com --competitor https://comp1.com --json
+
+# Multiple competitors with minimum DR filter
+python custom-skills/22-seo-link-building/code/scripts/link_gap_finder.py \
+  --target https://example.com --competitor https://comp1.com \
+  --competitor https://comp2.com --min-dr 30 --json
+```
+
+## Output
+- Domain Rating, backlink stats, dofollow ratio
+- Anchor text distribution percentages
+- Toxic link list with detection reason
+- Link velocity (new/lost last 30 days)
+- Korean platform backlink counts
+- Gap domains scored by DR, traffic, and relevance
+- Reports saved to Notion SEO Audit Log (Category: Link Building, ID: LINK-YYYYMMDD-NNN)
diff --git a/.claude/commands/seo-migration-planner.md b/.claude/commands/seo-migration-planner.md
new file mode 100644
index 0000000..9f96600
--- /dev/null
+++ b/.claude/commands/seo-migration-planner.md
@@ -0,0 +1,57 @@
+---
+description: Site migration planning and post-migration monitoring
+---
+
+# SEO Migration Planner
+
+Pre-migration risk assessment, redirect mapping, and post-migration traffic/indexation monitoring.
+
+## Triggers
+- "site migration", "domain move", "사이트 이전"
+
+## Capabilities
+
+1. **URL Inventory** - Full URL capture via Firecrawl crawl with status codes
+2. **Traffic Baseline** - Per-page traffic and keyword baseline via our-seo-agent
+3. **Redirect Mapping** - Old URL to new URL mapping with per-URL risk scoring
+4. **Risk Assessment** - Per-URL risk based on traffic, backlinks, keyword rankings
+5. **Pre-Migration Checklist** - Automated checklist generation
+6. **Post-Migration Monitoring** - Traffic comparison, redirect health, indexation tracking
+7. **Migration Types** - Domain move, platform change, URL restructure, HTTPS, subdomain consolidation
+
+## Scripts
+
+```bash
+# Domain move planning
+python custom-skills/33-seo-migration-planner/code/scripts/migration_planner.py \
+  --domain https://example.com --type domain-move --new-domain https://new-example.com --json
+
+# Platform migration (e.g., WordPress to headless)
+python custom-skills/33-seo-migration-planner/code/scripts/migration_planner.py \
+  --domain https://example.com --type platform --json
+
+# URL restructuring
+python custom-skills/33-seo-migration-planner/code/scripts/migration_planner.py \
+  --domain https://example.com --type url-restructure --json
+
+# HTTPS migration
+python custom-skills/33-seo-migration-planner/code/scripts/migration_planner.py \
+  --domain http://example.com --type https --json
+
+# Post-launch traffic comparison
+python custom-skills/33-seo-migration-planner/code/scripts/migration_monitor.py \
+  --domain https://new-example.com --migration-date 2025-01-15 --baseline baseline.json --json
+
+# Quick redirect health check
+python custom-skills/33-seo-migration-planner/code/scripts/migration_monitor.py \
+  --domain https://new-example.com --migration-date 2025-01-15 --json
+```
+
+## Output
+- URL inventory with traffic/keyword baselines
+- Redirect map (source -> target, status code, priority)
+- Risk assessment (high/medium/low risk URL counts, overall risk level)
+- Pre-migration checklist
+- Post-migration: traffic delta, broken redirects, ranking changes, recovery timeline
+- Alerts for traffic drops >20%
+- Saved to Notion SEO Audit Log (Category: SEO Migration, Audit ID: MIGR-YYYYMMDD-NNN)
diff --git a/.claude/commands/seo-on-page.md b/.claude/commands/seo-on-page.md
index 39f9a90..7efedd7 100644
--- a/.claude/commands/seo-on-page.md
+++ b/.claude/commands/seo-on-page.md
@@ -20,11 +20,11 @@ On-page SEO analysis for meta tags, headings, content, and links.
 
 ```bash
 # Full page analysis
-python custom-skills/11-seo-on-page-audit/code/scripts/page_analyzer.py \
+python custom-skills/13-seo-on-page-audit/code/scripts/page_analyzer.py \
   --url https://example.com/page
 
 # Multiple pages
-python custom-skills/11-seo-on-page-audit/code/scripts/page_analyzer.py \
+python custom-skills/13-seo-on-page-audit/code/scripts/page_analyzer.py \
   --urls urls.txt --output report.json
 ```
 
diff --git a/.claude/commands/seo-position-tracking.md b/.claude/commands/seo-position-tracking.md
new file mode 100644
index 0000000..c4953e9
--- /dev/null
+++ b/.claude/commands/seo-position-tracking.md
@@ -0,0 +1,55 @@
+---
+description: Keyword rank monitoring with visibility scores and alerts
+---
+
+# SEO Position Tracking
+
+Monitor keyword rankings, detect position changes with threshold alerts, and calculate visibility scores.
+
+## Triggers
+- "rank tracking", "position monitoring", "순위 추적"
+
+## Capabilities
+
+1. **Position Tracking** - Retrieve current ranking positions for tracked keywords
+2. **Change Detection** - Detect position changes with configurable threshold alerts
+3. **Visibility Scoring** - Calculate visibility scores weighted by search volume
+4. **Brand/Non-Brand Segments** - Segment keywords into brand vs non-brand
+5. **Competitor Comparison** - Compare rank positions against competitors
+6. **Ranking Reports** - Period-over-period trend analysis with top movers
+
+## Scripts
+
+```bash
+# Get current positions
+python custom-skills/21-seo-position-tracking/code/scripts/position_tracker.py \
+  --target https://example.com --json
+
+# With change threshold alerts (flag moves of +-5 or more)
+python custom-skills/21-seo-position-tracking/code/scripts/position_tracker.py \
+  --target https://example.com --threshold 5 --json
+
+# Filter by brand segment
+python custom-skills/21-seo-position-tracking/code/scripts/position_tracker.py \
+  --target https://example.com --segment brand --json
+
+# Compare with competitor
+python custom-skills/21-seo-position-tracking/code/scripts/position_tracker.py \
+  --target https://example.com --competitor https://comp1.com --json
+
+# 30-day ranking report
+python custom-skills/21-seo-position-tracking/code/scripts/ranking_reporter.py \
+  --target https://example.com --period 30 --json
+
+# Quarterly report with competitor comparison
+python custom-skills/21-seo-position-tracking/code/scripts/ranking_reporter.py \
+  --target https://example.com --competitor https://comp1.com --period 90 --json
+```
+
+## Output
+- Position distribution (top 3/10/20/50/100)
+- Change summary (improved, declined, stable, new, lost)
+- Threshold alerts for significant position changes
+- Visibility score and trend over time
+- Brand vs non-brand segment breakdown
+- Reports saved to Notion SEO Audit Log (Category: Position Tracking, ID: RANK-YYYYMMDD-NNN)
diff --git a/.claude/commands/seo-reporting-dashboard.md b/.claude/commands/seo-reporting-dashboard.md
new file mode 100644
index 0000000..f6d628a
--- /dev/null
+++ b/.claude/commands/seo-reporting-dashboard.md
@@ -0,0 +1,59 @@
+---
+description: SEO reporting dashboard and executive reports
+---
+
+# SEO Reporting Dashboard
+
+Aggregate all SEO skill outputs into executive reports and interactive HTML dashboards.
+
+## Triggers
+- "SEO report", "SEO dashboard", "보고서"
+
+## Capabilities
+
+1. **Report Aggregation** - Collect and normalize outputs from skills 11-33 into unified structure
+2. **Cross-Skill Health Score** - Weighted scores across technical, on-page, performance, content, links, keywords
+3. **HTML Dashboard** - Self-contained Chart.js dashboard with gauge, line, bar, pie, and radar charts
+4. **Executive Report** - Korean-language summaries tailored to audience (C-level, marketing, technical)
+5. **Priority Issues** - Top issues ranked across all audit dimensions
+6. **Trend Analysis** - Period-over-period comparison narrative with audit timeline
+
+## Scripts
+
+```bash
+# Aggregate all skill outputs for a domain
+python custom-skills/34-seo-reporting-dashboard/code/scripts/report_aggregator.py \
+  --domain https://example.com --json
+
+# Aggregate with date range filter
+python custom-skills/34-seo-reporting-dashboard/code/scripts/report_aggregator.py \
+  --domain https://example.com --from 2025-01-01 --to 2025-03-31 --json
+
+# Generate HTML dashboard
+python custom-skills/34-seo-reporting-dashboard/code/scripts/dashboard_generator.py \
+  --report aggregated_report.json --output dashboard.html
+
+# C-level executive summary (Korean)
+python custom-skills/34-seo-reporting-dashboard/code/scripts/executive_report.py \
+  --report aggregated_report.json --audience c-level --output report.md
+
+# Marketing team report
+python custom-skills/34-seo-reporting-dashboard/code/scripts/executive_report.py \
+  --report aggregated_report.json --audience marketing --output report.md
+
+# Technical team report
+python custom-skills/34-seo-reporting-dashboard/code/scripts/executive_report.py \
+  --report aggregated_report.json --audience technical --output report.md
+```
+
+## Output
+- Aggregated JSON report with overall health score, category scores, top issues/wins
+- Self-contained HTML dashboard (responsive, no external dependencies except Chart.js CDN)
+- Korean executive summary in Markdown (tailored by audience level)
+- Saved to Notion SEO Audit Log (Category: SEO Dashboard, Audit ID: DASH-YYYYMMDD-NNN)
+
+## Workflow
+1. Run audits with individual skills (11-33)
+2. Aggregate with `report_aggregator.py`
+3. Generate dashboard and/or executive report
+4. Share HTML dashboard or Markdown report with stakeholders
diff --git a/.claude/commands/seo-schema-generator.md b/.claude/commands/seo-schema-generator.md
index 5ebc6d8..c85b719 100644
--- a/.claude/commands/seo-schema-generator.md
+++ b/.claude/commands/seo-schema-generator.md
@@ -19,11 +19,11 @@ Generate JSON-LD structured data markup from templates.
 
 ```bash
 # Generate from template
-python custom-skills/14-seo-schema-generator/code/scripts/schema_generator.py \
+python custom-skills/17-seo-schema-generator/code/scripts/schema_generator.py \
   --type LocalBusiness --output schema.json
 
 # With custom data
-python custom-skills/14-seo-schema-generator/code/scripts/schema_generator.py \
+python custom-skills/17-seo-schema-generator/code/scripts/schema_generator.py \
   --type Article \
   --data '{"headline": "My Article", "author": "John Doe"}' \
   --output article-schema.json
diff --git a/.claude/commands/seo-schema-validator.md b/.claude/commands/seo-schema-validator.md
index b9d217f..f251b65 100644
--- a/.claude/commands/seo-schema-validator.md
+++ b/.claude/commands/seo-schema-validator.md
@@ -20,15 +20,15 @@ JSON-LD structured data validation and analysis.
 
 ```bash
 # Validate page schema
-python custom-skills/13-seo-schema-validator/code/scripts/schema_validator.py \
+python custom-skills/16-seo-schema-validator/code/scripts/schema_validator.py \
   --url https://example.com
 
 # Validate local file
-python custom-skills/13-seo-schema-validator/code/scripts/schema_validator.py \
+python custom-skills/16-seo-schema-validator/code/scripts/schema_validator.py \
   --file schema.json
 
 # Batch validation
-python custom-skills/13-seo-schema-validator/code/scripts/schema_validator.py \
+python custom-skills/16-seo-schema-validator/code/scripts/schema_validator.py \
   --urls urls.txt --output validation_report.json
 ```
 
diff --git a/.claude/commands/seo-serp-analysis.md b/.claude/commands/seo-serp-analysis.md
new file mode 100644
index 0000000..fb9a0a7
--- /dev/null
+++ b/.claude/commands/seo-serp-analysis.md
@@ -0,0 +1,46 @@
+---
+description: Google and Naver SERP feature detection and competitor mapping
+---
+
+# SEO SERP Analysis
+
+Detect SERP features, map competitor positions, and score feature opportunities for Google and Naver.
+
+## Triggers
+- "SERP analysis", "SERP features", "검색 결과 분석"
+
+## Capabilities
+
+1. **Google SERP Feature Detection** - Featured snippet, PAA, knowledge panel, local pack, video carousel, ads, image pack, site links
+2. **Competitor Position Mapping** - Map competitor domains and positions per keyword
+3. **Content Type Distribution** - Analyze content types in results (blog, product, service, news, video)
+4. **Opportunity Scoring** - Score SERP feature opportunities for target site
+5. **Intent Validation** - Validate search intent from SERP composition
+6. **Naver SERP Analysis** - Section detection (블로그, 카페, 지식iN, 스마트스토어, 브랜드존, 숏폼, 인플루언서)
+
+## Scripts
+
+```bash
+# Google SERP analysis
+python custom-skills/20-seo-serp-analysis/code/scripts/serp_analyzer.py \
+  --keyword "치과 임플란트" --country kr --json
+
+# Multiple keywords from file
+python custom-skills/20-seo-serp-analysis/code/scripts/serp_analyzer.py \
+  --keywords-file keywords.txt --country kr --json
+
+# Naver SERP analysis
+python custom-skills/20-seo-serp-analysis/code/scripts/naver_serp_analyzer.py \
+  --keyword "치과 임플란트" --json
+
+# Naver multiple keywords
+python custom-skills/20-seo-serp-analysis/code/scripts/naver_serp_analyzer.py \
+  --keywords-file keywords.txt --json
+```
+
+## Output
+- SERP feature presence map with ad counts
+- Competitor positions with domain, URL, title, and content type
+- Opportunity score and intent signals
+- Naver section priority mapping and content type distribution
+- Reports saved to Notion SEO Audit Log (Category: SERP Analysis, ID: SERP-YYYYMMDD-NNN)
diff --git a/.claude/commands/seo-technical.md b/.claude/commands/seo-technical.md
index 2214803..6bb8568 100644
--- a/.claude/commands/seo-technical.md
+++ b/.claude/commands/seo-technical.md
@@ -19,15 +19,15 @@ Technical SEO audit for robots.txt and sitemap validation.
 
 ```bash
 # Check robots.txt
-python custom-skills/10-seo-technical-audit/code/scripts/robots_checker.py \
+python custom-skills/12-seo-technical-audit/code/scripts/robots_checker.py \
   --url https://example.com
 
 # Validate sitemap
-python custom-skills/10-seo-technical-audit/code/scripts/sitemap_validator.py \
+python custom-skills/12-seo-technical-audit/code/scripts/sitemap_validator.py \
   --url https://example.com/sitemap.xml
 
 # Crawl sitemap URLs
-python custom-skills/10-seo-technical-audit/code/scripts/sitemap_crawler.py \
+python custom-skills/12-seo-technical-audit/code/scripts/sitemap_crawler.py \
   --sitemap https://example.com/sitemap.xml --output report.json
 ```
 
diff --git a/.claude/commands/seo-vitals.md b/.claude/commands/seo-vitals.md
index 47b5a42..041c9b0 100644
--- a/.claude/commands/seo-vitals.md
+++ b/.claude/commands/seo-vitals.md
@@ -20,15 +20,15 @@ Google PageSpeed Insights and Core Web Vitals analysis.
 
 ```bash
 # Analyze single URL
-python custom-skills/15-seo-core-web-vitals/code/scripts/pagespeed_client.py \
+python custom-skills/14-seo-core-web-vitals/code/scripts/pagespeed_client.py \
   --url https://example.com
 
 # Mobile and desktop
-python custom-skills/15-seo-core-web-vitals/code/scripts/pagespeed_client.py \
+python custom-skills/14-seo-core-web-vitals/code/scripts/pagespeed_client.py \
   --url https://example.com --strategy both
 
 # Batch analysis
-python custom-skills/15-seo-core-web-vitals/code/scripts/pagespeed_client.py \
+python custom-skills/14-seo-core-web-vitals/code/scripts/pagespeed_client.py \
   --urls urls.txt --output vitals_report.json
 ```
 
diff --git a/.gitignore b/.gitignore
index 03059c2..7608df3 100644
--- a/.gitignore
+++ b/.gitignore
@@ -81,8 +81,9 @@ credentials.json
 secrets.json
 token.json
 
-# Claude Code local config
-.claude/
+# Claude Code local config (keep commands tracked for slash commands)
+.claude/*
+!.claude/commands/
 
 # Temporary files
 output/
diff --git a/CLAUDE.md b/CLAUDE.md
index 642ca3c..c16d335 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -112,17 +112,17 @@ This is a Claude Skills collection repository containing:
 
 | Command | Purpose |
 |---------|---------|
-| `/reference-curator-pipeline` | Full pipeline orchestration with QA loop handling |
+| `/reference-curator` | Full pipeline orchestration with QA loop handling |
 
 ```bash
 # Full pipeline from topic
-/reference-curator-pipeline "Claude Code best practices" --max-sources 5
+/reference-curator "Claude Code best practices" --max-sources 5
 
 # From URLs (skip discovery)
-/reference-curator-pipeline https://docs.anthropic.com/en/docs/prompt-caching
+/reference-curator https://docs.anthropic.com/en/docs/prompt-caching
 
 # With auto-approve and fine-tuning output
-/reference-curator-pipeline "MCP servers" --auto-approve --export-format fine_tuning
+/reference-curator "MCP servers" --auto-approve --export-format fine_tuning
 ```
 
 **Individual Sub-skills:**
@@ -130,7 +130,7 @@ This is a Claude Skills collection repository containing:
 | Skill | Command | Purpose |
 |-------|---------|---------|
 | reference-discovery | `/reference-discovery` | Search & validate authoritative sources |
-| web-crawler-orchestrator | `/web-crawler` | Multi-backend crawling (Firecrawl/Node/aiohttp/Scrapy) |
+| web-crawler | `/web-crawler` | Multi-backend crawling (Firecrawl/Node/aiohttp/Scrapy) |
 | content-repository | `/content-repository` | MySQL storage with version tracking |
 | content-distiller | `/content-distiller` | Summarization & key concept extraction |
 | quality-reviewer | `/quality-reviewer` | QA loop with approve/refactor/research routing |
diff --git a/custom-skills/90-reference-curator/commands/reference-curator-pipeline.md b/custom-skills/90-reference-curator/commands/reference-curator-pipeline.md
index 919e312..f7424e6 100644
--- a/custom-skills/90-reference-curator/commands/reference-curator-pipeline.md
+++ b/custom-skills/90-reference-curator/commands/reference-curator-pipeline.md
@@ -1,6 +1,6 @@
 ---
-description: Orchestrates full reference curation pipeline as background task. Runs discovery → crawl → store → distill → review → export with QA loop handling.
-argument-hint: <topic|urls|manifest> [--max-sources 10] [--max-pages 50] [--auto-approve] [--threshold 0.85] [--max-iterations 3] [--export-format project_files]
+description: Orchestrates full reference curation pipeline with configurable depth. Runs discovery > crawl > store > distill > review > export with QA loop handling.
+argument-hint: <topic|urls|manifest> [--depth light|standard|deep|full] [--output ~/Documents/reference-library/] [--max-sources 100] [--max-pages 50] [--auto-approve] [--threshold 0.85] [--max-iterations 3] [--export-format project_files]
 allowed-tools: WebSearch, WebFetch, Read, Write, Bash, Grep, Glob, Task
 ---
 
@@ -19,28 +19,191 @@ Full-stack orchestration of the 6-skill reference curation workflow.
 ## Arguments
 
 - `<input>`: Required. Topic string, URL(s), or manifest file path
-- `--max-sources`: Maximum sources to discover (topic mode, default: 10)
-- `--max-pages`: Maximum pages per source to crawl (default: 50)
+- `--depth`: Crawl depth level (default: `standard`). See Depth Levels below
+- `--output`: Output directory path (default: `~/Documents/reference-library/`)
+- `--max-sources`: Maximum sources to discover (topic mode, default: 100)
+- `--max-pages`: Maximum pages per source to crawl (default varies by depth)
 - `--auto-approve`: Auto-approve scores above threshold
 - `--threshold`: Approval threshold (default: 0.85)
 - `--max-iterations`: Max QA loop iterations per document (default: 3)
 - `--export-format`: Output format: `project_files`, `fine_tuning`, `jsonl` (default: project_files)
+- `--include-subdomains`: Include subdomains in site mapping (default: false)
+- `--follow-external`: Follow external links found in content (default: false)
+
+## Output Directory
+
+**IMPORTANT: Never store output in any claude-skills, `.claude/`, or skill-related directory.**
+
+The `--output` argument sets the base path for all pipeline output. If omitted, the default is `~/Documents/reference-library/`.
+
+### Directory Structure
+
+```
+{output}/
+├── {topic-slug}/                   # One folder per pipeline run
+│   ├── README.md                   # Index with table of contents
+│   ├── 00-page-name.md             # Individual page files
+│   ├── 01-page-name.md
+│   ├── ...
+│   ├── {topic-slug}-complete.md    # Combined bundle (all pages)
+│   └── manifest.json               # Crawl metadata
+├── pipeline_state/                 # Resume state (auto-managed)
+│   └── run_XXX/state.json
+└── exports/                        # Fine-tuning / JSONL exports
+```
+
+### Resolution Rules
+
+1. If `--output` is provided, use that path exactly
+2. If not provided, use `~/Documents/reference-library/`
+3. **Before writing any files**, check if the output directory exists
+4. If the directory does NOT exist, **ask the user for permission** before creating it:
+   - Show the full resolved path that will be created
+   - Wait for explicit user approval
+   - Only then run `mkdir -p <path>`
+5. The topic slug is derived from the input (URL domain+path or topic string)
+
+### Examples
+
+```bash
+# Uses default: ~/Documents/reference-library/glossary-for-wordpress/
+/reference-curator https://docs.codeat.co/glossary/
+
+# Custom path: /tmp/research/mcp-docs/
+/reference-curator "MCP servers" --output /tmp/research
+
+# Explicit home subfolder: ~/Projects/client-docs/api-reference/
+/reference-curator https://api.example.com/docs --output ~/Projects/client-docs
+```
+
+## Depth Levels
+
+### `--depth light`
+Fast scan for quick reference. Main content only, minimal crawling.
+
+| Parameter | Value |
+|-----------|-------|
+| `onlyMainContent` | `true` |
+| `formats` | `["markdown"]` |
+| `maxDiscoveryDepth` | 1 |
+| `max-pages` default | 20 |
+| Map limit | 50 |
+| `deduplicateSimilarURLs` | `true` |
+| Follow sub-links | No |
+| JS rendering wait | None |
+
+**Best for:** Quick lookups, single-page references, API docs you already know.
+
+### `--depth standard` (default)
+Balanced crawl. Main content with links for cross-referencing.
+
+| Parameter | Value |
+|-----------|-------|
+| `onlyMainContent` | `true` |
+| `formats` | `["markdown", "links"]` |
+| `maxDiscoveryDepth` | 2 |
+| `max-pages` default | 50 |
+| Map limit | 100 |
+| `deduplicateSimilarURLs` | `true` |
+| Follow sub-links | Same-domain only |
+| JS rendering wait | None |
+
+**Best for:** Documentation sites, plugin guides, knowledge bases.
+
+### `--depth deep`
+Thorough crawl. Full page content including sidebars, nav, and related pages.
+
+| Parameter | Value |
+|-----------|-------|
+| `onlyMainContent` | `false` |
+| `formats` | `["markdown", "links", "html"]` |
+| `maxDiscoveryDepth` | 3 |
+| `max-pages` default | 150 |
+| Map limit | 300 |
+| `deduplicateSimilarURLs` | `true` |
+| Follow sub-links | Same-domain + linked resources |
+| JS rendering wait | `waitFor: 3000` |
+| `includeSubdomains` | `true` |
+
+**Best for:** Complete product documentation, research material, sites with sidebars/code samples hidden behind tabs.
+
+### `--depth full`
+Exhaustive crawl. Everything captured including raw HTML, screenshots, and external references.
+
+| Parameter | Value |
+|-----------|-------|
+| `onlyMainContent` | `false` |
+| `formats` | `["markdown", "html", "rawHtml", "links"]` |
+| `maxDiscoveryDepth` | 5 |
+| `max-pages` default | 500 |
+| Map limit | 1000 |
+| `deduplicateSimilarURLs` | `false` |
+| Follow sub-links | All (same-domain + external references) |
+| JS rendering wait | `waitFor: 5000` |
+| `includeSubdomains` | `true` |
+| Screenshots | Capture for JS-heavy pages |
+
+**Best for:** Archival, migration references, preserving sites, training data collection.
+
+## Depth Comparison
+
+```
+light       ████░░░░░░░░░░░░  Speed: fastest   Pages: ~20    Content: main only
+standard    ████████░░░░░░░░  Speed: fast       Pages: ~50    Content: main + links
+deep        ████████████░░░░  Speed: moderate   Pages: ~150   Content: full page + HTML
+full        ████████████████  Speed: slow       Pages: ~500   Content: everything + raw
+```
 
 ## Pipeline Stages
 
 ```
 1. reference-discovery  (topic mode only)
-2. web-crawler-orchestrator
+2. web-crawler              <- depth controls this stage
 3. content-repository
-4. content-distiller    ◄────────┐
-5. quality-reviewer              │
-   ├── APPROVE → export          │
-   ├── REFACTOR ─────────────────┤
-   ├── DEEP_RESEARCH → crawler ──┘
-   └── REJECT → archive
+4. content-distiller    <--------+
+5. quality-reviewer              |
+   +-- APPROVE -> export         |
+   +-- REFACTOR -----------------+
+   +-- DEEP_RESEARCH -> crawler -+
+   +-- REJECT -> archive
 6. markdown-exporter
 ```
 
+## Crawl Execution by Depth
+
+When executing the crawl (Stage 2), apply the depth settings to the Firecrawl tools:
+
+### Site Mapping (`firecrawl_map`)
+```
+firecrawl_map:
+  url: <target>
+  limit: {depth.map_limit}
+  includeSubdomains: {depth.includeSubdomains}
+```
+
+### Page Scraping (`firecrawl_scrape`)
+```
+firecrawl_scrape:
+  url: <page>
+  formats: {depth.formats}
+  onlyMainContent: {depth.onlyMainContent}
+  waitFor: {depth.waitFor}           # deep/full only
+  excludeTags: ["nav", "footer"]     # light/standard only
+```
+
+### Batch Crawling (`firecrawl_crawl`) - for deep/full only
+```
+firecrawl_crawl:
+  url: <target>
+  maxDiscoveryDepth: {depth.maxDiscoveryDepth}
+  limit: {depth.max_pages}
+  deduplicateSimilarURLs: {depth.dedup}
+  scrapeOptions:
+    formats: {depth.formats}
+    onlyMainContent: {depth.onlyMainContent}
+    waitFor: {depth.waitFor}
+```
+
 ## QA Loop Handling
 
 | Decision | Action | Max Iterations |
@@ -54,17 +217,23 @@ After max iterations, document marked as `needs_manual_review`.
 ## Example Usage
 
 ```
-# Full pipeline from topic
-/reference-curator-pipeline "Claude Code best practices" --max-sources 5
+# Quick scan of a single doc page
+/reference-curator https://docs.example.com/api --depth light
 
-# Pipeline from specific URLs (skip discovery)
-/reference-curator-pipeline https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching
+# Standard documentation crawl (default)
+/reference-curator "Glossary for WordPress" --max-sources 5
+
+# Deep crawl capturing full page content and HTML
+/reference-curator https://docs.codeat.co/glossary/ --depth deep
+
+# Full archival crawl with all formats
+/reference-curator https://docs.anthropic.com --depth full --max-pages 300
+
+# Deep crawl with auto-approval and fine-tuning export
+/reference-curator "MCP servers" --depth deep --auto-approve --export-format fine_tuning
 
 # Resume from existing manifest
-/reference-curator-pipeline ./manifest.json --auto-approve
-
-# Fine-tuning dataset output
-/reference-curator-pipeline "MCP servers" --export-format fine_tuning --auto-approve
+/reference-curator ./manifest.json --auto-approve
 ```
 
 ## State Management
@@ -78,7 +247,7 @@ SELECT * FROM pipeline_runs WHERE run_id = 123;
 
 **File-based fallback:**
 ```
-~/reference-library/pipeline_state/run_XXX/state.json
+~/Documents/reference-library/pipeline_state/run_XXX/state.json
 ```
 
 ## Output
@@ -89,6 +258,7 @@ Pipeline returns summary on completion:
 {
   "run_id": 123,
   "status": "completed",
+  "depth": "standard",
   "stats": {
     "sources_discovered": 5,
     "pages_crawled": 45,
@@ -101,7 +271,7 @@ Pipeline returns summary on completion:
   },
   "exports": {
     "format": "project_files",
-    "path": "~/reference-library/exports/"
+    "path": "~/Documents/reference-library/exports/"
   }
 }
 ```