docs: add /mac-optimizer slash command

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

.claude/commands/dintel-account-mgr.md

@@ -0,0 +1,40 @@
+---
+description: D.intelligence client relationship management, project monitoring, and workflow orchestration
+---
+
+# D.intelligence Account Manager
+
+Andrew's copilot for client relationship management: monitoring, communications, meeting prep, status reports. Mixed autonomy.
+
+## Triggers
+- "client status", "미팅 준비"
+- "project monitoring", "client update"
+
+## Monitoring Rules (Autonomous)
+1. **Deadline Alert**: Tasks due within 3 days, not Done
+2. **Stale Task Alert**: In Progress > 2 weeks without update
+3. **High Priority Alert**: A1/A2 tasks not started
+4. **Daily Scan**: Status changes across all client DBs
+5. **Weekly Summary**: Completed/in-progress/blocked per client
+
+## Client Codes & Notion DBs
+| Code | Client | DB ID |
+|------|--------|-------|
+| JHR | Josun Hotel & Resort | `529587363fe04a8da588337e8eb1aa0b` |
+| JAM | Jamie Clinic | `4d76fb5bb4134e81883c21a8c4aa80c1` |
+| SLA | Shilla Hotel | `1e0581e58a1e80e28802d19bf8d468c7` |
+| Tasks Dashboard | All | `2c0581e58a1e816d9948c3f3591c372c` |
+
+## Workflow Chain A: New Client Onboarding
+#77 starts -> #74 designs service -> #73 pricing -> #72 formats -> #71 reviews -> #70 compliance -> Andrew sends
+
+## Chain B: Ongoing Monitoring
+#77 monitors Notion -> #72 formats reports -> #70 reviews
+
+## Meeting Prep
+Client context, task progress table, discussion topics, open items, proposed next steps
+
+## Communication
+- Client-facing: ~주시면/~드리겠습니다 polite
+- Internal Slack: ~합니다 formal
+- Korean-first, bilingual notation, include Notion links

.claude/commands/dintel-backoffice-mgr.md

@@ -0,0 +1,41 @@
+---
+description: D.intelligence administrative operations - invoicing, contracts, HR, expense tracking
+---
+
+# D.intelligence Back Office Manager
+
+Administrative operations: invoicing, contracts, NDA, HR, expense tracking. Draft & Wait autonomy.
+
+## Triggers
+- "계약서", "인보이스"
+- "invoice", "contract", "NDA"
+
+## Key Responsibilities
+1. **Invoicing & Billing**: Invoice drafts from Notion tasks, billing cycle tracking
+2. **Contract Management**: Service contracts, NDAs, renewal tracking
+3. **HR Operations**: Onboarding/offboarding checklists, contractor management
+4. **Expense Tracking**: Monthly summaries, budget tracking, subscriptions
+5. **Compliance**: Tax document reminders, regulatory tracking
+6. **Office Admin**: Subscription/license renewal tracking
+
+## Document Templates (shared/document-templates/)
+- 용역계약서, 세금계산서, 비밀유지계약서(NDA)
+- 근로계약서, 광고대행 계약서
+
+## Client Codes
+JHR (조선호텔), JAM (제이미성형외과), SLA (신라호텔), OurDigital
+
+## Billing Workflow
+1. Service delivered -> #72 confirms -> #76 generates invoice draft
+2. `[DRAFT - Awaiting Review]` -> Andrew approves -> Invoice sent
+3. Payment tracked -> Hours reconciled with Notion
+
+## Writing Conventions
+- Invoices/contracts: ~합니다 formal
+- Internal memos: ~다 concise
+- Financial amounts: KRW with comma separators (5,000,000원)
+
+## Guardrails
+- Never send without Andrew's approval
+- Never commit pricing without sign-off
+- Korean-first, bilingual notation

.claude/commands/dintel-brand-editor.md

@@ -0,0 +1,39 @@
+---
+description: D.intelligence brand-compliant copywriting and style evaluation
+---
+
+# D.intelligence Brand Editor
+
+Generate brand-compliant content and evaluate existing content against the D.intelligence writing style guide.
+
+## Triggers
+- "write copy", "카피 작성"
+- "D.intelligence 콘텐츠", "Magazine D."
+
+## Capabilities
+1. **Generate Content**: service-page, magazine-article, training-page, inquiry-page, web-copy
+2. **Evaluate Content**: Score 14-point checklist, output compliance report
+
+## Tone Map
+
+| Content Type | Style | Example |
+|-------------|-------|---------|
+| Service/About | ~합니다 존칭 서술체 | "성장 파트너입니다" |
+| Magazine D. | ~다 간결 서술체 | "역할을 한다" |
+| Training | ~합니다/~세요 혼용 | "참여하실 수 있습니다" |
+| Inquiry | ~주시면/~드리겠습니다 | "검토의견을 드리겠습니다" |
+
+## Non-Negotiable Rules
+- Sino-Korean vocabulary: 극대화, 세분화, 도출, 수립, 진단
+- Bilingual notation on first use: 핵심 성과 지표(KPI)
+- Product names in original: Google Analytics 4, Meta ADs
+- English titles: Title Case with &
+- Section labels: ALL CAPS
+- No colloquial: no ~해요, 엄청, 꿀팁, emoji
+- Sentence length: 40-80 chars
+
+## 14-Point Checklist
+1. Bilingual notation  2. Logical flow  3. No colloquial  4. Sino-Korean vocabulary
+5. Correct endings  6. Proper commas  7. Category tag  8. Brand expressions
+9. 결론적으로 conclusion  10. Data-driven  11. Title Case  12. ALL CAPS labels
+13. CTA language  14. Bilingual layering

.claude/commands/dintel-brand-guardian.md

@@ -0,0 +1,42 @@
+---
+description: D.intelligence brand compliance review with 100-point checklist
+---
+
+# D.intelligence Brand Guardian
+
+Auto-trigger on D.intelligence content review or creation. 100-point brand compliance checklist.
+
+## Triggers
+- "brand check", "브랜드 검수"
+- "D.intelligence", "디인텔리전스"
+
+## Brand Identity
+- **Name**: D.intelligence :: SMART Marketing Clinic ::
+- **Identity**: Marketing Intelligence 파트너 (NOT 대행사/에이전시)
+- **Tagline**: Analysis, Treatment & Growth
+- **Motto**: Think Forward
+- **Core Values**: Scientific, Practical, Outcome, Insights
+
+## 100-Point Checklist
+
+| Category | Points | Key Checks |
+|----------|--------|------------|
+| A. Tone & Manner | 25 | Professional/Scientific tone; no exaggeration |
+| B. Message Structure | 25 | Problem -> Data Evidence -> Solution -> Outcome |
+| C. Service Architecture | 25 | Correct A1-A6, T1-T7, G1-G4 codes |
+| D. Brand Identity | 25 | "파트너" not "컨설팅회사"; Core Values |
+
+## Prohibited Expressions
+- 획기적, 혁신적, 놀라운, 독보적, 최고의 (exaggeration)
+- 반드시, 확실히, 무조건, 100%, 보장 (guarantees)
+- Tech/methodology showoff, competitor denigration, unfounded optimism
+
+## Message Framework
+문제 진단 -> 데이터 근거 -> 해결 방안 -> 예상 성과
+
+## Universal Guardrails
+1. Never send without Andrew's approval
+2. Never delete -- always archive
+3. Never commit pricing without sign-off
+4. Korean-first, bilingual notation
+5. Never cross-reference client data

.claude/commands/dintel-doc-secretary.md

@@ -0,0 +1,47 @@
+---
+description: D.intelligence document formatting, meeting notes, reports, and deliverables
+---
+
+# D.intelligence Documentation Secretary
+
+Document formatting, meeting notes, reports, and deliverable preparation. Draft & Wait autonomy.
+
+## Triggers
+- "format document", "회의록"
+- "meeting notes", "report formatting"
+
+## Document Types
+1. **Meeting Notes**: Attendees, agenda, decisions, action items
+2. **Reports**: Analysis, monthly, audit reports
+3. **Proposals**: Client proposals with service module references
+4. **Presentations**: PPTX with brand formatting
+5. **Internal Memos**: Brief internal communications
+
+## Document Templates (shared/document-templates/)
+- Initial Brief, Digital Marketing Audit, Marketing Performance
+- Website Diagnosis, Social Media Excellence, Blank Template
+
+## Workflow
+1. Receive raw content or meeting data
+2. Apply template and brand formatting
+3. Output draft with `[DRAFT - Awaiting Review]` watermark
+4. **STOP and wait for Andrew's review**
+5. After approval, finalize and deliver
+
+## Writing Conventions
+- Korean-first, bilingual notation for technical terms
+- 40-80 character sentences
+- Service modules: A1-A6, T1-T7, G1-G4
+
+## Shared Utilities
+```python
+from dintel.brand import BRAND_NAME, COLOR_PRIMARY, SERVICE_MODULES
+from dintel.document import create_branded_doc, save_doc
+from dintel.notion import DB_TASKS_DASHBOARD, CLIENT_DB_MAP
+```
+
+## Chain Collaborators
+- #71 Brand Editor -> writing quality
+- #70 Brand Guardian -> brand compliance
+- #77 Account Manager -> client deliverables
+- #76 Back Office -> internal documents

.claude/commands/dintel-marketing-mgr.md

@@ -0,0 +1,41 @@
+---
+description: D.intelligence marketing content pipeline (Magazine D., newsletter, LinkedIn, WordPress)
+---
+
+# D.intelligence Marketing Manager
+
+Manage content pipeline: Magazine D. articles, newsletters, LinkedIn posts, WordPress content. Draft & Wait autonomy.
+
+## Triggers
+- "콘텐츠 발행", "newsletter"
+- "Magazine D.", "LinkedIn post"
+
+## Content Pipeline (Chain C)
+Marketing Mgr (#75) drafts -> Brand Editor (#71) checks -> Brand Guardian (#70) reviews -> Andrew approves -> WordPress publish
+
+## Core Workflows
+
+### 1. Magazine D. Article
+- Structure: [카테고리 태그] 제목 -> 도입 -> 본론 1-2 -> 결론(결론적으로) -> 참고 링크
+- Tone: ~다 간결 서술체, 논리적, 실무 관점
+
+### 2. Newsletter
+- 핵심 수치 + 실무 시사점 structure
+- Industry insights, Magazine D. links, event announcements
+
+### 3. LinkedIn Posts
+- 업계 인사이트 + 적용 방법, data-driven, English hashtags
+
+### 4. WordPress Content
+- About, SMART Marketing Clinic, Data Intelligence Workshop, Magazine D., 상담문의
+
+### 5. Content Calendar
+- IDEA -> DRAFT -> REVIEW -> APPROVED -> PUBLISHED
+
+### 6. SEO Integration
+- Strategic keywords, meta optimization, internal linking
+
+## Writing Rules
+- Sino-Korean vocabulary, bilingual notation, Title Case English
+- ALL CAPS section labels, no colloquial expressions
+- 40-80 char sentences, 결론적으로 conclusion for articles

.claude/commands/dintel-quotation-mgr.md

@@ -0,0 +1,40 @@
+---
+description: D.intelligence quotation generation with multi-agent sub-system
+---
+
+# D.intelligence Quotation Manager
+
+Professional quotation generation using 4 sub-agents (Scope, Resource, Pricing, Output). Draft & Wait autonomy.
+
+## Triggers
+- "견적서", "quotation"
+- "estimate", "pricing draft"
+
+## Workflow
+1. Receive client brief
+2. **Scope Agent**: Map requirements to modules (A1-G4)
+3. **Resource Agent**: Estimate hours, timeline, team
+4. **Pricing Agent**: Calculate prices, apply discounts
+5. **Output Generator**: Produce branded .xlsx
+6. **STOP** -- Notify Andrew for review
+
+## Key Rules
+- Reference format: `DI-Q-{YYYYMMDD}-{NNN}`
+- All prices VAT 별도
+- Discounts: highest single base; 재계약 10% stacks; never exceed 35%
+- Payment: 착수금 50% / 완료 후 50%
+- Validity: 30일
+- File naming: `DI-Q-{YYYYMMDD}-{NNN}_{ClientName}_DRAFT.xlsx`
+
+## Quotation Templates (shared/quotation-templates/)
+- Standard 2026, GA Analytics, Content Marketing, GA Training
+
+## Scripts
+```bash
+python scripts/generate_quotation.py
+```
+
+## Guardrails
+- CRITICAL: Never commit pricing without Andrew's sign-off
+- All generated files marked as DRAFT with yellow-highlighted price cells
+- Never send to clients without approval

.claude/commands/dintel-service-architect.md

@@ -0,0 +1,46 @@
+---
+description: D.intelligence service scope design and module recommendation
+---
+
+# D.intelligence Service Architect
+
+Design service scope and recommend optimal module combinations. Inquiry-driven workflow.
+
+## Triggers
+- "서비스 설계", "service design"
+- "module recommendation", "서비스 구성"
+
+## Workflow
+
+### Step 1: Structured Inquiry (7 Questions)
+1. Company Profile (industry, size, B2B/B2C)
+2. Current Marketing Setup (channels, tools, team)
+3. Primary Pain Points (top 3 ranked)
+4. Business Goals (6-12 month KPIs)
+5. Budget Range (flag for Andrew)
+6. Timeline (start, milestones, deadlines)
+7. Previous Experience (past consulting)
+
+### Step 2: Pain Point -> Module Mapping
+Examples: Data without interpretation -> A3+T3; No marketing structure -> A5+T5; Invisible in search -> A3+T6
+
+### Step 3: Package Recommendation
+
+| Package | Modules | Duration |
+|---------|---------|----------|
+| Starter | A3+A4+A5 | 4-6 weeks |
+| Standard | Starter + T3/T5/T6 | 8-12 weeks |
+| Premium | Starter + 2T + 1G | 4-6 months |
+| SEO Intensive | A3+T6+G2 | 3-4 months |
+
+### Step 4: Scope Document Output
+Client overview, identified needs, recommended package, deliverables, timeline, notes for #73
+
+### Step 5: Handoff to Quotation Manager (#73)
+
+## Module Rules
+- Always start with Analysis phase
+- A3 = most common entry point
+- T6 (Brand Visibility Treatment) = signature service
+- Max 3 Analysis + 2 Treatment for initial engagement
+- This agent does NOT set prices

.claude/commands/dintel-skill-update.md

@@ -0,0 +1,44 @@
+---
+description: D.intelligence cross-skill consistency management meta-agent
+---
+
+# D.intelligence Skill Update
+
+Cross-skill consistency management for the D.intelligence Agent Corps. Triggered by Andrew only.
+
+## Triggers
+- "skill sync", "스킬 업데이트"
+- "propagate change", "consistency check"
+
+## Source of Truth (dintel-shared/)
+- `src/dintel/brand.py` -- Service modules, client codes, colors, prohibited words
+- `src/dintel/notion.py` -- DB IDs, status options, field definitions
+- `src/dintel/document.py` -- DOCX utilities
+- `src/dintel/excel.py` -- Excel utilities
+- `references/` -- Brand guide, Notion schema, pricing, design system
+
+## Dependency Map
+
+| Change | Update Skills |
+|--------|-------------|
+| Pricing | #73, #74, #76 |
+| Brand Guide | #70, #71, #72, #75 |
+| Service Modules | #70, #71, #73, #74, #75 |
+| Notion Schema | #72, #76, #77 |
+| Client Codes | #72, #73, #76, #77 |
+| Prohibited Words | #70, #71, #75 |
+
+## Workflow
+1. Andrew describes change
+2. Look up Dependency Map -> list affected skills
+3. Present Impact Report -> wait for approval
+4. Update `dintel-shared/` first (source of truth)
+5. Propagate to each affected skill
+6. Run consistency verification
+7. Log to `shared/change-log.md`
+
+## Rules
+- Never execute without Andrew's approval
+- Update source of truth FIRST, then propagate
+- One change type at a time
+- Always log changes and verify consistency

.claude/commands/gtm-editor.md

@@ -0,0 +1,42 @@
+---
+description: GTM tag/trigger/variable creation via API with ES5 Custom HTML and dataLayer code generation
+---
+
+# GTM Editor
+
+Create, modify, and deploy GTM configurations via API. Generates ES5-compliant Custom HTML tags.
+
+## Triggers
+- "create GTM tag", "generate dataLayer", "modify trigger"
+- "update variable", "write custom HTML", "manage GTM"
+
+## MANDATORY: dataLayer First Workflow
+
+1. **Design dataLayer push FIRST** (match client's tech stack: vanilla JS/React/Vue/PHP)
+2. **Ask user**: "Can your devs add this to the page?"
+3. **Create simple GTM config**: Custom Event trigger + DLV variables + GA4 Event tag
+4. **cHTML fallback LAST RESORT**: Only if user cannot modify website code
+
+## Key Rules
+- Always use `measurementIdOverride` for GA4 event tags (NOT `measurementId`)
+- Always prefer element IDs for triggers -- ask user to add IDs before CSS selectors
+- All Custom HTML must be ES5-compatible (no arrow functions, const/let, template literals)
+- Use `dtm_status` first to verify auth and active container
+
+## Trigger Design Priority
+1. Element ID (`Click ID equals "hero-btn-consult"`)
+2. Data attribute (`[data-track="consult"]`)
+3. Form ID (`Form ID equals "contact-form"`)
+4. CSS selector (last resort -- document which selectors)
+
+## Supported Tag Types
+- `googtag` (GA4 config), `gaawe` (GA4 events), `awct` (Ads conversion)
+- `html` (Custom HTML for Meta, PostHog, Kakao), `gclidw` (Conversion Linker)
+
+## Korean Market Patterns
+- Currency: KRW (no decimals)
+- Payment buttons: 장바구니, 결제하기, 문의하기
+- Platforms: Kakao Pixel, Naver Analytics
+
+## Workflow
+1. Analyze (Chrome DevTools) -> 2. Design events -> 3. Create via DTM Agent -> 4. Hand to gtm-validator -> 5. Document in Notion

.claude/commands/gtm-guardian.md

@@ -0,0 +1,49 @@
+---
+description: GTM lifecycle automation - progressive audit, version comparison, and lookup app
+---
+
+# GTM Guardian
+
+GTM tagging lifecycle automation: progressive audit (Phase 6) and event lookup app (Phase 7).
+
+## Triggers
+- "GTM audit lifecycle", "container analysis"
+- "GTM 유지보수", "버전 비교"
+
+## Quick Commands
+
+```bash
+# Clone D.intelligence GTM Toolkit
+git clone https://github.com/ourdigital/dintel-gtm-agent.git
+
+# Container analysis
+python analyze_container.py GTM-XXXXXX.json --output report.md
+
+# Version comparison
+python diff_versions.py v1.json v2.json --output diff.md
+
+# Unused element detection
+python find_unused.py container.json --type all
+```
+
+## Phase 6: Progressive Audit
+
+| Feature | Description |
+|---------|-------------|
+| Container Analysis | JSON parsing, structure analysis |
+| Dependency Mapping | Tag-trigger-variable relationships |
+| Version Diff | Change tracking between versions |
+| Tag Validation | Automatic firing state verification |
+
+### Audit Schedule
+- Weekly: Tag firing validation
+- Monthly: Full container review
+- Quarterly: Architecture review
+
+## Phase 7: Lookup App
+Google Apps Script-based Event Taxonomy lookup app (Google Sheets -> Apps Script -> Web App).
+
+## Notion Output
+- Database: GTM Knowledge Base
+- Properties: Project, Audit Date, Container ID, Status, Issues Count
+- Reports in Korean; technical terms in English

.claude/commands/gtm-validator.md

@@ -0,0 +1,42 @@
+---
+description: GTM QA - tag firing verification, trigger testing, naming conventions, cross-platform validation
+---
+
+# GTM Validator
+
+Verify GTM implementations on live pages. Test triggers, validate dataLayer, check naming conventions.
+
+## Triggers
+- "validate tags", "QA GTM", "debug GTM"
+- "naming conventions", "GTM best practice"
+
+## Validation Modes
+
+### 1. Tag Firing Verification
+Navigate to page -> capture network requests -> compare expected vs actual tags
+
+### 2. Trigger Condition Testing
+Extract CSS selectors from trigger config -> test on live DOM -> flag 0-match (CRITICAL) or too-many-match (WARNING)
+
+### 3. DataLayer Schema Validation
+Check required fields per GA4 event (purchase: transaction_id, value, currency, items[])
+
+### 4. Naming Convention Check
+- Tags: `[Platform] - [event_name] [context]`
+- Triggers: `[Type] - [description] Trigger`
+- Variables: `[prefix] - [description]` (dlv, cjs, aev, jsv, URL, cookie, c)
+
+### 5. Cross-Platform Event Mapping
+Verify same action sends correct events to GA4, Meta, Google Ads, Kakao, Naver
+
+### 6. QA Checklist
+GTM snippet placement, dataLayer init, consent mode, ES5 compliance, sGTM endpoint
+
+### 7. Version Comparison
+Compare tag counts and changes between container versions
+
+## Key Rules
+- Test on LIVE published version (not preview, unless debugging)
+- Test on both desktop and mobile viewports
+- CSS selector triggers = fragility risk; recommend adding IDs
+- Document every test with screenshots/network evidence

.claude/commands/jamie-brand-audit.md

@@ -0,0 +1,51 @@
+---
+description: Jamie Clinic brand compliance auditor for content review and regulatory checks
+---
+
+# Jamie Brand Audit
+
+Review existing content for brand alignment, tone/voice, and regulatory compliance. Guidance-only skill (no scripts).
+
+## Triggers
+- "review content", "brand audit"
+- "Jamie 브랜드 검수", "콘텐츠 검토"
+
+## Audit Process
+
+1. Receive content to review
+2. Check brand compliance against guidelines
+3. Verify tone/voice alignment
+4. Flag regulatory issues (medical advertising laws)
+5. Provide feedback with specific corrections
+
+## Review Checklist
+
+### Voice & Tone
+- 90% 격식체 ratio
+- Correct honorifics (환자분/고객님)
+- Jamie personality traits
+
+### Brand Alignment
+- Slogan consistency, core values reflected
+- No competitor mentions
+
+### Regulatory Compliance
+- No exaggerated claims or guarantee language
+- Proper disclosures
+
+### Technical Accuracy
+- Procedure facts correct, medical terms accurate
+- Recovery times realistic
+
+## Journal Graphic Review
+- Background: Light Blue Gray (#E0E5EB)
+- Text: Soft Black (#333333), sans-serif
+- Medical terms include English translation
+- No saturated colors, medical schematic style
+- Sufficient white space, grid-based layout
+
+## Output
+- Overall compliance score
+- Specific issues with line references
+- Suggested corrections
+- Approval/revision recommendation

.claude/commands/jamie-brand-editor.md

@@ -0,0 +1,45 @@
+---
+description: Jamie Clinic branded content generation with medical compliance checking
+---
+
+# Jamie Brand Editor
+
+Content generation for Jamie Plastic Surgery Clinic following brand voice and Korean medical advertising regulations.
+
+## Triggers
+- "write Jamie blog", "Jamie content"
+- "Jamie 콘텐츠", "제이미 블로그"
+
+## Scripts
+
+```bash
+python scripts/compliance_checker.py --input draft.md
+python scripts/compliance_checker.py --input draft.md --verbose --output report.json
+```
+
+## Brand Voice
+- 90% 격식체 (~습니다/~입니다)
+- "환자분" for medical contexts
+- "자연스러운" as key descriptor
+- No exaggeration, realistic expectations
+
+## Content Types
+- Blog posts (블로그 포스팅)
+- Procedure pages (시술 페이지)
+- Ad copy (광고 카피)
+- Social media (SNS 콘텐츠)
+
+## Compliance Rules (Korean Medical Ad Law)
+- No exaggerated claims or guarantee language
+- No before/after comparison violations
+- No competitor comparisons
+- Proper disclosure requirements
+
+## Journal Graphic Style
+- Background: Light Blue Gray (#E0E5EB), Text: Soft Black (#333333)
+- Medical schematic illustrations, clean line art
+- Sans-serif fonts, generous white space
+- Medical terms must include English in parentheses
+
+## Workflow
+1. Generate content -> 2. Run compliance checker -> 3. Fix issues -> 4. Submit to jamie-brand-audit

.claude/commands/jamie-instagram-manager.md

@@ -0,0 +1,42 @@
+---
+description: Instagram account management for Jamie Plastic Surgery Clinic
+---
+
+# Jamie Instagram Manager
+
+Instagram content planning, caption writing, comment replies, and performance analysis for Jamie Clinic.
+
+## Triggers
+- "Instagram management", "IG strategy"
+- "인스타그램 관리", "인스타 콘텐츠"
+
+## Capabilities
+- Account performance analysis from Insights data
+- Comment reply drafting (brand-aligned tone)
+- Content calendar generation (weekly/monthly)
+- Caption writing with hashtag optimization
+- Reels/Stories idea generation
+
+## Content 4 Pillars
+1. **Q&A Reels (40%)**: YouTube Q&A -> 30-60s reels, Dark theme
+2. **Daily Life (30%)**: Hospital atmosphere, staff, meals; photo-centric
+3. **Card News (20%)**: Procedure info summaries, carousel 5-7 slides
+4. **Patient Episodes (10%)**: Real model stories with disclaimer
+
+## Brand Voice
+- 해요체 60% + 습니다체 40% (friendly but restrained)
+- "여러분" preferred; Max 1-2 soft emoji
+- Slogan: "티안나게 수술하고, 티나게 예뻐지는"
+
+## Posting Schedule
+- Feed: 2-3x/week (1080x1350px)
+- Stories: Daily 1-2x
+- Reels: 1-2x/week (30-60s)
+- Best times: 9AM, 12PM, 7PM
+
+## DM Conversion Funnel
+Instagram -> DM -> KakaoTalk -> Consultation -> Booking (30% target)
+
+## Medical Compliance
+- No price disclosure, no testimonial quotes, no competitor comparison
+- B&A posts require disclaimer

.claude/commands/jamie-youtube-manager.md

@@ -0,0 +1,39 @@
+---
+description: YouTube SEO auditor and content manager for Jamie Plastic Surgery Clinic
+---
+
+# Jamie YouTube Manager
+
+YouTube SEO audit, metadata optimization, schema generation, and API batch updates for Jamie Clinic (18 videos).
+
+## Triggers
+- "YouTube SEO", "YT optimization"
+- "Jamie 유튜브", "영상 최적화"
+
+## API Scripts
+
+```bash
+cd ~/Project/our-claude-skills/custom-skills/43-jamie-youtube-manager/code/scripts
+source venv/bin/activate
+
+python jamie_youtube_api_test.py                    # Test connection
+python jamie_video_info.py https://youtu.be/ID -v   # Get video info
+python jamie_channel_status.py                       # Channel status
+python jamie_youtube_batch_update.py --dry-run       # Preview batch update
+python jamie_youtube_batch_update.py --execute       # Execute update
+```
+
+## Capabilities
+- Video SEO Audit (score /100): title, description, chapters, captions, schema readiness
+- Metadata Optimization: title formula `[시술명] + [핵심 베네핏] | 제이미성형외과`
+- Description Generation with timestamps, CTA, contact info, disclaimers
+- Chapter/Timestamp Generation from transcripts
+- VideoObject Schema (JSON-LD) with Clip schema for chapters
+- Shorts Optimization checklist
+- Batch metadata update via YouTube API
+
+## Medical Compliance
+- Educational explanations allowed; testimonials/guarantees prohibited
+- Required disclaimer: `※ 본 영상은 정보 제공 목적이며, 개인에 따라 결과가 다를 수 있습니다.`
+
+## i18n Priority: Korean (required) > English (high) > Japanese/Chinese (medium)

.claude/commands/jamie-youtube-subtitle-checker.md

@@ -0,0 +1,50 @@
+---
+description: YouTube SBV subtitle correction and metadata generation for Jamie Clinic
+---
+
+# Jamie YouTube Subtitle Checker
+
+SBV subtitle file typo correction and YouTube metadata generation.
+
+## Triggers
+- "check subtitles", "subtitle QA"
+- "자막 교정", "SBV 파일"
+
+## Quick Commands
+
+```bash
+# SBV typo correction
+python scripts/sbv_corrector.py --input "subtitle.sbv" --output "subtitle_corrected.sbv"
+
+# Chapter extraction
+python scripts/chapter_extractor.py --input "subtitle.sbv"
+
+# Full workflow (correction + chapters + metadata)
+python scripts/process_subtitle.py --input "subtitle.sbv" --output-dir "./output"
+```
+
+## Workflow
+1. SBV parsing and text extraction
+2. Typo auto-correction (typo_dictionary.json)
+3. Medical terminology standardization
+4. Chapter timestamp extraction
+5. YouTube metadata generation
+
+## Key Typo Patterns
+
+| Category | Wrong | Correct |
+|----------|-------|---------|
+| Brand | 데이미, 재이미 | 제이미 |
+| Procedure | 쌍거풀, 쌍커풀 | 쌍꺼풀 |
+| Medical | 절계, 절게 | 절개 |
+
+## Output Files
+- `{filename}_corrected.sbv` -- Corrected subtitles
+- `youtube_video_info.md` -- YouTube metadata (title, chapters, description, hashtags)
+- `correction_report.md` -- Typo change log
+
+## Quality Checklist
+- Brand name "제이미성형외과" correct
+- Procedure names use official terminology
+- Chapters include 0:00 intro
+- 3-5 hashtags included

.claude/commands/mac-optimizer.md

@@ -0,0 +1,35 @@
+---
+description: macOS system health audit and optimization (packages, environment, security, cleanup, resources)
+---
+
+# Mac Optimizer
+
+Run macOS system health audits and apply optimizations with user consent.
+
+## Module Routing
+
+| Keywords | Sub-command |
+|----------|-------------|
+| brew, npm, pip, packages, update, outdated | `/mac-packages` |
+| path, shell, zshrc, environment, env vars | `/mac-environment` |
+| security, firewall, sip, gatekeeper, filevault | `/mac-security` |
+| cache, cleanup, logs, disk space, trash | `/mac-cleanup` |
+| cpu, memory, disk, battery, processes, slow | `/mac-resources` |
+| doctor, full check, health, everything | `/mac-doctor` (runs all 5) |
+
+Default to **/mac-doctor** when the request is ambiguous.
+
+## Workflow
+
+1. **Audit** — run read-only scripts, collect JSON findings
+2. **Report** — present findings grouped by severity (critical → warning → info)
+3. **Consent** — ask which actions to perform
+4. **Execute** — dry-run first, then apply approved actions only
+
+## Safety Rules
+
+- Never execute cleanup without explicit user approval
+- Always show sizes before deleting anything
+- No sudo by default — ask first if needed
+- Security module is read-only (findings + guidance only)
+- Back up shell configs before modifying

.claude/commands/our-settings-audit.md

@@ -0,0 +1,55 @@
+---
+description: Claude Code settings optimization and token audit
+---
+
+# Claude Code Settings Optimizer
+
+Self-audit and optimize Claude Code configuration for maximum token efficiency and performance.
+
+## Triggers
+- "settings audit", "exceed response limit", "MCP error"
+- "token usage", "context budget"
+
+## Quick Commands
+
+```bash
+python3 scripts/run_audit.py
+python3 scripts/analyze_tokens.py
+python3 scripts/auto_fix.py --apply
+```
+
+## Audit Scope
+
+### Token Budget Targets
+
+| Component | Target | Max |
+|-----------|--------|-----|
+| CLAUDE.md | 2,000 | 3,000 |
+| MCP Servers | 5,000 | 10,000 |
+| Skills metadata | 500 | 1,000 |
+| Working space | >140,000 | -- |
+
+### MCP Server Strategy
+
+| Strategy | Criteria |
+|----------|----------|
+| `always` | Essential for daily work (Playwright, Notion) |
+| `lazy` | Occasionally needed (GitHub, Slack) |
+| `disable` | Rarely used or token-heavy |
+
+Every MCP server MUST have `serverInstructions` for Tool Search.
+
+### CLAUDE.md Health Checks
+- Line count (warn >200), token estimate (warn >3,000)
+- Structure quality, redundant info, unnecessary repetition
+
+### Auto-Fix (safe, with backup)
+- Add `serverInstructions` to MCP servers
+- Add frontmatter to commands missing it
+- Suggest CLAUDE.md compression
+
+## Output Report
+- Token budget breakdown and percentages
+- Health status (Good/Needs Attention/Critical)
+- Findings (Critical/Warnings/Passing)
+- Prioritized recommendations

.claude/commands/ourdigital-ad-manager.md

@@ -0,0 +1,38 @@
+---
+description: Ad copywriting and keyword research for OurDigital marketing
+---
+
+# OurDigital Ad Manager
+
+Automated ad copywriting and keyword research. Activated with "ourdigital" keyword.
+
+## Triggers
+- "ourdigital ad copy", "ourdigital 광고 카피"
+- "ourdigital keyword", "ourdigital 키워드"
+
+## Scripts
+
+```bash
+# Generate Google Ads copy
+python code/scripts/generate_ads.py --product "SEO 컨설팅" --platform google --variations 3
+
+# Keyword research
+python code/scripts/keyword_research.py --seed "데이터 분석" --market korea
+
+# Bulk ad generation
+python code/scripts/generate_ads.py --input keywords.csv --platform naver --output ads.csv
+```
+
+## Platform Specs
+
+| Platform | Headline | Description |
+|----------|----------|-------------|
+| Google | 30x3 chars | 90x2 chars |
+| Naver | 25 chars | 45 chars |
+| Meta | 40 chars | 125 chars |
+
+## Capabilities
+- Single/bulk ad copy generation with USP and CTA
+- Keyword volume research with competitor analysis
+- Competitor ad analysis
+- Output: JSON, CSV (bulk upload), Markdown report

.claude/commands/ourdigital-backoffice.md

@@ -0,0 +1,39 @@
+---
+description: Business document creation (quotes, proposals, cost analysis) for OurDigital
+---
+
+# OurDigital Backoffice
+
+Business document generation with pricing automation. Activated with "ourdigital" keyword.
+
+## Triggers
+- "ourdigital quote", "ourdigital 견적서"
+- "ourdigital proposal", "ourdigital 제안서"
+
+## Scripts
+
+```bash
+# Generate quote
+python code/scripts/generate_quote.py --client "ABC Company" --services "seo_audit,gtm_setup"
+
+# Create proposal
+python code/scripts/create_proposal.py --client "XYZ Corp" --project "마케팅 자동화" --duration "3months"
+
+# Cost analysis
+python code/scripts/cost_analysis.py --project "GTM 구축" --investment 5000000 --period 12months
+```
+
+## Service Codes & Base Prices
+
+| Code | Service | Price |
+|------|---------|-------|
+| `seo_audit` | SEO Technical Audit | 4,000,000 |
+| `seo_monthly` | SEO Monthly | 2,000,000/월 |
+| `gtm_setup` | GTM Setup | 3,000,000 |
+| `ga4_setup` | GA4 Implementation | 2,000,000 |
+| `dashboard` | Dashboard Dev | 4,000,000 |
+| `consulting` | Consulting Day | 1,500,000/일 |
+| `workshop` | Workshop | 1,500,000/회 |
+
+## Output Formats
+- Markdown (default), PDF, DOCX

.claude/commands/ourdigital-blog.md

@@ -0,0 +1,42 @@
+---
+description: Korean blog drafting for blog.ourdigital.org with Ghost CMS integration
+---
+
+# OurDigital Blog
+
+Korean blog draft creation for blog.ourdigital.org. Activated with "ourdigital" keyword.
+
+## Triggers
+- "ourdigital blog", "ourdigital 블로그"
+- "ourdigital 한국어 포스트"
+
+## Channel Profile
+
+- URL: blog.ourdigital.org
+- Language: Korean (영문 전문용어 병기)
+- Tone: Analytical, Educational
+- Platform: Ghost CMS
+- Length: 1,500-3,000자
+
+## Workflow
+
+1. **Topic Clarification**: 주제, 타겟 독자, 깊이 수준
+2. **Draft Structure**: 도입부(Hook) -> 본론(3-5 포인트) -> 결론(Summary + 열린 질문)
+3. **Writing Style**: 분석적+개인적 톤, 한글 기본 영문 병기, 관찰->분석->함의
+4. **SEO Metadata**: title(60자), meta_description(155자), slug, tags
+5. **Output**: Markdown with YAML frontmatter
+
+## Scripts
+
+```bash
+python shared/scripts/export_blog.py --output ulysses
+python shared/scripts/ghost_publish.py --draft
+```
+
+## Export Options
+1. Ulysses -> `$ULYSSES_EXPORT_PATH`
+2. Ghost Draft -> API push
+3. Local -> `./output/blog/`
+
+## Brand Compliance
+- 분석적 톤, 기술+인간적 함의, 전문용어 영문 병기, 1,500-3,000자

.claude/commands/ourdigital-document.md

@@ -0,0 +1,47 @@
+---
+description: Notion-to-presentation workflow for OurDigital branded documents
+---
+
+# OurDigital Document
+
+Automated Notion-to-presentation pipeline with brand styling.
+
+## Triggers
+- "ourdigital document", "ourdigital 문서"
+- "ourdigital presentation", "ourdigital 프레젠테이션"
+
+## Pipeline
+
+```
+extract_notion.py -> synthesize_content.py -> apply_brand.py
+     |                    |                      |
+ research.json       synthesis.json         presentation.pptx
+```
+
+## Quick Start
+
+```bash
+python scripts/run_workflow.py --notion-url [URL] --output presentation.pptx
+
+# Step-by-step
+python scripts/extract_notion.py [URL] > research.json
+python scripts/synthesize_content.py research.json > synthesis.json
+python scripts/apply_brand.py synthesis.json --output presentation.pptx
+```
+
+## Scripts
+
+| Script | Purpose |
+|--------|---------|
+| `run_workflow.py` | Orchestrate full pipeline |
+| `extract_notion.py` | Extract content from Notion |
+| `synthesize_content.py` | Analyze and structure |
+| `apply_brand.py` | Apply corporate styling |
+
+## Output Formats
+- PowerPoint (.pptx)
+- Figma (via API)
+- HTML preview
+
+## Brand Configuration
+See `code/assets/brand_config.json` for logo, colors (OurDigital palette), fonts (Poppins/Lora), slide templates.

.claude/commands/ourdigital-journal.md

@@ -0,0 +1,44 @@
+---
+description: English essay creation for journal.ourdigital.org with Ghost CMS integration
+---
+
+# OurDigital Journal
+
+English essay and article creation for journal.ourdigital.org. Activated with "ourdigital" keyword.
+
+## Triggers
+- "ourdigital journal", "ourdigital essay"
+- "ourdigital English article"
+
+## Channel Profile
+
+- URL: journal.ourdigital.org
+- Language: English
+- Tone: Conversational, Poetic, Reflective
+- Platform: Ghost CMS
+- Length: 1,000-2,000 words
+
+## Workflow
+
+1. **Topic Exploration**: Angle, audience, depth level
+2. **Essay Structure**: Opening (evocative) -> Exploration (3-4 observations) -> Synthesis -> Closing (open-ended)
+3. **Writing Style**: First-person reflective, philosophical-technical hybrid, epistemic humility, cultural bridging
+4. **Output**: Markdown with YAML frontmatter (title, meta_description, slug, tags)
+
+## Content Types
+
+| Type | Length |
+|------|--------|
+| Personal Essay | 1,000-1,500 words |
+| Cultural Observation | 1,500-2,000 words |
+| Industry Insight | 1,200-1,800 words |
+
+## Scripts
+
+```bash
+python shared/scripts/ghost_publish.py --file essay.md --channel journal --draft
+```
+
+## Export Options
+1. Ghost Draft -> API push
+2. Local -> `./output/journal/`

.claude/commands/ourdigital-skill-creator.md

@@ -0,0 +1,39 @@
+---
+description: Meta skill for creating new OurDigital Claude Skills with scaffolding
+---
+
+# OurDigital Skill Creator
+
+Create and manage OurDigital Claude Skills with automated scaffolding and Notion sync.
+
+## Triggers
+- "ourdigital 스킬 만들기", "ourdigital skill creator"
+- "create ourdigital skill", "new ourdigital skill"
+
+## Quick Start
+
+```bash
+python shared/scripts/init_skill.py {skill-name} --number XX
+python shared/scripts/validate_skill.py XX-ourdigital-{skill-name}
+python shared/scripts/sync_notion.py XX-ourdigital-{skill-name} --action=create
+```
+
+## Workflow
+
+1. **Suitability Check**: Clear trigger, focused scope, reusable resources, no overlap (>=3 passes)
+2. **Requirements Q&A**: Purpose, trigger, tools, output, environment
+3. **Generate Structure**: `mkdir -p XX-ourdigital-{name}/{code,desktop,shared/{references,templates,scripts},docs/logs}`
+4. **YAML Frontmatter**: Standard template with name, description, triggers, features
+5. **Validation**: Directory structure, SKILL.md in both versions, content 800-1,200 words
+6. **Notion Sync**: Record to Working with AI database
+
+## Skill Categories
+
+| Number | Category |
+|--------|----------|
+| 01-09 | OurDigital Core |
+| 10 | Meta (this skill) |
+| 11-19 | SEO |
+| 20-29 | GTM/Analytics |
+| 31-39 | Notion |
+| 40-49 | Jamie Clinic |

.claude/commands/ourdigital-trainer.md

@@ -0,0 +1,42 @@
+---
+description: Training material creation and workshop planning for OurDigital
+---
+
+# OurDigital Trainer
+
+Training material generation with template-based curriculum and evaluation forms.
+
+## Triggers
+- "ourdigital training", "ourdigital 교육"
+- "ourdigital workshop", "ourdigital 워크샵"
+
+## Scripts
+
+```bash
+# Generate curriculum
+python code/scripts/generate_curriculum.py --topic "데이터 리터러시" --duration "4hours" --audience "마케터"
+
+# Create workshop agenda
+python code/scripts/create_workshop.py --topic "AI 활용법" --format "half-day" --participants 20
+
+# Generate evaluation form
+python code/scripts/create_evaluation.py --training "SEO 기초" --type "pre-post"
+```
+
+## Workshop Formats
+
+| Format | Duration | Modules |
+|--------|----------|---------|
+| mini | 2 hours | 2 |
+| half-day | 4 hours | 3-4 |
+| full-day | 8 hours | 5-6 |
+| series | Multiple | Custom |
+
+## Evaluation Types
+- pre-post: 학습 전후 비교
+- satisfaction: 만족도 조사
+- knowledge: 지식 평가
+- application: 현업 적용도
+
+## Output Formats
+- Markdown (default), JSON, Google Slides export

.claude/commands/seo-comprehensive-audit.md

@@ -0,0 +1,40 @@
+---
+description: Unified 6-stage SEO audit orchestrator with weighted health score
+---
+
+# SEO Comprehensive Audit
+
+Runs 6 sub-skill audits, merges results into unified report with weighted health score (0-100), pushes to Notion.
+
+## Triggers
+- "comprehensive SEO", "full SEO audit"
+- "종합 SEO 감사"
+
+## Quick Start
+
+```bash
+python scripts/seo_audit_orchestrator.py --url https://example.com
+python scripts/seo_audit_orchestrator.py --url https://example.com --skip-local --skip-gsc
+python scripts/seo_audit_orchestrator.py --url https://example.com --json
+```
+
+## Pipeline (6 Stages)
+
+| Stage | Audit | Weight |
+|-------|-------|--------|
+| 1 | Technical SEO (robots, sitemap) | 20% |
+| 2 | On-Page SEO (meta, headings, links) | 20% |
+| 3 | Core Web Vitals (LCP, CLS, INP) | 25% |
+| 4 | Schema Validation | 15% |
+| 5 | Local SEO (GBP, Naver, NAP) | 10% |
+| 6 | Search Console (rankings, CTR) | 10% |
+
+## Stage 5: Local SEO Key Requirements
+- Business Identity extraction is MANDATORY first step
+- Korean market: GBP and Naver Smart Place = Critical; Kakao Map = High
+- GBP/Naver Map are JS-rendered; report unfound as "not discoverable via web search"
+
+## Notion Output
+- Database ID: `2c8581e5-8a1e-8035-880b-e38cefc2f3ef`
+- Report in Korean; technical English terms as-is
+- Audit ID format: COMP-YYYYMMDD-NNN

.claude/commands/seo-core-web-vitals.md

@@ -0,0 +1,45 @@
+---
+description: Core Web Vitals analyzer using PageSpeed Insights API (LCP, CLS, INP, FID)
+---
+
+# SEO Core Web Vitals
+
+PageSpeed Insights API client for CWV measurement and recommendations.
+
+## Triggers
+- "Core Web Vitals", "page speed"
+- "LCP", "CLS", "INP", "performance audit"
+
+## Quick Start
+
+```bash
+export PAGESPEED_API_KEY=your_api_key
+python scripts/pagespeed_client.py --url https://example.com
+python scripts/pagespeed_client.py --url https://example.com --strategy both
+python scripts/pagespeed_client.py --urls urls.txt --output results.json
+```
+
+## CWV Thresholds
+
+| Metric | Good | Poor |
+|--------|------|------|
+| LCP | <=2.5s | >4s |
+| FID | <=100ms | >300ms |
+| CLS | <=0.1 | >0.25 |
+| INP | <=200ms | >500ms |
+
+## Common Fixes
+
+| Issue | Fix |
+|-------|-----|
+| Large LCP | Optimize images, preload critical resources |
+| High CLS | Set image dimensions, avoid injected content |
+| Poor INP | Reduce JavaScript, optimize event handlers |
+| Slow TTFB | Improve server response, use CDN |
+
+## Rate Limits
+- No API key: 25/day; With key: 25,000/day
+
+## Notion Output
+- Database: `2c8581e5-8a1e-8035-880b-e38cefc2f3ef`
+- Korean report, Audit ID: [TYPE]-YYYYMMDD-NNN

.claude/commands/seo-local-audit.md

@@ -0,0 +1,42 @@
+---
+description: Local SEO audit for Korean-market businesses (GBP, Naver Place, NAP, citations)
+---
+
+# SEO Local Audit
+
+Korean-market local SEO: business identity, GBP, Naver Smart Place, Kakao Map, NAP consistency, citations, LocalBusiness schema.
+
+## Triggers
+- "local SEO", "Google Business Profile"
+- "Naver Place", "NAP consistency"
+
+## Workflow (7 Steps)
+
+1. **Business Identity (MANDATORY FIRST)**: Extract from JSON-LD, contact page, footer
+2. **Website NAP Extraction**: Establish canonical NAP baseline
+3. **GBP Verification**: Layered discovery (provided URL -> website -> WebSearch fallback)
+4. **Naver Smart Place**: Layered discovery with Korean search queries
+5. **Kakao Map Verification**: Check website links, then WebSearch
+6. **Citation Discovery**: Industry directories (강남언니, 바비톡, 굿닥, etc.)
+7. **LocalBusiness Schema Validation**: JSON-LD completeness check
+
+## Scoring Weights
+
+| Component | Weight |
+|-----------|--------|
+| NAP Consistency | 20% |
+| GBP Optimization | 20% |
+| Naver Smart Place | 20% |
+| LocalBusiness Schema | 15% |
+| Kakao Map | 10% |
+| Citations | 10% |
+| Business Identity | 5% |
+
+## Key Rules
+- GBP and Naver Map are JS-rendered -- use WebSearch for discovery
+- "Not discoverable via web search" != "does not exist"
+- Korean market: Naver Smart Place is as important as GBP
+
+## Notion Output
+- Database: `2c8581e5-8a1e-8035-880b-e38cefc2f3ef`
+- Category: Local SEO, Audit ID: LOCAL-YYYYMMDD-NNN

.claude/commands/seo-on-page-audit.md

@@ -0,0 +1,40 @@
+---
+description: On-page SEO analyzer for meta tags, headings, links, images, and Open Graph
+---
+
+# SEO On-Page Audit
+
+Single-page optimization analysis: meta tags, heading structure, links, images, OG data.
+
+## Triggers
+- "on-page SEO", "meta tags"
+- "heading analysis", "page SEO check"
+
+## Quick Start
+
+```bash
+python scripts/page_analyzer.py --url https://example.com
+python scripts/page_analyzer.py --url https://example.com --json
+python scripts/page_analyzer.py --urls urls.txt
+```
+
+## Analysis Categories
+- **Meta Tags**: Title (length, keywords), description, canonical, robots
+- **Heading Structure**: H1 presence/count, hierarchy validation, keyword placement
+- **Links**: Internal/external count, broken links, nofollow distribution
+- **Images**: Alt attributes, file sizes, lazy loading
+- **Open Graph**: OG title/description/image, Twitter Cards
+
+## Common Issues
+
+| Issue | Severity |
+|-------|----------|
+| Missing H1 | High |
+| Title too long (>60) | Medium |
+| No meta description | High |
+| Images without alt | Medium |
+| Multiple H1 tags | Medium |
+
+## Notion Output
+- Database: `2c8581e5-8a1e-8035-880b-e38cefc2f3ef`
+- Korean report, Audit ID: [TYPE]-YYYYMMDD-NNN

.claude/commands/seo-search-console.md

@@ -0,0 +1,42 @@
+---
+description: Google Search Console data retrieval (rankings, CTR, impressions, sitemaps)
+---
+
+# SEO Search Console
+
+GSC API client for search analytics, sitemap status, and index coverage.
+
+## Triggers
+- "Search Console", "rankings"
+- "GSC data", "search performance"
+
+## Quick Start
+
+```bash
+python scripts/gsc_client.py --site sc-domain:example.com --action summary
+python scripts/gsc_client.py --site sc-domain:example.com --action queries --limit 100
+python scripts/gsc_client.py --site sc-domain:example.com --action pages
+```
+
+## Configuration
+
+- Credentials: `~/.credential/ourdigital-seo-agent.json`
+- Service account: `ourdigital-seo-agent@ourdigital-insights.iam.gserviceaccount.com`
+
+## Actions
+
+| Action | Description |
+|--------|-------------|
+| `summary` | Clicks, impressions, CTR, position overview |
+| `queries` | Top search queries |
+| `pages` | Top pages by clicks |
+| `sitemaps` | Sitemap submission status |
+| `coverage` | Index coverage issues |
+
+## Site Property Formats
+- Domain: `sc-domain:example.com`
+- URL prefix: `https://www.example.com/`
+
+## Notion Output
+- Database: `2c8581e5-8a1e-8035-880b-e38cefc2f3ef`
+- Korean report, Audit ID: [TYPE]-YYYYMMDD-NNN

.claude/commands/seo-technical-audit.md

@@ -0,0 +1,44 @@
+---
+description: Technical SEO audit for robots.txt, XML sitemap, and URL crawlability
+---
+
+# SEO Technical Audit
+
+Crawlability fundamentals: robots.txt validation, XML sitemap analysis, URL accessibility checking.
+
+## Triggers
+- "technical SEO", "crawlability"
+- "robots.txt", "sitemap validation"
+
+## Quick Start
+
+```bash
+python scripts/robots_checker.py --url https://example.com
+python scripts/sitemap_validator.py --url https://example.com/sitemap.xml
+python scripts/sitemap_crawler.py --sitemap https://example.com/sitemap.xml
+```
+
+## Scripts
+
+| Script | Purpose |
+|--------|---------|
+| `robots_checker.py` | Parse robots.txt, test URL rules |
+| `sitemap_validator.py` | Validate XML structure, URL count, lastmod |
+| `sitemap_crawler.py` | Async check URL accessibility, HTTP status |
+
+## Common Issues Detected
+
+| Issue | Severity |
+|-------|----------|
+| Missing sitemap declaration | Medium |
+| Blocking CSS/JS resources | High |
+| URLs returning 404 | High |
+| Exceeds 50,000 URL limit | High |
+| Non-canonical URLs included | Medium |
+
+## Config
+- `CRAWL_DELAY=1.0`, `MAX_CONCURRENT=20`, `REQUEST_TIMEOUT=30`
+
+## Notion Output
+- Database: `2c8581e5-8a1e-8035-880b-e38cefc2f3ef`
+- Korean report, Audit ID: [TYPE]-YYYYMMDD-NNN

AGENTS.md

@@ -129,9 +129,19 @@ Task 2: general-purpose - "Implement the planned skill"  # Needs Task 1 result
 
 ### GTM Skills (60-69)
 
-- Use **gtm-manager** agent for GTM-specific debugging
+Three specialized skills with clear handoff workflow: **audit → edit → validate**
-- Requires Chrome GTM Debug profile for live testing
+
-- Scripts interact with GTM API and dataLayer
+| Skill | Purpose | MCP Tools |
+|-------|---------|-----------|
+| 60-gtm-audit | Scan pages, gap analysis, tag design blueprints | DTM Agent + Chrome DevTools |
+| 61-gtm-editor | Create/modify tags, triggers, variables via GTM API | DTM Agent + Chrome DevTools |
+| 62-gtm-validator | QA tag firing, trigger selectors, naming conventions | DTM Agent + Chrome DevTools |
+
+- **gtm-audit** Mode D outputs blueprints → hand off to **gtm-editor** for implementation
+- **gtm-editor** creates tags → hand off to **gtm-validator** for QA verification
+- **gtm-validator** finds broken selectors → hand back to **gtm-editor** for fixes
+- All three use DTM Agent MCP for container operations and Chrome DevTools MCP for browser inspection
+- Audit reports write to Notion GTM Audit Log database
 
 ### Jamie Clinic Skills (40-49)
 
@@ -172,6 +182,16 @@ Task(
 
 **Parallel workflows:** Set `NOTEBOOKLM_HOME` per agent to avoid context conflicts.
 
+### Mac Optimizer (92)
+
+- **Claude Code only** — no Desktop version
+- Runs read-only audit scripts that output JSON lines, then presents findings as severity-ranked tables
+- 5 audit modules: packages, environment, security, cleanup, resources
+- `doctor` mode runs all 5 sequentially and presents unified report
+- **Always ask user consent** before executing any cleanup or system changes
+- Scripts are in `custom-skills/92-mac-optimizer/scripts/`
+- Reference docs in `custom-skills/92-mac-optimizer/references/`
+
 ### Reference Curator Skills (90-99)
 
 - Use **reference-curator-pipeline** for full automated curation workflows
@@ -204,7 +224,7 @@ For long-running tasks, use `run_in_background: true`:
 
 ```
 # Good candidates for background execution:
-- Full skill audit across all 52 skills
+- Full skill audit across all 62 skills
 - Running Python tests on multiple skills
 - Generating comprehensive documentation
 

CLAUDE.md

@@ -7,7 +7,7 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 **GitHub**: https://github.com/ourdigital/our-claude-skills
 
 This is a Claude Skills collection repository containing:
-- **custom-skills/**: 61 custom skills for OurDigital workflows, SEO, GTM, Jamie Brand, NotebookLM, Notion, D.intelligence Agent Corps, Reference Curation, and Multi-Agent Collaboration
+- **custom-skills/**: 62 custom skills for OurDigital workflows, SEO, GTM, Jamie Brand, NotebookLM, Notion, D.intelligence Agent Corps, Reference Curation, Mac Optimizer, TUI Designer, and Multi-Agent Collaboration
 - **example-skills/**: Reference examples from Anthropic's official skills repository
 - **official-skills/**: Notion integration skills (3rd party)
 - **reference/**: Skill format requirements documentation
@@ -68,9 +68,9 @@ This is a Claude Skills collection repository containing:
 
 | # | Skill | Purpose | Trigger |
 |---|-------|---------|---------|
-| 60 | gtm-audit | GTM container audit | "audit GTM", "GTM analysis" |
+| 60 | gtm-audit | GTM audit — page scan, site audit, gap analysis, tag design | "GTM audit", "scan page", "tracking coverage", "gap analysis" |
-| 61 | gtm-manager | GTM management + dataLayer | "GTM manager", "dataLayer" |
+| 61 | gtm-editor | GTM tag/trigger/variable creation via API, ES5 Custom HTML, dataLayer | "create GTM tag", "generate dataLayer", "modify trigger", "manage GTM" |
-| 62 | gtm-guardian | Live tag monitoring & validation | "monitor GTM", "tag validation" |
+| 62 | gtm-validator | GTM QA — tag firing, trigger testing, naming conventions, cross-platform | "validate tags", "QA GTM", "debug GTM", "naming conventions" |
 
 ### Notion Tools (31-39)
 
@@ -85,7 +85,6 @@ This is a Claude Skills collection repository containing:
 |---|-------|---------|---------|
 | 40 | jamie-brand-editor | Branded content generation | "write Jamie blog", "Jamie content" |
 | 41 | jamie-brand-audit | Content review/compliance | "review content", "brand audit" |
-| 42 | jamie-journal-editor | Clinic journal editing | "Jamie journal", "진료 일지" |
 | 43 | jamie-youtube-manager | YouTube SEO audit & management | "YouTube SEO", "YT optimization" |
 | 44 | jamie-youtube-subtitle-checker | YouTube subtitle validation | "check subtitles", "subtitle QA" |
 | 45 | jamie-instagram-manager | Instagram account management | "Instagram management", "IG strategy" |
@@ -121,7 +120,14 @@ This is a Claude Skills collection repository containing:
 
 **User Guide:** `custom-skills/dintel-shared/USER-GUIDE.md`
 
-### Reference Curator & Multi-Agent (90-99)
+### System & Design Tools (92-93)
+
+| # | Skill | Purpose | Trigger |
+|---|-------|---------|---------|
+| 92 | mac-optimizer | macOS system health audit & optimization (Claude Code only) | "audit my mac", "system health", "clean up caches", "check security", "update packages" |
+| 93 | tui-designer | TUI wizard interface design (Norton Commander / Gopher style, Rich) | "build TUI", "CLI wizard", "terminal UI", "Rich TUI" |
+
+### Reference Curator & Multi-Agent (90-91)
 
 | # | Skill | Purpose | Trigger |
 |---|-------|---------|---------|
@@ -247,15 +253,14 @@ our-claude-skills/
 │   ├── 34-seo-reporting-dashboard/
 │   │
 │   ├── 60-gtm-audit/
-│   ├── 61-gtm-manager/
+│   ├── 61-gtm-editor/
-│   ├── 62-gtm-guardian/
+│   ├── 62-gtm-validator/
 │   │
 │   ├── 31-notion-organizer/
 │   ├── 32-notion-writer/
 │   │
 │   ├── 40-jamie-brand-editor/
 │   ├── 41-jamie-brand-audit/
-│   ├── 42-jamie-journal-editor/
 │   ├── 43-jamie-youtube-manager/
 │   ├── 44-jamie-youtube-subtitle-checker/
 │   ├── 45-jamie-instagram-manager/
@@ -290,6 +295,10 @@ our-claude-skills/
 │   │
 │   ├── 91-multi-agent-guide/
 │   │
+│   ├── 92-mac-optimizer/            # macOS system health toolkit (Claude Code only)
+│   │
+│   ├── 93-tui-designer/             # TUI wizard design (Rich, Norton Commander style)
+│   │
 │   └── 99_archive/
 │
 ├── example-skills/skills-main/

README.md

@@ -2,7 +2,7 @@
 
 > **Internal R&D Repository** - This repository is restricted for internal use only.
 
-A collection of **61 custom Claude Skills** for OurDigital workflows, D.intelligence Agent Corps (9-agent business operations suite), Jamie Plastic Surgery Clinic brand management, SEO/GTM tools, NotebookLM automation, Notion integrations, reference documentation curation, and multi-agent collaboration.
+A collection of **62 custom Claude Skills** for OurDigital workflows, D.intelligence Agent Corps (9-agent business operations suite), Jamie Plastic Surgery Clinic brand management, SEO/GTM tools, NotebookLM automation, Notion integrations, reference documentation curation, macOS system optimization, TUI wizard design, and multi-agent collaboration.
 
 ## Quick Install
 
@@ -88,9 +88,9 @@ cd our-claude-skills/custom-skills/_ourdigital-shared
 
 | # | Skill | Purpose |
 |---|-------|---------|
-| 60 | `gtm-audit` | GTM container audit with Chrome DevTools |
+| 60 | `gtm-audit` | GTM container audit — page scan, site audit, gap analysis, tag design (DTM Agent + Chrome DevTools MCP) |
-| 61 | `gtm-manager` | GTM management + dataLayer generation |
+| 61 | `gtm-editor` | GTM tag/trigger/variable creation via API, ES5 Custom HTML, dataLayer generation, workspace lifecycle |
-| 62 | `gtm-guardian` | Live tag monitoring & validation |
+| 62 | `gtm-validator` | GTM QA — tag firing verification, trigger testing, dataLayer schema, naming conventions, cross-platform mapping |
 
 ### Notion Tools (31-39)
 
@@ -105,7 +105,6 @@ cd our-claude-skills/custom-skills/_ourdigital-shared
 |---|-------|---------|
 | 40 | `jamie-brand-editor` | Branded content generation |
 | 41 | `jamie-brand-audit` | Content review/compliance |
-| 42 | `jamie-journal-editor` | Clinic journal editing |
 | 43 | `jamie-youtube-manager` | YouTube SEO audit & management |
 | 44 | `jamie-youtube-subtitle-checker` | YouTube subtitle validation |
 | 45 | `jamie-instagram-manager` | Instagram account management |
@@ -121,7 +120,14 @@ cd our-claude-skills/custom-skills/_ourdigital-shared
 
 **Prerequisites:** `pip install notebooklm-py && playwright install chromium && notebooklm login`
 
-### Reference Curator & Multi-Agent (90-99)
+### System & Design Tools (92-93)
+
+| # | Skill | Purpose |
+|---|-------|---------|
+| 92 | `mac-optimizer` | macOS system health audit & optimization (Claude Code only) |
+| 93 | `tui-designer` | TUI wizard interface design (Norton Commander / Gopher style, Rich) |
+
+### Reference Curator & Multi-Agent (90-91)
 
 | # | Skill | Purpose |
 |---|-------|---------|
@@ -177,6 +183,8 @@ our-claude-skills/
 │   ├── 50-53 (NotebookLM tools)
 │   ├── 90-reference-curator/
 │   ├── 91-multi-agent-guide/
+│   ├── 92-mac-optimizer/
+│   ├── 93-tui-designer/
 │   └── 99_archive/
 │
 ├── example-skills/              # Anthropic reference examples

custom-skills/11-seo-comprehensive-audit/code/gotcha/JHR-josunhotel.md

@@ -0,0 +1,28 @@
+# JHR — josunhotel.com Gotchas
+
+Client: **JHR** (Josun Hotels & Resorts / 조선호텔앤리조트)
+Domain: josunhotel.com + subdomains (gjb, gjj, jpg, grp)
+
+---
+
+## 1. Intentionally Truncated Directory Names in robots.txt
+
+**Date discovered**: 2026-03-20
+**Audit ID**: COMP-20260320-001
+
+The following `Disallow` paths in robots.txt look like typos but are **intentional directory names** on the server:
+
+| robots.txt path | Looks like it should be | Actual status |
+|-----------------|------------------------|---------------|
+| `/cnfirm` | `/confirm` | **Intentional** — real directory name |
+| `/mber` | `/member` | **Intentional** — real directory name |
+
+**Do NOT recommend renaming these** in audit reports. The server-side application uses these truncated names by design.
+
+### Context
+
+The josunhotel.com backend (Java/.do endpoints) uses shortened directory names for certain internal paths. This is likely a legacy naming convention from the original application architecture.
+
+### Audit Impact
+
+When running Technical SEO audits (Stage 1), skip the "typo in Disallow paths" finding for `/cnfirm` and `/mber`. These are valid paths that correctly block crawler access to confirmation and member-related pages.

custom-skills/11-seo-comprehensive-audit/code/gotcha/JHR-lescapehotel.md

@@ -0,0 +1,30 @@
+# JHR — lescapehotel.com Gotchas
+
+Client: **JHR** (Josun Hotels & Resorts)
+Domain: lescapehotel.com → les.josunhotel.com (migrated)
+
+---
+
+## 1. Domain Migration Complete — Monitor Redirects & Link Juice
+
+**Date discovered**: 2025-12-14
+**Updated**: 2026-03-20
+**Status**: Migration COMPLETE
+
+The L'Escape Hotel domain migration from `lescapehotel.com` to `les.josunhotel.com` has been completed.
+
+### What to Monitor (Watchtower)
+
+- **301 redirects**: Verify all old lescapehotel.com URLs still 301 to correct les.josunhotel.com counterparts
+- **Link juice preservation**: Check that backlinks from external sites pointing to lescapehotel.com are passing authority through redirects
+- **Redirect chains**: Watch for double redirects (lescapehotel.com → old intermediate → les.josunhotel.com)
+- **GSC coverage**: Monitor les.josunhotel.com indexing in Google Search Console
+- **Referring domains**: Track referring domain count in Ahrefs/GSC to ensure backlink equity is maintained
+
+### Audit Checklist (Run Periodically)
+
+1. Sample 10-20 old lescapehotel.com URLs — verify 301 status
+2. Check for any 404s on les.josunhotel.com that should have redirects
+3. Compare organic traffic trends pre/post migration
+4. Verify old sitemap URLs are all redirecting properly
+5. Check Naver Search Advisor for indexing status

custom-skills/11-seo-comprehensive-audit/code/gotcha/SLA-shillahotels.md

@@ -0,0 +1,40 @@
+# SLA — shillahotels.com Gotchas
+
+Client: **SLA** (Shilla Hotels & Resorts / 신라호텔)
+Domain: shillahotels.com
+
+---
+
+## 1. www1 / www2 Are Dev/Stage Hosts, NOT Production
+
+**Date discovered**: 2026-03-20
+**Context**: SLA new integrated website under construction
+
+The Shilla Hotels domain uses numbered subdomains for development environments:
+
+| Subdomain | Purpose | Status |
+|-----------|---------|--------|
+| `www1.shillahotels.com` | Development | Active — deployed intermittently |
+| `www2.shillahotels.com` | Staging | Active — deployed intermittently |
+| `www.shillahotels.com` | Production (current) | Live |
+| TBD (new integrated site) | Production (future) | **Target launch: end of June 2026** |
+
+**Do NOT run technical SEO audits against www1 or www2** unless specifically instructed. These are pre-production environments and will have:
+- No robots.txt
+- No XML sitemap
+- Incomplete meta tags
+- Missing canonical/hreflang tags
+
+These are expected states for dev/stage, not audit findings.
+
+### When to Scan
+
+The client will notify when www1/www2 need technical SEO element checks. Do NOT proactively audit these subdomains.
+
+## 2. No robots.txt or Sitemap on Dev/Stage Hosts
+
+**Date discovered**: 2026-03-20
+
+robots.txt and sitemap.xml are intentionally not deployed to www1 and www2. This is expected for pre-production environments. Do NOT flag as issues.
+
+Wait for client instruction before scanning technical SEO elements on these hosts.

custom-skills/60-gtm-audit/code/SKILL.md

@@ -0,0 +1,141 @@
+---
+name: gtm-audit
+description: >
+  Automated GTM audit and analysis. Scans websites for tracking coverage, compares
+  against GTM container config, identifies gaps, and reports to Notion. Uses Chrome
+  DevTools MCP for browser inspection and DTM Agent MCP for container operations.
+  Triggers on "GTM audit", "audit website", "scan page", "check tracking",
+  "tracking coverage", "gap analysis", "site audit", "tag firing check".
+  NOT for creating/modifying tags (use gtm-editor) or validating/QA (use gtm-validator).
+---
+
+# GTM Audit Skill
+
+Analyze GTM implementations by scanning websites and comparing against container configuration.
+
+## Available Tools
+
+### Browser Inspection (Chrome DevTools MCP)
+- `navigate_page` — Load target URL
+- `evaluate_script` — Capture dataLayer, detect GTM containers, check JS globals
+- `list_network_requests` — Capture tag firing network requests
+- `take_screenshot` — Document page state
+- `click` / `hover` — Simulate user interactions
+- `list_console_messages` — Check for JS errors
+
+### GTM Container (DTM Agent MCP)
+- `dtm_status` — Check auth and active container
+- `dtm_list_tags` / `dtm_list_triggers` / `dtm_list_variables` — Get container config
+- `dtm_audit_scan` — Scan page with collected data (returns structured PageData)
+- `dtm_audit_gap` — Run gap analysis (returns GapReport with OK/MISSING/ORPHAN)
+
+### Reporting (Notion MCP)
+- Write findings to GTM Audit Log: `collection://2cf581e5-8a1e-815a-a7f8-000b88b93585`
+
+## 4 Audit Modes
+
+### Mode A: Page Scan (`/gtm-audit scan <url>`)
+
+Quick single-page diagnostics. No GTM container needed.
+
+1. `navigate_page` to URL, wait for load
+2. `evaluate_script`: capture dataLayer
+   ```javascript
+   JSON.stringify(window.dataLayer || [])
+   ```
+3. `evaluate_script`: detect GTM containers
+   ```javascript
+   (function(){var s=document.querySelectorAll('script[src*="googletagmanager.com/gtm.js"]');var ids=[];s.forEach(function(el){var m=el.src.match(/id=(GTM-[A-Z0-9]+)/);if(m)ids.push(m[1]);});return JSON.stringify(ids);})()
+   ```
+4. `evaluate_script`: detect tracking pixels
+   ```javascript
+   (function(){var f=[];if(window.fbq)f.push('Meta Pixel');if(window.gtag)f.push('GA4');if(window.clarity)f.push('Clarity');if(window.kakaoPixel)f.push('Kakao');if(window.wcs)f.push('Naver');if(window.ttq)f.push('TikTok');return JSON.stringify(f);})()
+   ```
+5. `list_network_requests` — filter for tag domains
+6. Call `dtm_audit_scan` with collected html, network_requests, datalayer_json
+7. Report findings
+
+### Mode B: Site Audit (`/gtm-audit site <url>`)
+
+Full website coverage audit with auto-discovery.
+
+1. Navigate to root URL
+2. `evaluate_script`: extract all internal links
+3. Classify pages by type (home, product, service, form, blog, about)
+4. For each page type: run Mode A scan
+5. Build coverage matrix (page type × event × platform)
+6. Run Mode C gap analysis against container
+7. Write comprehensive report to Notion
+
+### Mode C: Gap Analysis (`/gtm-audit gap <url>`) — MOST IMPORTANT
+
+Compare GTM container config against actual tag firing.
+
+1. `dtm_status` — verify auth and active container
+2. `dtm_list_tags` + `dtm_list_triggers` — get expected configuration
+3. `navigate_page` to URL
+4. `evaluate_script` — capture dataLayer
+5. `list_network_requests` — capture actual tag firings
+6. Call `dtm_audit_gap` with network_requests
+7. Analyze gaps: MISSING (in GTM, not firing), ORPHAN (firing, not in GTM)
+8. Write to Notion GTM Audit Log
+
+### Mode D: Tag Design (`/gtm-audit design <url>`)
+
+AI-powered analysis of what SHOULD be tracked on a page.
+
+1. `navigate_page` to URL
+2. `take_screenshot` — visual reference
+3. `evaluate_script` — inspect DOM: forms, buttons, links, product elements
+4. `evaluate_script` — capture existing dataLayer schema
+5. `dtm_list_tags` — check existing configuration
+6. Design recommendations: which events, triggers, variables are needed
+7. Output as structured blueprint (hand off to gtm-editor for implementation)
+
+## Detection Patterns
+
+### Cloudflare Zaraz Proxy
+URLs with `/1tbv/` path proxy GA4/Ads through the site's domain:
+```
+https://site.com/1tbv/ag/g/c?tid=G-XXXXX → GA4
+https://site.com/1tbv/ag/g/c?tid=AW-XXXXX → Google Ads
+```
+
+### Server-Side GTM (sGTM)
+Custom subdomains: `stms.*`, `sgtm.*`, `ss.*`, `tag.*`
+```
+https://stms.site.com/g/collect?tid=G-XXXXX → GA4 via sGTM
+```
+
+### GA4 Multiple Endpoints
+One GA4 page_view fires to multiple endpoints — this is normal:
+- `google-analytics.com/g/collect`
+- `analytics.google.com/g/s/collect`
+- `stats.g.doubleclick.net/g/collect`
+- `www.google.com/ccm/collect` (Consent Mode)
+- Zaraz proxy endpoints
+
+## Notion Report Fields
+
+| Field | Value |
+|-------|-------|
+| Site | domain name |
+| URL | full URL |
+| Container IDs | GTM-XXXXX |
+| Audit Status | Pass / Warning / Fail |
+| GTM Status | Installed / Not Found / Multiple Containers |
+| Tags Fired | [GA4, Google Ads, Meta Pixel, Kakao, Naver, ...] |
+| Journey Type | full / pageview / scroll / form / checkout / datalayer |
+| Critical Issues | count |
+| Issues Count | count |
+| Summary | AI-generated findings |
+
+## Rules
+
+- Always check `dtm_status` before gap analysis
+- Wait for page to fully load before capturing network requests
+- Use `evaluate_script` to check consent mode before interpreting missing tags
+- Orphan count may be high due to GA4 multi-endpoint — note this in reports
+- **In Mode D (tag design), check elements for `id` attributes** — if missing, recommend adding IDs before designing CSS-based triggers. Suggest naming: `[section]-[element]-[action]`
+- Hand off tag creation work to `gtm-editor` skill
+- Hand off QA/validation work to `gtm-validator` skill

custom-skills/60-gtm-audit/code/docs/common_issues.md

@@ -196,6 +196,121 @@ dataLayer.push({
 
 ---
 
+## Content Grouping Issues (RegEx Table Variables)
+
+### How Content Grouping Works in GTM
+
+Content grouping uses **RegEx Table** variables to categorize pages by URL/path patterns.
+The variable takes an input (typically `{{Page Path}}` or `{{Page URL}}`), tests it against
+an ordered list of regex patterns, and returns the first matching output value.
+If no pattern matches, it falls to the **Default Value** (usually "Other").
+
+**Key settings:**
+- **Full Matches Only**: OFF — partial regex match is sufficient
+- **Capture Groups and Replace**: OFF — output is the literal value, not a regex replacement
+- **Ignore Case**: ON — case-insensitive matching
+
+### New Page Paths Fall Through to "Other"
+
+**Symptoms**: New sections (campaigns, special events, landing pages) show as "Other" in GA4 content group reports.
+
+**Root cause**: The RegEx Table was built for the site's original URL structure. New paths like `/specialEvent/`, `/campaign/`, `/timesale/` don't match any existing pattern.
+
+**Example**: JHR site has `/specialEvent/landersshoppingfesta2026/teaser.do` but only `/package/` and `/event/` are in the regex table, not `/specialEvent/`.
+
+**Fix**: Add regex rule for the new path pattern. Place it BEFORE the default.
+
+**Gotcha — two variables to update**: Sites often have parallel content group variables:
+1. **Page Path based** (e.g., `(\/m)?\/specialEvent\/(.*)`) — for internal reports
+2. **Page URL based** (e.g., full URL with domain regex) — for cross-domain or subdomain tracking
+
+Both must be updated or they'll produce inconsistent groupings.
+
+### RegEx Pattern Conventions (JHR Example)
+
+Page Path patterns follow this structure:
+```
+(\/m)?\/section\/(.*)    →  Korean Category Label
+```
+- `(\/m)?` — optional mobile path prefix
+- `\/section\/` — the URL path segment to match
+- `(.*)` — match anything after
+
+Page URL patterns include domain matching:
+```
+^https\:\/\/(www|app|jpg|gjb|gjj|grp|\.)?josunhotel\.com(\/m)?\/section\/(.*)
+```
+- Multi-subdomain support via alternation group
+- Same `(\/m)?` mobile prefix handling
+
+### Content Group Categories (Hospitality Reference)
+
+| Pattern | Category (KR) | Category (EN) |
+|---------|---------------|---------------|
+| `/intro.do`, `/main.do` | 메인페이지 | Main Page |
+| `/about/`, `/press/` | 기업 소개 | Corporate Info |
+| `/hotel/` | 호텔 소개 | Hotel Info |
+| `/rooms/` | 객실 소개 | Room Info |
+| `/dining/` | 다이닝 이용 | Dining |
+| `/facilities/`, `/meeting/`, `/fitness/` | 부대시설 소개 | Facilities |
+| `/package/`, `/event/` | 이벤트 \| 패키지 조회 | Events & Packages |
+| `/specialEvent/` | 캠페인 \| 프로모션 | Campaign & Promotion |
+| `/timesale/`, `/campaign/` *(placeholder — not actual paths yet, replace when specific paths are registered)* | 캠페인 \| 프로모션 | Campaign & Promotion |
+| `/activity/` | 액티비티 소개 | Activities |
+| `/step[0-4]` | 룸, 패키지 예약 프로세스 | Booking Process |
+| `/resve/dining/` | 다이닝 예약 프로세스 | Dining Booking |
+| `/membership/` | 멤버쉽 | Membership |
+| `/mypage/`, `/login/`, `/join/` | 웹회원 관련 | Member Portal |
+| `/retail/`, `/product/`, `/office/` | 리테일 관련 | Retail |
+| `/voc/`, `/customer/` | 고객지원 | Customer Support |
+| `/policy/` | 웹사이트 정책 | Website Policy |
+| `/upload_file/event/html/` | 캠페인 \| 프로모션 | Campaign & Promotion |
+| Default | Other | Other |
+
+### Two Content Group Variables — Old vs New (JHR)
+
+The JHR container has two content group variables for menu categories:
+
+| | **Contents Group 2** (ID:1234) | **Contents Group new** (ID:1826) |
+|---|---|---|
+| Input | `{{Page Path}}` | `{{Page URL}}` |
+| Rules | 20 | 24 (replacement) |
+| Domain matching | No — path only | Yes — full URL with subdomain alternation |
+| Subdomain coverage | N/A | `www\|app\|jpg\|gjb\|gjj\|grp\|les\|\.` |
+| Cross-domain | No | Yes — booking, josuntns, lounge subdomains |
+| Mobile path | `(\/m)?` prefix | `(\/m)?` prefix within URL pattern |
+
+**"Contents Group new" (ID:1826) is the replacement** — it handles subdomains (booking, T&S, lounge, les) that the old path-based variable cannot distinguish. When auditing, check which variable is referenced in the GA4 config tag — the newer one should be used.
+
+**Gotcha — adding new subdomains**: When a new hotel brand subdomain launches (e.g., `les.josunhotel.com`), the subdomain alternation group `(www|app|...|les|\.)` in ALL main-domain rules must be updated. This affects 14+ rules in the URL-based variable.
+
+### Gotcha — Subdomain Regex Dot Separator
+
+**Bug**: `(www|app|jpg|les|\.)?josunhotel\.com` does NOT match `www.josunhotel.com`.
+
+The `\.` inside the alternation group matches a literal dot OR `www` matches `www`, but neither consumes the `.` between the subdomain and `josunhotel`. The regex engine sees `www` then expects `josunhotel` but finds `.josunhotel`.
+
+**Fix**: Move the dot outside the group as an optional separator:
+```
+BROKEN: (www|app|jpg|gjb|gjj|grp|les|\.)?josunhotel\.com
+FIXED:  (www|app|jpg|gjb|gjj|grp|les)?\.?josunhotel\.com
+```
+
+This correctly matches: `www.josunhotel.com`, `les.josunhotel.com`, `josunhotel.com` (bare), `app.josunhotel.com`.
+
+**Note**: GTM's "Full Matches Only = OFF" means `re.search` (partial match) is used, which may accidentally match the broken pattern on some URLs. But strict `re.match` or JavaScript `pattern.test()` will fail. Always test with the full URL in JavaScript console.
+
+### Audit Checklist for Content Grouping
+
+- [ ] Run `dtm var info <var_id>` to dump the full regex table
+- [ ] Check if new site sections have matching patterns
+- [ ] Verify both Path and URL variables are in sync
+- [ ] Check GA4 config tag references the correct variable
+- [ ] Test in GTM Preview: navigate to new page, check variable value
+- [ ] After update, verify in GA4 Realtime > Content Group report
+
+---
+
 ## Performance Issues
 
 ### Tags Slowing Page Load

custom-skills/60-gtm-audit/code/docs/jhr-ga4-tagging-reference.md

@@ -0,0 +1,298 @@
+# JHR GA4 Tagging Reference
+
+Source: [JHR - User Behaviour, Event Planning & GA setup](https://docs.google.com/spreadsheets/d/1rhzYApbZ4wbe1gE-E43E-mlRdLl_etkIOZnqs1g9X1U)
+
+Container: GTM-NP6NJMP (JHR Website - 통합)
+
+---
+
+## 1. Tag Naming Convention
+
+Format: `{Platform} {TriggerElement} - {Purpose} - {EventName}`
+
+### Platform Categories
+
+| Platform | Usage |
+|----------|-------|
+| GA4 | Google Analytics 4 events |
+| Google Ads | Conversion tracking |
+| Meta | Facebook/Instagram pixel |
+| Kakao | Kakao pixel/moment |
+| Marketing | Cross-platform marketing tags |
+| Analytics | Analytics configuration tags |
+| Site | Site-specific utility tags |
+| SEO | SEO-related tags |
+| Test | Testing/debug tags |
+| {{Campaign Name}} | Campaign-specific tags (e.g., "LandersFesta") |
+
+### Trigger Elements (what triggers the tag)
+
+| Element | Description |
+|---------|-------------|
+| pageview | Page load / virtual pageview |
+| click | Generic click |
+| link | Link click |
+| button | Button click |
+| tab | Tab selection |
+| form | Form submission |
+| layer | Layer/modal/popup view |
+| popup | Popup interaction |
+| banner | Banner click/impression |
+| dropdown | Dropdown selection |
+| radio | Radio button selection |
+| checkbox | Checkbox toggle |
+| ajax | AJAX request complete |
+| dataLayer | DataLayer push event |
+
+### Tag Purposes (page/feature area)
+
+| Purpose | Area |
+|---------|------|
+| booking | Room/package reservation process |
+| dining | Dining reservation process |
+| membership | Club Josun membership |
+| package | Package/event listing & detail |
+| theme | Theme package pages |
+| campaign | Campaign/promotion pages |
+| event | Event pages |
+| timesale | Time-limited sale pages |
+| survey | Survey/feedback |
+| ecommerce | E-commerce tracking |
+| SEO | SEO schema/config |
+| site | Site-wide interactions |
+| config | Configuration/settings |
+| ux | UX tracking |
+| test | Testing |
+
+### Examples
+
+```
+GA4 pageview - booking - room_booking_step1
+GA4 button - theme - theme_pkg_detail
+GA4 click - campaign - kakao_channel_add
+Kakao banner - timesale - {{Event Name}}
+Meta form - event - {{Event Name}}
+Marketing - meta pixel - join_complete
+Marketing - Kakao Pixel - package detail
+```
+
+---
+
+## 2. Inherited Settings Variables
+
+Tags inherit common parameters through shared settings variables.
+This avoids duplicating parameters across hundreds of tags.
+
+### GA4 Configuration Setting (shared across ALL GA4 tags)
+
+| Parameter | Variable | Description |
+|-----------|----------|-------------|
+| login_status | {{cjs - login status Variable}} | Login state |
+| user_lang | locale={{cjs - page language Variable}} | Page language |
+| contents_group_hotel | {{Contents Group 1 - Hotel Site}} | Hotel brand grouping |
+| contents_group_menu | {{Contents Group new - Menu Categories}} | Page section grouping |
+| naver_query | {{URL referrer - naver query}} | Naver search query |
+| naver_oquery | {{URL referrer - naver oquery}} | Naver original query |
+
+### GA4 Event Settings (added to event tags)
+
+| Parameter | Variable |
+|-----------|----------|
+| page_path | {{Page Path}} |
+| login_status | {{cjs - login status Variable}} |
+| user_lang | {{cjs - page language Variable}} |
+
+### GA4 eCommerce Settings (added to ecommerce tags)
+
+| Parameter | Variable |
+|-----------|----------|
+| pkg_name | {{dlv - eCommerce - item_name}} |
+| pkg_hotel | {{dlv - eCommerce - item_brand}} |
+| pkg_price | {{dlv - eCommerce - price}} |
+| pkg_room_type | {{dlv - eCommerce - item_variant}} |
+| pkg_id | {{dlv - eCommerce - item_id}} |
+| page_path | {{Page Path}} |
+
+### GA4 Promotion Settings (added to package/event detail tags)
+
+| Parameter | Variable |
+|-----------|----------|
+| page_path | {{Page Path}} |
+| login_status | {{cjs - login status Variable}} |
+| user_lang | {{cjs - page language Variable}} |
+| packageSn | {{URL query - packageSn Variable}} |
+| themeSn | {{URL query - themeSn Variable}} |
+| eventSn | {{URL query - eventSn Variable}} |
+
+---
+
+## 3. Standard Parameter Keys
+
+| Parameter Name | Allowed Values / Variable |
+|----------------|--------------------------|
+| event_type | click |
+| ui | GNB, modal, button, tab, link, banner, footer |
+| page_path | {{Page Path}} |
+| login_status | (from cjs variable) |
+| user_lang | (from cjs variable) |
+| pkg_name | (package/event title) |
+| click_text | (clicked element text) |
+| click_url | (clicked element URL) |
+
+---
+
+## 4. Property Codes
+
+| # | Hotel Name | URL | Website Code | Report Code |
+|---|-----------|-----|-------------|-------------|
+| 1 | 조선 팰리스 | jpg.josunhotel.com | JPY | JPG |
+| 2 | 웨스틴 조선 서울 | josunhotel.com/hotel/westinSeoul.do | TWC | WJS |
+| 3 | 웨스틴 조선 부산 | josunhotel.com/hotel/westinBusan.do | TWCB | WJB |
+| 4 | 그랜드 조선 부산 | gjb.josunhotel.com | GJB | GJB |
+| 5 | 그랜드 조선 제주 | gjj.josunhotel.com | GJJ | GJJ |
+| 6 | 레스케이프 호텔 | les.josunhotel.com | LESCAPE | LES |
+| 7 | 그래비티 조선 서울 판교 | grp.josunhotel.com | GRP | GVP |
+| 8 | 포포인츠 서울역 | josunhotel.com/hotel/fpbsSeoul.do | FPBSS | FPS |
+| 9 | 포포인츠 서울 명동 | josunhotel.com/hotel/fpbsMyeongdong.do | FPBSM | FPM |
+| - | 전사 공통 | josunhotel.com | JOSUN HOTEL | JHR |
+| 10 | 파라스파라 | paraspara.co.kr | - | - |
+| 11 | 코랄로 바이 조선 | coralloyangyang.com | CBJ | YYH |
+
+---
+
+## 5. Meta / Kakao Pixel Event Mapping
+
+### Meta (Facebook) Pixel
+
+| User Action | Event Name | Pixel Code | GTM Tag Name |
+|-------------|-----------|------------|--------------|
+| 회원가입 완료 | 등록완료 | CompleteRegistration | Marketing - meta pixel - join_complete |
+| 이벤트 자세히 보기 | 콘텐츠 조회 | ViewContent | Marketing - meta Pixel - package detail |
+| 관심상품 담기 | 위시리스트에 추가 | AddToWishlist | Marketing - meta Pixel - bookmark |
+| 룸/패키지 예약 클릭 | 예약 | Schedule | Marketing - mata Pixel - bookmark |
+| 잠재고객 | 잠재고객 | Lead | (not configured) |
+
+### Kakao Pixel
+
+| User Action | Event Name | Event Code | GTM Tag Name |
+|-------------|-----------|------------|--------------|
+| 회원가입 완료 | 회원가입 | CompleteRegistration | Marketing - Kakao Pixel - join member complete |
+| 이벤트 자세히 보기 | 콘텐츠/상품 조회 | ViewContent | Marketing - Kakao Pixel - package detail |
+| 관심상품 담기 | 관심상품추가 | AddToWishList | Marketing - Kakao Pixel - bookmark |
+| 룸/패키지 예약 클릭 | 구매 | Purchase | Marketing - Kakao Pixel - click booking |
+| 잠재고객 (멤버십) | 잠재고객 | Participation - Consulting | Marketing - Kakao Pixel - button - membership_detail_view |
+| 잠재고객 (매스프로모션) | 잠재고객 | Participation - PreBooking | Marketing - Kakao pixel - button - massPromotion_detail |
+
+---
+
+## 6. Custom Channel Grouping (JHR)
+
+| Order | Channel | Custom Rules |
+|-------|---------|-------------|
+| 1 | Direct | (default) |
+| 2 | Cross-network | (default) |
+| 3 | Paid Shopping | (default) |
+| 4 | Paid Search | (default) |
+| 5 | Paid Social | + kakao / sms |
+| 6 | Paid Video | (default) |
+| 7 | Paid Other | (default) |
+| 8 | Display | (default) |
+| 9 | Map Search | place.map.kakao.com, m.place.naver.com, pcmap.place.naver.com, map.kakao.com |
+| 10 | Organic Shopping | (default) |
+| 11 | Organic Social | (default) |
+| 12 | Organic Video | (default) |
+| 13 | Organic Search | (default) |
+| 14 | Email | (default) |
+| 15 | Affiliates | + event.ssg.com, marriott.com, blossom.shinsegae.com |
+| 16 | Referral | (default) |
+| 17-19 | Audio / SMS / Mobile Push | (default) |
+| - | Unassigned | hotelQR / QRcoupon |
+
+---
+
+## 7. eCommerce Product Categories
+
+| Category | Description |
+|----------|-------------|
+| ROOM ONLY | 객실 상품만 제공 |
+| 멤버십 전용 | CJM 회원 전용 상품 |
+| 선결제 | 선결제 상품 (현재 미등록) |
+| 얼리버드 | 조기 예약 상품 |
+| 조식 | 조식 포함 패키지 |
+| 패키지 | 프로모션 오퍼 포함 패키지 |
+
+---
+
+## 8. Event Catalog (173 events)
+
+### Booking Process Events
+| Event Name | Description |
+|------------|-------------|
+| room_search | Room search initiated |
+| room_search_home | Room search from homepage |
+| room_tab_room_only | Room only tab selected |
+| room_tab_package | Package tab selected |
+| room_tab_members_only | Members only tab selected |
+| room_booking_step4 | Booking step 4 (confirmation) |
+| room_booking_promo | Promo code applied |
+| book_room | Room booking completed |
+| begin_checkout | Checkout started |
+| purchase | Purchase completed |
+| refund | Refund processed |
+
+### Dining Events
+| Event Name | Description |
+|------------|-------------|
+| dining_booking_start | Dining booking initiated |
+| dining_hotel_select | Hotel selected for dining |
+| dining_restaurant_select | Restaurant selected |
+| dining_step0_view ~ dining_step4_view | Dining booking steps |
+| dining_book | Dining reservation completed |
+| dining_menu_view_click | Menu viewed |
+| dining_search_home | Dining search from home |
+
+### Package & Event Events
+| Event Name | Description |
+|------------|-------------|
+| package_list_view | Package listing viewed |
+| event_list_view | Event listing viewed |
+| event_see_detail | Event detail clicked |
+| theme_pkg_detail | Theme package detail clicked |
+| pageview_theme_pkg | Theme package page viewed |
+| bookmark_promotion | Package/event bookmarked |
+| event_share | Event shared (Kakao/email/SMS/URL) |
+| massPromotion_detail | Mass promotion detail viewed |
+
+### Membership Events
+| Event Name | Description |
+|------------|-------------|
+| memberED2_list_view | Membership list viewed |
+| memberED2_join | Membership join started |
+| memberED2_detail_{TIER} | Tier detail viewed (BLACK/GOLD/PLATINUM/PREMIER/GRANDJOSUN) |
+| memberED2_detail_share | Membership shared |
+| memberED2_inquiry | Membership inquiry |
+
+### Navigation & Site Events
+| Event Name | Description |
+|------------|-------------|
+| GNB_all_menu | All menu opened |
+| GNB_sub_menu_click | Sub menu clicked |
+| main_select_hotel | Hotel selected from main |
+| main_room_booking | Room booking from main |
+| main_dining_booking | Dining booking from main |
+| hotel_layer_view | Hotel info layer viewed |
+| login_click | Login clicked |
+| join_click | Join clicked |
+| lang_change | Language changed |
+
+### E-commerce Events (GA4 Standard)
+| Event Name | Description |
+|------------|-------------|
+| view_item_list | Item list viewed |
+| view_item | Item detail viewed |
+| add_to_cart | Added to cart |
+| add_to_wishlist | Added to wishlist |
+| remove_from_wishlist | Removed from wishlist |
+| begin_checkout | Checkout started |
+| purchase | Purchase completed |
+| refund | Refund |

custom-skills/61-gtm-editor/code/SKILL.md

@@ -0,0 +1,294 @@
+---
+name: gtm-editor
+description: >
+  GTM implementation toolkit. Creates, updates, and modifies GTM tags, triggers,
+  variables via API. Generates Custom HTML with ES5 compliance. Handles workspace
+  lifecycle, DOM analysis for trigger design, and dataLayer code generation.
+  Triggers on "create GTM tag", "generate dataLayer", "modify trigger", "update variable",
+  "inject tracking code", "write custom HTML", "manage GTM", "design tags",
+  "create conversion tag", "set up tracking".
+  NOT for auditing (use gtm-audit) or validation/QA (use gtm-validator).
+---
+
+# GTM Editor Skill
+
+Create, modify, and deploy GTM configurations via API. Generates ES5-compliant Custom HTML tags.
+
+## Available Tools
+
+### GTM Container Management (DTM Agent MCP)
+- `dtm_status` — Check auth and active account/container
+- `dtm_set_account` / `dtm_set_container` — Switch context
+- `dtm_list_tags` / `dtm_get_tag` / `dtm_create_tag` / `dtm_update_tag` / `dtm_delete_tag`
+- `dtm_list_triggers` / `dtm_get_trigger` / `dtm_create_trigger` / `dtm_delete_trigger`
+- `dtm_list_variables` / `dtm_get_variable` / `dtm_create_variable` / `dtm_delete_variable`
+- `dtm_list_folders` / `dtm_list_workspaces` / `dtm_get_workspace_status`
+- `dtm_list_versions` / `dtm_get_live_version` / `dtm_create_version`
+
+### Browser Analysis (Chrome DevTools MCP)
+- `navigate_page` — Load page for DOM analysis
+- `evaluate_script` — Inspect forms, buttons, links, CSS selectors
+- `take_snapshot` — Get page structure for trigger design
+- `list_network_requests` — Verify tags fire after changes
+
+### Reporting (Notion MCP)
+- Write implementation plans and tag configurations to Notion
+
+## Tagging Workflow: dataLayer First (MANDATORY)
+
+**Always push complexity into the dataLayer, not GTM triggers.**
+
+### Step 1: Design the dataLayer push FIRST
+
+Before creating any GTM configuration, design the `dataLayer.push()` that the website should implement. Present this to the user as a code snippet matching their tech stack:
+
+**For vanilla JS / static HTML (ES5):**
+```javascript
+window.dataLayer = window.dataLayer || [];
+window.dataLayer.push({
+  'event': 'generate_lead',
+  'lead_type': document.getElementById('requestType').value,
+  'form_id': 'contact-form'
+});
+```
+
+**For React / Next.js / TypeScript:**
+```typescript
+declare global { interface Window { dataLayer: Record<string, any>[]; } }
+
+window.dataLayer = window.dataLayer || [];
+window.dataLayer.push({
+  event: 'generate_lead',
+  lead_type: selectedType,
+  form_id: 'contact-form',
+});
+```
+
+**For Vue:**
+```javascript
+window.dataLayer?.push({
+  event: 'generate_lead',
+  lead_type: this.selectedType,
+  form_id: 'contact-form',
+});
+```
+
+**For PHP / WordPress:**
+```php
+add_action('wp_footer', function() { ?>
+<script>
+document.getElementById('contact-form').addEventListener('submit', function() {
+  window.dataLayer = window.dataLayer || [];
+  window.dataLayer.push({
+    'event': 'generate_lead',
+    'lead_type': document.getElementById('requestType').value
+  });
+});
+</script>
+<?php });
+```
+
+**ASK the user:** "Here's the dataLayer code for your developers. Can they add this to the page? What's your tech stack?"
+
+### Step 2: Create simple GTM config
+
+Once dataLayer push is agreed:
+- **Trigger:** Custom Event `{{_event}}` equals `generate_lead` (simple, robust)
+- **Variables:** DataLayer Variable for each parameter (e.g., `dlv - lead_type`)
+- **Tag:** GA4 Event with `measurementIdOverride` + DLV parameters
+
+### Step 3: cHTML fallback (LAST RESORT)
+
+Only if user confirms they CANNOT modify the website code:
+1. Create a Custom HTML tag that listens for DOM events
+2. The cHTML pushes to dataLayer internally
+3. A Custom Event trigger picks it up (same clean pattern)
+
+**All cHTML must be ES5-compatible** (see ES5 section below).
+
+### Decision Tree
+```
+Track user action?
+  ├─ Can devs add dataLayer.push()? → YES → Simple CE trigger ✅
+  ├─ Can't modify code, element has ID? → Use Click ID trigger ✅
+  ├─ No ID? → Ask user to add one first
+  └─ Nothing possible? → cHTML + CE trigger (last resort)
+```
+
+---
+
+## Core Capabilities
+
+### 1. Tag Creation via GTM API
+
+Create tags directly in GTM — no manual pasting. The API handles workspace lifecycle automatically (auto-creates new workspace if current one is published).
+
+**GA4 Event Tags:**
+```
+GA4 event tags use type "gaawe" with:
+  - eventName: the GA4 event name (snake_case)
+  - measurementIdOverride: {{GA4 Measurement ID variable}} (NOT measurementId)
+  - eventParameters: list of name/value maps
+```
+
+**CRITICAL: measurementIdOverride, NOT measurementId**
+GA4 event tags inherit from config — use `measurementIdOverride` to reference the measurement ID variable. The API rejects `measurementId`.
+
+### 2. Trigger Design from DOM Analysis
+
+Analyze page DOM to design precise triggers:
+
+```javascript
+// Extract forms
+(function(){var forms=document.querySelectorAll('form');return JSON.stringify(Array.from(forms).map(function(f){return{id:f.id,action:f.action,fields:Array.from(f.querySelectorAll('input,textarea,select')).map(function(el){return{name:el.name,type:el.type,id:el.id}})}}));})()
+
+// Extract CTAs and buttons
+(function(){return JSON.stringify(Array.from(document.querySelectorAll('a[class*="btn"],button,[role="button"]')).map(function(el){return{text:(el.textContent||'').trim().substring(0,50),href:el.href||'',classes:el.className,id:el.id}}));})()
+```
+
+**Trigger types:**
+| Type | Use For | Key Parameter |
+|------|---------|---------------|
+| `linkClick` | `<a>` elements | `autoEventFilter` with CSS selector |
+| `click` | Any element | `filter` on Click ID/Classes |
+| `formSubmission` | Form submit | `filter` on Form ID |
+| `customEvent` | dataLayer events | `custom_event_filter` on `{{_event}}` |
+| `scrollDepth` | Scroll tracking | `verticalThresholdsPercent` |
+| `timer` | Time on page | `interval`, `limit` |
+| `domReady` | DOM loaded | No filter needed |
+
+### 3. Custom HTML Generation (ES5 MANDATORY)
+
+GTM Custom HTML uses a JavaScript compiler that does NOT support ES2020+.
+
+**FORBIDDEN:**
+```javascript
+// NO: optional chaining, arrow functions, const/let, template literals,
+//     destructuring, spread, async/await
+```
+
+**REQUIRED:**
+```javascript
+// YES: var, function(){}, string concatenation, explicit property access
+(function() {
+  var form = document.getElementById('contact-form');
+  if (!form) return;
+  form.addEventListener('submit', function() {
+    window.dataLayer = window.dataLayer || [];
+    window.dataLayer.push({
+      'event': 'generate_lead',
+      'lead_type': form.querySelector('#requestType').value
+    });
+  });
+})();
+```
+
+### 4. Workspace Lifecycle Management
+
+GTM workspaces become **read-only after publishing**. The DTM Agent auto-handles this:
+- If create/update fails with "Workspace is already submitted"
+- Auto-creates a new workspace
+- Retries the operation
+- Caches the workspace ID for subsequent calls
+
+**You don't need to manage workspaces manually.** Just call `dtm_create_tag` etc. and it works.
+
+### 5. DataLayer Code Generation
+
+Generate dataLayer push code for common tracking scenarios:
+
+**E-commerce:**
+```javascript
+// purchase event
+window.dataLayer = window.dataLayer || [];
+window.dataLayer.push({ ecommerce: null }); // Clear previous
+window.dataLayer.push({
+  'event': 'purchase',
+  'ecommerce': {
+    'transaction_id': /* order ID */,
+    'currency': 'KRW',
+    'value': /* total */,
+    'items': [{ item_id: '', item_name: '', price: 0, quantity: 1 }]
+  }
+});
+```
+
+**Forms/Leads:**
+```javascript
+window.dataLayer.push({
+  'event': 'generate_lead',
+  'lead_type': /* form type */,
+  'form_id': /* form element ID */
+});
+```
+
+## Korean Market Patterns
+
+| Context | Pattern |
+|---------|---------|
+| Currency | KRW (no decimals) |
+| Payment buttons | 장바구니, 결제하기, 주문하기, 문의하기 |
+| Payment methods | 카카오페이, 네이버페이, 토스, 신용카드 |
+| Platforms | Kakao Pixel (`track.kakao.com`), Naver Analytics (`wcs.naver.net`) |
+
+## Supported Tag Types
+
+| GTM Type | Name | Platform |
+|----------|------|----------|
+| `googtag` | Google Tag | GA4 config |
+| `gaawe` | GA4 Event | GA4 events |
+| `gclidw` | Conversion Linker | Google Ads |
+| `awct` | Ads Conversion | Google Ads |
+| `html` | Custom HTML | Any (Meta, PostHog, Kakao, etc.) |
+| `cvt_MQDKZ` | Clarity | Microsoft Clarity |
+| `cvt_WF3R3` | Amplitude | Amplitude |
+
+## FB Conversions API Integration
+
+When creating tags that should trigger FB CAPI:
+1. Check existing FBEventName mapping table (Regex Table variable)
+2. If your custom event isn't mapped, add a new rule: `event_name → FB_Standard_Event`
+3. Key mappings: `generate_lead → Lead`, `purchase → Purchase`, `page_view → PageView`
+
+## Workflow
+
+1. **Analyze**: Use Chrome DevTools to inspect the page (or receive from gtm-audit Mode D)
+2. **Design**: Determine events, triggers, variables needed
+3. **Create**: Use DTM Agent MCP tools to create in GTM
+4. **Verify**: Hand off to gtm-validator for QA
+5. **Document**: Write implementation details to Notion
+
+## Trigger Design: IDs First (MANDATORY)
+
+**Always prefer element `id` over CSS selectors.** IDs survive redesigns; CSS selectors break.
+
+**Before creating ANY click/form trigger:**
+1. Check if the target element has an `id` attribute via Chrome DevTools `evaluate_script`
+2. **If it has an ID** → use `Click ID` or `Form ID` filter
+3. **If it does NOT have an ID** → **ASK the user** before falling back to CSS:
+   > "This element doesn't have an ID. Can you add one to the website/app code?
+   > Suggested: `id="[section]-[element]-[action]"` e.g., `id="hero-btn-consult"`"
+4. Only use CSS selectors when the user explicitly confirms they cannot modify the HTML
+
+**Priority order:**
+1. Element ID (`Click ID equals "hero-btn-consult"`)
+2. Data attribute (`Click Element matches CSS [data-track="consult"]`)
+3. Form ID (`Form ID equals "contact-form"`)
+4. CSS selector (last resort — document which selectors are used)
+
+**Suggested ID naming:** `[section]-[element]-[action]`
+- Navigation: `nav-about`, `nav-services`, `nav-insights`
+- CTAs: `hero-btn-consult`, `cta-btn-booking`
+- Forms: `contact-form`, `newsletter-form`
+- Footer: `footer-social-linkedin`, `footer-email`
+
+## Rules
+
+- Always use `dtm_status` first to verify auth and active container
+- Always use `measurementIdOverride` for GA4 event tags (NOT `measurementId`)
+- **Always prefer element IDs for triggers — ask user to add IDs before using CSS selectors**
+- All Custom HTML must be ES5-compatible
+- Use `--dry-run` conceptually — verify trigger selectors via Chrome DevTools before creating
+- Rate limit: space API calls 1 second apart in batch operations
+- Never delete tags without explicit user confirmation — move to Archive folder instead
+- After creating tags, suggest user run gtm-validator to verify

custom-skills/61-gtm-manager/code/docs/common_issues.md

@@ -196,6 +196,121 @@ dataLayer.push({
 
 ---
 
+## Content Grouping Issues (RegEx Table Variables)
+
+### How Content Grouping Works in GTM
+
+Content grouping uses **RegEx Table** variables to categorize pages by URL/path patterns.
+The variable takes an input (typically `{{Page Path}}` or `{{Page URL}}`), tests it against
+an ordered list of regex patterns, and returns the first matching output value.
+If no pattern matches, it falls to the **Default Value** (usually "Other").
+
+**Key settings:**
+- **Full Matches Only**: OFF — partial regex match is sufficient
+- **Capture Groups and Replace**: OFF — output is the literal value, not a regex replacement
+- **Ignore Case**: ON — case-insensitive matching
+
+### New Page Paths Fall Through to "Other"
+
+**Symptoms**: New sections (campaigns, special events, landing pages) show as "Other" in GA4 content group reports.
+
+**Root cause**: The RegEx Table was built for the site's original URL structure. New paths like `/specialEvent/`, `/campaign/`, `/timesale/` don't match any existing pattern.
+
+**Example**: JHR site has `/specialEvent/landersshoppingfesta2026/teaser.do` but only `/package/` and `/event/` are in the regex table, not `/specialEvent/`.
+
+**Fix**: Add regex rule for the new path pattern. Place it BEFORE the default.
+
+**Gotcha — two variables to update**: Sites often have parallel content group variables:
+1. **Page Path based** (e.g., `(\/m)?\/specialEvent\/(.*)`) — for internal reports
+2. **Page URL based** (e.g., full URL with domain regex) — for cross-domain or subdomain tracking
+
+Both must be updated or they'll produce inconsistent groupings.
+
+### RegEx Pattern Conventions (JHR Example)
+
+Page Path patterns follow this structure:
+```
+(\/m)?\/section\/(.*)    →  Korean Category Label
+```
+- `(\/m)?` — optional mobile path prefix
+- `\/section\/` — the URL path segment to match
+- `(.*)` — match anything after
+
+Page URL patterns include domain matching:
+```
+^https\:\/\/(www|app|jpg|gjb|gjj|grp|\.)?josunhotel\.com(\/m)?\/section\/(.*)
+```
+- Multi-subdomain support via alternation group
+- Same `(\/m)?` mobile prefix handling
+
+### Content Group Categories (Hospitality Reference)
+
+| Pattern | Category (KR) | Category (EN) |
+|---------|---------------|---------------|
+| `/intro.do`, `/main.do` | 메인페이지 | Main Page |
+| `/about/`, `/press/` | 기업 소개 | Corporate Info |
+| `/hotel/` | 호텔 소개 | Hotel Info |
+| `/rooms/` | 객실 소개 | Room Info |
+| `/dining/` | 다이닝 이용 | Dining |
+| `/facilities/`, `/meeting/`, `/fitness/` | 부대시설 소개 | Facilities |
+| `/package/`, `/event/` | 이벤트 \| 패키지 조회 | Events & Packages |
+| `/specialEvent/` | 캠페인 \| 프로모션 | Campaign & Promotion |
+| `/timesale/`, `/campaign/` *(placeholder — not actual paths yet, replace when specific paths are registered)* | 캠페인 \| 프로모션 | Campaign & Promotion |
+| `/activity/` | 액티비티 소개 | Activities |
+| `/step[0-4]` | 룸, 패키지 예약 프로세스 | Booking Process |
+| `/resve/dining/` | 다이닝 예약 프로세스 | Dining Booking |
+| `/membership/` | 멤버쉽 | Membership |
+| `/mypage/`, `/login/`, `/join/` | 웹회원 관련 | Member Portal |
+| `/retail/`, `/product/`, `/office/` | 리테일 관련 | Retail |
+| `/voc/`, `/customer/` | 고객지원 | Customer Support |
+| `/policy/` | 웹사이트 정책 | Website Policy |
+| `/upload_file/event/html/` | 캠페인 \| 프로모션 | Campaign & Promotion |
+| Default | Other | Other |
+
+### Two Content Group Variables — Old vs New (JHR)
+
+The JHR container has two content group variables for menu categories:
+
+| | **Contents Group 2** (ID:1234) | **Contents Group new** (ID:1826) |
+|---|---|---|
+| Input | `{{Page Path}}` | `{{Page URL}}` |
+| Rules | 20 | 24 (replacement) |
+| Domain matching | No — path only | Yes — full URL with subdomain alternation |
+| Subdomain coverage | N/A | `www\|app\|jpg\|gjb\|gjj\|grp\|les\|\.` |
+| Cross-domain | No | Yes — booking, josuntns, lounge subdomains |
+| Mobile path | `(\/m)?` prefix | `(\/m)?` prefix within URL pattern |
+
+**"Contents Group new" (ID:1826) is the replacement** — it handles subdomains (booking, T&S, lounge, les) that the old path-based variable cannot distinguish. When auditing, check which variable is referenced in the GA4 config tag — the newer one should be used.
+
+**Gotcha — adding new subdomains**: When a new hotel brand subdomain launches (e.g., `les.josunhotel.com`), the subdomain alternation group `(www|app|...|les|\.)` in ALL main-domain rules must be updated. This affects 14+ rules in the URL-based variable.
+
+### Gotcha — Subdomain Regex Dot Separator
+
+**Bug**: `(www|app|jpg|les|\.)?josunhotel\.com` does NOT match `www.josunhotel.com`.
+
+The `\.` inside the alternation group matches a literal dot OR `www` matches `www`, but neither consumes the `.` between the subdomain and `josunhotel`. The regex engine sees `www` then expects `josunhotel` but finds `.josunhotel`.
+
+**Fix**: Move the dot outside the group as an optional separator:
+```
+BROKEN: (www|app|jpg|gjb|gjj|grp|les|\.)?josunhotel\.com
+FIXED:  (www|app|jpg|gjb|gjj|grp|les)?\.?josunhotel\.com
+```
+
+This correctly matches: `www.josunhotel.com`, `les.josunhotel.com`, `josunhotel.com` (bare), `app.josunhotel.com`.
+
+**Note**: GTM's "Full Matches Only = OFF" means `re.search` (partial match) is used, which may accidentally match the broken pattern on some URLs. But strict `re.match` or JavaScript `pattern.test()` will fail. Always test with the full URL in JavaScript console.
+
+### Audit Checklist for Content Grouping
+
+- [ ] Run `dtm var info <var_id>` to dump the full regex table
+- [ ] Check if new site sections have matching patterns
+- [ ] Verify both Path and URL variables are in sync
+- [ ] Check GA4 config tag references the correct variable
+- [ ] Test in GTM Preview: navigate to new page, check variable value
+- [ ] After update, verify in GA4 Realtime > Content Group report
+
+---
+
 ## Performance Issues
 
 ### Tags Slowing Page Load

custom-skills/61-gtm-manager/code/docs/jhr-ga4-tagging-reference.md

@@ -0,0 +1,298 @@
+# JHR GA4 Tagging Reference
+
+Source: [JHR - User Behaviour, Event Planning & GA setup](https://docs.google.com/spreadsheets/d/1rhzYApbZ4wbe1gE-E43E-mlRdLl_etkIOZnqs1g9X1U)
+
+Container: GTM-NP6NJMP (JHR Website - 통합)
+
+---
+
+## 1. Tag Naming Convention
+
+Format: `{Platform} {TriggerElement} - {Purpose} - {EventName}`
+
+### Platform Categories
+
+| Platform | Usage |
+|----------|-------|
+| GA4 | Google Analytics 4 events |
+| Google Ads | Conversion tracking |
+| Meta | Facebook/Instagram pixel |
+| Kakao | Kakao pixel/moment |
+| Marketing | Cross-platform marketing tags |
+| Analytics | Analytics configuration tags |
+| Site | Site-specific utility tags |
+| SEO | SEO-related tags |
+| Test | Testing/debug tags |
+| {{Campaign Name}} | Campaign-specific tags (e.g., "LandersFesta") |
+
+### Trigger Elements (what triggers the tag)
+
+| Element | Description |
+|---------|-------------|
+| pageview | Page load / virtual pageview |
+| click | Generic click |
+| link | Link click |
+| button | Button click |
+| tab | Tab selection |
+| form | Form submission |
+| layer | Layer/modal/popup view |
+| popup | Popup interaction |
+| banner | Banner click/impression |
+| dropdown | Dropdown selection |
+| radio | Radio button selection |
+| checkbox | Checkbox toggle |
+| ajax | AJAX request complete |
+| dataLayer | DataLayer push event |
+
+### Tag Purposes (page/feature area)
+
+| Purpose | Area |
+|---------|------|
+| booking | Room/package reservation process |
+| dining | Dining reservation process |
+| membership | Club Josun membership |
+| package | Package/event listing & detail |
+| theme | Theme package pages |
+| campaign | Campaign/promotion pages |
+| event | Event pages |
+| timesale | Time-limited sale pages |
+| survey | Survey/feedback |
+| ecommerce | E-commerce tracking |
+| SEO | SEO schema/config |
+| site | Site-wide interactions |
+| config | Configuration/settings |
+| ux | UX tracking |
+| test | Testing |
+
+### Examples
+
+```
+GA4 pageview - booking - room_booking_step1
+GA4 button - theme - theme_pkg_detail
+GA4 click - campaign - kakao_channel_add
+Kakao banner - timesale - {{Event Name}}
+Meta form - event - {{Event Name}}
+Marketing - meta pixel - join_complete
+Marketing - Kakao Pixel - package detail
+```
+
+---
+
+## 2. Inherited Settings Variables
+
+Tags inherit common parameters through shared settings variables.
+This avoids duplicating parameters across hundreds of tags.
+
+### GA4 Configuration Setting (shared across ALL GA4 tags)
+
+| Parameter | Variable | Description |
+|-----------|----------|-------------|
+| login_status | {{cjs - login status Variable}} | Login state |
+| user_lang | locale={{cjs - page language Variable}} | Page language |
+| contents_group_hotel | {{Contents Group 1 - Hotel Site}} | Hotel brand grouping |
+| contents_group_menu | {{Contents Group new - Menu Categories}} | Page section grouping |
+| naver_query | {{URL referrer - naver query}} | Naver search query |
+| naver_oquery | {{URL referrer - naver oquery}} | Naver original query |
+
+### GA4 Event Settings (added to event tags)
+
+| Parameter | Variable |
+|-----------|----------|
+| page_path | {{Page Path}} |
+| login_status | {{cjs - login status Variable}} |
+| user_lang | {{cjs - page language Variable}} |
+
+### GA4 eCommerce Settings (added to ecommerce tags)
+
+| Parameter | Variable |
+|-----------|----------|
+| pkg_name | {{dlv - eCommerce - item_name}} |
+| pkg_hotel | {{dlv - eCommerce - item_brand}} |
+| pkg_price | {{dlv - eCommerce - price}} |
+| pkg_room_type | {{dlv - eCommerce - item_variant}} |
+| pkg_id | {{dlv - eCommerce - item_id}} |
+| page_path | {{Page Path}} |
+
+### GA4 Promotion Settings (added to package/event detail tags)
+
+| Parameter | Variable |
+|-----------|----------|
+| page_path | {{Page Path}} |
+| login_status | {{cjs - login status Variable}} |
+| user_lang | {{cjs - page language Variable}} |
+| packageSn | {{URL query - packageSn Variable}} |
+| themeSn | {{URL query - themeSn Variable}} |
+| eventSn | {{URL query - eventSn Variable}} |
+
+---
+
+## 3. Standard Parameter Keys
+
+| Parameter Name | Allowed Values / Variable |
+|----------------|--------------------------|
+| event_type | click |
+| ui | GNB, modal, button, tab, link, banner, footer |
+| page_path | {{Page Path}} |
+| login_status | (from cjs variable) |
+| user_lang | (from cjs variable) |
+| pkg_name | (package/event title) |
+| click_text | (clicked element text) |
+| click_url | (clicked element URL) |
+
+---
+
+## 4. Property Codes
+
+| # | Hotel Name | URL | Website Code | Report Code |
+|---|-----------|-----|-------------|-------------|
+| 1 | 조선 팰리스 | jpg.josunhotel.com | JPY | JPG |
+| 2 | 웨스틴 조선 서울 | josunhotel.com/hotel/westinSeoul.do | TWC | WJS |
+| 3 | 웨스틴 조선 부산 | josunhotel.com/hotel/westinBusan.do | TWCB | WJB |
+| 4 | 그랜드 조선 부산 | gjb.josunhotel.com | GJB | GJB |
+| 5 | 그랜드 조선 제주 | gjj.josunhotel.com | GJJ | GJJ |
+| 6 | 레스케이프 호텔 | les.josunhotel.com | LESCAPE | LES |
+| 7 | 그래비티 조선 서울 판교 | grp.josunhotel.com | GRP | GVP |
+| 8 | 포포인츠 서울역 | josunhotel.com/hotel/fpbsSeoul.do | FPBSS | FPS |
+| 9 | 포포인츠 서울 명동 | josunhotel.com/hotel/fpbsMyeongdong.do | FPBSM | FPM |
+| - | 전사 공통 | josunhotel.com | JOSUN HOTEL | JHR |
+| 10 | 파라스파라 | paraspara.co.kr | - | - |
+| 11 | 코랄로 바이 조선 | coralloyangyang.com | CBJ | YYH |
+
+---
+
+## 5. Meta / Kakao Pixel Event Mapping
+
+### Meta (Facebook) Pixel
+
+| User Action | Event Name | Pixel Code | GTM Tag Name |
+|-------------|-----------|------------|--------------|
+| 회원가입 완료 | 등록완료 | CompleteRegistration | Marketing - meta pixel - join_complete |
+| 이벤트 자세히 보기 | 콘텐츠 조회 | ViewContent | Marketing - meta Pixel - package detail |
+| 관심상품 담기 | 위시리스트에 추가 | AddToWishlist | Marketing - meta Pixel - bookmark |
+| 룸/패키지 예약 클릭 | 예약 | Schedule | Marketing - mata Pixel - bookmark |
+| 잠재고객 | 잠재고객 | Lead | (not configured) |
+
+### Kakao Pixel
+
+| User Action | Event Name | Event Code | GTM Tag Name |
+|-------------|-----------|------------|--------------|
+| 회원가입 완료 | 회원가입 | CompleteRegistration | Marketing - Kakao Pixel - join member complete |
+| 이벤트 자세히 보기 | 콘텐츠/상품 조회 | ViewContent | Marketing - Kakao Pixel - package detail |
+| 관심상품 담기 | 관심상품추가 | AddToWishList | Marketing - Kakao Pixel - bookmark |
+| 룸/패키지 예약 클릭 | 구매 | Purchase | Marketing - Kakao Pixel - click booking |
+| 잠재고객 (멤버십) | 잠재고객 | Participation - Consulting | Marketing - Kakao Pixel - button - membership_detail_view |
+| 잠재고객 (매스프로모션) | 잠재고객 | Participation - PreBooking | Marketing - Kakao pixel - button - massPromotion_detail |
+
+---
+
+## 6. Custom Channel Grouping (JHR)
+
+| Order | Channel | Custom Rules |
+|-------|---------|-------------|
+| 1 | Direct | (default) |
+| 2 | Cross-network | (default) |
+| 3 | Paid Shopping | (default) |
+| 4 | Paid Search | (default) |
+| 5 | Paid Social | + kakao / sms |
+| 6 | Paid Video | (default) |
+| 7 | Paid Other | (default) |
+| 8 | Display | (default) |
+| 9 | Map Search | place.map.kakao.com, m.place.naver.com, pcmap.place.naver.com, map.kakao.com |
+| 10 | Organic Shopping | (default) |
+| 11 | Organic Social | (default) |
+| 12 | Organic Video | (default) |
+| 13 | Organic Search | (default) |
+| 14 | Email | (default) |
+| 15 | Affiliates | + event.ssg.com, marriott.com, blossom.shinsegae.com |
+| 16 | Referral | (default) |
+| 17-19 | Audio / SMS / Mobile Push | (default) |
+| - | Unassigned | hotelQR / QRcoupon |
+
+---
+
+## 7. eCommerce Product Categories
+
+| Category | Description |
+|----------|-------------|
+| ROOM ONLY | 객실 상품만 제공 |
+| 멤버십 전용 | CJM 회원 전용 상품 |
+| 선결제 | 선결제 상품 (현재 미등록) |
+| 얼리버드 | 조기 예약 상품 |
+| 조식 | 조식 포함 패키지 |
+| 패키지 | 프로모션 오퍼 포함 패키지 |
+
+---
+
+## 8. Event Catalog (173 events)
+
+### Booking Process Events
+| Event Name | Description |
+|------------|-------------|
+| room_search | Room search initiated |
+| room_search_home | Room search from homepage |
+| room_tab_room_only | Room only tab selected |
+| room_tab_package | Package tab selected |
+| room_tab_members_only | Members only tab selected |
+| room_booking_step4 | Booking step 4 (confirmation) |
+| room_booking_promo | Promo code applied |
+| book_room | Room booking completed |
+| begin_checkout | Checkout started |
+| purchase | Purchase completed |
+| refund | Refund processed |
+
+### Dining Events
+| Event Name | Description |
+|------------|-------------|
+| dining_booking_start | Dining booking initiated |
+| dining_hotel_select | Hotel selected for dining |
+| dining_restaurant_select | Restaurant selected |
+| dining_step0_view ~ dining_step4_view | Dining booking steps |
+| dining_book | Dining reservation completed |
+| dining_menu_view_click | Menu viewed |
+| dining_search_home | Dining search from home |
+
+### Package & Event Events
+| Event Name | Description |
+|------------|-------------|
+| package_list_view | Package listing viewed |
+| event_list_view | Event listing viewed |
+| event_see_detail | Event detail clicked |
+| theme_pkg_detail | Theme package detail clicked |
+| pageview_theme_pkg | Theme package page viewed |
+| bookmark_promotion | Package/event bookmarked |
+| event_share | Event shared (Kakao/email/SMS/URL) |
+| massPromotion_detail | Mass promotion detail viewed |
+
+### Membership Events
+| Event Name | Description |
+|------------|-------------|
+| memberED2_list_view | Membership list viewed |
+| memberED2_join | Membership join started |
+| memberED2_detail_{TIER} | Tier detail viewed (BLACK/GOLD/PLATINUM/PREMIER/GRANDJOSUN) |
+| memberED2_detail_share | Membership shared |
+| memberED2_inquiry | Membership inquiry |
+
+### Navigation & Site Events
+| Event Name | Description |
+|------------|-------------|
+| GNB_all_menu | All menu opened |
+| GNB_sub_menu_click | Sub menu clicked |
+| main_select_hotel | Hotel selected from main |
+| main_room_booking | Room booking from main |
+| main_dining_booking | Dining booking from main |
+| hotel_layer_view | Hotel info layer viewed |
+| login_click | Login clicked |
+| join_click | Join clicked |
+| lang_change | Language changed |
+
+### E-commerce Events (GA4 Standard)
+| Event Name | Description |
+|------------|-------------|
+| view_item_list | Item list viewed |
+| view_item | Item detail viewed |
+| add_to_cart | Added to cart |
+| add_to_wishlist | Added to wishlist |
+| remove_from_wishlist | Removed from wishlist |
+| begin_checkout | Checkout started |
+| purchase | Purchase completed |
+| refund | Refund |

custom-skills/62-gtm-guardian/code/references/jhr-ga4-tagging-reference.md

@@ -0,0 +1,298 @@
+# JHR GA4 Tagging Reference
+
+Source: [JHR - User Behaviour, Event Planning & GA setup](https://docs.google.com/spreadsheets/d/1rhzYApbZ4wbe1gE-E43E-mlRdLl_etkIOZnqs1g9X1U)
+
+Container: GTM-NP6NJMP (JHR Website - 통합)
+
+---
+
+## 1. Tag Naming Convention
+
+Format: `{Platform} {TriggerElement} - {Purpose} - {EventName}`
+
+### Platform Categories
+
+| Platform | Usage |
+|----------|-------|
+| GA4 | Google Analytics 4 events |
+| Google Ads | Conversion tracking |
+| Meta | Facebook/Instagram pixel |
+| Kakao | Kakao pixel/moment |
+| Marketing | Cross-platform marketing tags |
+| Analytics | Analytics configuration tags |
+| Site | Site-specific utility tags |
+| SEO | SEO-related tags |
+| Test | Testing/debug tags |
+| {{Campaign Name}} | Campaign-specific tags (e.g., "LandersFesta") |
+
+### Trigger Elements (what triggers the tag)
+
+| Element | Description |
+|---------|-------------|
+| pageview | Page load / virtual pageview |
+| click | Generic click |
+| link | Link click |
+| button | Button click |
+| tab | Tab selection |
+| form | Form submission |
+| layer | Layer/modal/popup view |
+| popup | Popup interaction |
+| banner | Banner click/impression |
+| dropdown | Dropdown selection |
+| radio | Radio button selection |
+| checkbox | Checkbox toggle |
+| ajax | AJAX request complete |
+| dataLayer | DataLayer push event |
+
+### Tag Purposes (page/feature area)
+
+| Purpose | Area |
+|---------|------|
+| booking | Room/package reservation process |
+| dining | Dining reservation process |
+| membership | Club Josun membership |
+| package | Package/event listing & detail |
+| theme | Theme package pages |
+| campaign | Campaign/promotion pages |
+| event | Event pages |
+| timesale | Time-limited sale pages |
+| survey | Survey/feedback |
+| ecommerce | E-commerce tracking |
+| SEO | SEO schema/config |
+| site | Site-wide interactions |
+| config | Configuration/settings |
+| ux | UX tracking |
+| test | Testing |
+
+### Examples
+
+```
+GA4 pageview - booking - room_booking_step1
+GA4 button - theme - theme_pkg_detail
+GA4 click - campaign - kakao_channel_add
+Kakao banner - timesale - {{Event Name}}
+Meta form - event - {{Event Name}}
+Marketing - meta pixel - join_complete
+Marketing - Kakao Pixel - package detail
+```
+
+---
+
+## 2. Inherited Settings Variables
+
+Tags inherit common parameters through shared settings variables.
+This avoids duplicating parameters across hundreds of tags.
+
+### GA4 Configuration Setting (shared across ALL GA4 tags)
+
+| Parameter | Variable | Description |
+|-----------|----------|-------------|
+| login_status | {{cjs - login status Variable}} | Login state |
+| user_lang | locale={{cjs - page language Variable}} | Page language |
+| contents_group_hotel | {{Contents Group 1 - Hotel Site}} | Hotel brand grouping |
+| contents_group_menu | {{Contents Group new - Menu Categories}} | Page section grouping |
+| naver_query | {{URL referrer - naver query}} | Naver search query |
+| naver_oquery | {{URL referrer - naver oquery}} | Naver original query |
+
+### GA4 Event Settings (added to event tags)
+
+| Parameter | Variable |
+|-----------|----------|
+| page_path | {{Page Path}} |
+| login_status | {{cjs - login status Variable}} |
+| user_lang | {{cjs - page language Variable}} |
+
+### GA4 eCommerce Settings (added to ecommerce tags)
+
+| Parameter | Variable |
+|-----------|----------|
+| pkg_name | {{dlv - eCommerce - item_name}} |
+| pkg_hotel | {{dlv - eCommerce - item_brand}} |
+| pkg_price | {{dlv - eCommerce - price}} |
+| pkg_room_type | {{dlv - eCommerce - item_variant}} |
+| pkg_id | {{dlv - eCommerce - item_id}} |
+| page_path | {{Page Path}} |
+
+### GA4 Promotion Settings (added to package/event detail tags)
+
+| Parameter | Variable |
+|-----------|----------|
+| page_path | {{Page Path}} |
+| login_status | {{cjs - login status Variable}} |
+| user_lang | {{cjs - page language Variable}} |
+| packageSn | {{URL query - packageSn Variable}} |
+| themeSn | {{URL query - themeSn Variable}} |
+| eventSn | {{URL query - eventSn Variable}} |
+
+---
+
+## 3. Standard Parameter Keys
+
+| Parameter Name | Allowed Values / Variable |
+|----------------|--------------------------|
+| event_type | click |
+| ui | GNB, modal, button, tab, link, banner, footer |
+| page_path | {{Page Path}} |
+| login_status | (from cjs variable) |
+| user_lang | (from cjs variable) |
+| pkg_name | (package/event title) |
+| click_text | (clicked element text) |
+| click_url | (clicked element URL) |
+
+---
+
+## 4. Property Codes
+
+| # | Hotel Name | URL | Website Code | Report Code |
+|---|-----------|-----|-------------|-------------|
+| 1 | 조선 팰리스 | jpg.josunhotel.com | JPY | JPG |
+| 2 | 웨스틴 조선 서울 | josunhotel.com/hotel/westinSeoul.do | TWC | WJS |
+| 3 | 웨스틴 조선 부산 | josunhotel.com/hotel/westinBusan.do | TWCB | WJB |
+| 4 | 그랜드 조선 부산 | gjb.josunhotel.com | GJB | GJB |
+| 5 | 그랜드 조선 제주 | gjj.josunhotel.com | GJJ | GJJ |
+| 6 | 레스케이프 호텔 | les.josunhotel.com | LESCAPE | LES |
+| 7 | 그래비티 조선 서울 판교 | grp.josunhotel.com | GRP | GVP |
+| 8 | 포포인츠 서울역 | josunhotel.com/hotel/fpbsSeoul.do | FPBSS | FPS |
+| 9 | 포포인츠 서울 명동 | josunhotel.com/hotel/fpbsMyeongdong.do | FPBSM | FPM |
+| - | 전사 공통 | josunhotel.com | JOSUN HOTEL | JHR |
+| 10 | 파라스파라 | paraspara.co.kr | - | - |
+| 11 | 코랄로 바이 조선 | coralloyangyang.com | CBJ | YYH |
+
+---
+
+## 5. Meta / Kakao Pixel Event Mapping
+
+### Meta (Facebook) Pixel
+
+| User Action | Event Name | Pixel Code | GTM Tag Name |
+|-------------|-----------|------------|--------------|
+| 회원가입 완료 | 등록완료 | CompleteRegistration | Marketing - meta pixel - join_complete |
+| 이벤트 자세히 보기 | 콘텐츠 조회 | ViewContent | Marketing - meta Pixel - package detail |
+| 관심상품 담기 | 위시리스트에 추가 | AddToWishlist | Marketing - meta Pixel - bookmark |
+| 룸/패키지 예약 클릭 | 예약 | Schedule | Marketing - mata Pixel - bookmark |
+| 잠재고객 | 잠재고객 | Lead | (not configured) |
+
+### Kakao Pixel
+
+| User Action | Event Name | Event Code | GTM Tag Name |
+|-------------|-----------|------------|--------------|
+| 회원가입 완료 | 회원가입 | CompleteRegistration | Marketing - Kakao Pixel - join member complete |
+| 이벤트 자세히 보기 | 콘텐츠/상품 조회 | ViewContent | Marketing - Kakao Pixel - package detail |
+| 관심상품 담기 | 관심상품추가 | AddToWishList | Marketing - Kakao Pixel - bookmark |
+| 룸/패키지 예약 클릭 | 구매 | Purchase | Marketing - Kakao Pixel - click booking |
+| 잠재고객 (멤버십) | 잠재고객 | Participation - Consulting | Marketing - Kakao Pixel - button - membership_detail_view |
+| 잠재고객 (매스프로모션) | 잠재고객 | Participation - PreBooking | Marketing - Kakao pixel - button - massPromotion_detail |
+
+---
+
+## 6. Custom Channel Grouping (JHR)
+
+| Order | Channel | Custom Rules |
+|-------|---------|-------------|
+| 1 | Direct | (default) |
+| 2 | Cross-network | (default) |
+| 3 | Paid Shopping | (default) |
+| 4 | Paid Search | (default) |
+| 5 | Paid Social | + kakao / sms |
+| 6 | Paid Video | (default) |
+| 7 | Paid Other | (default) |
+| 8 | Display | (default) |
+| 9 | Map Search | place.map.kakao.com, m.place.naver.com, pcmap.place.naver.com, map.kakao.com |
+| 10 | Organic Shopping | (default) |
+| 11 | Organic Social | (default) |
+| 12 | Organic Video | (default) |
+| 13 | Organic Search | (default) |
+| 14 | Email | (default) |
+| 15 | Affiliates | + event.ssg.com, marriott.com, blossom.shinsegae.com |
+| 16 | Referral | (default) |
+| 17-19 | Audio / SMS / Mobile Push | (default) |
+| - | Unassigned | hotelQR / QRcoupon |
+
+---
+
+## 7. eCommerce Product Categories
+
+| Category | Description |
+|----------|-------------|
+| ROOM ONLY | 객실 상품만 제공 |
+| 멤버십 전용 | CJM 회원 전용 상품 |
+| 선결제 | 선결제 상품 (현재 미등록) |
+| 얼리버드 | 조기 예약 상품 |
+| 조식 | 조식 포함 패키지 |
+| 패키지 | 프로모션 오퍼 포함 패키지 |
+
+---
+
+## 8. Event Catalog (173 events)
+
+### Booking Process Events
+| Event Name | Description |
+|------------|-------------|
+| room_search | Room search initiated |
+| room_search_home | Room search from homepage |
+| room_tab_room_only | Room only tab selected |
+| room_tab_package | Package tab selected |
+| room_tab_members_only | Members only tab selected |
+| room_booking_step4 | Booking step 4 (confirmation) |
+| room_booking_promo | Promo code applied |
+| book_room | Room booking completed |
+| begin_checkout | Checkout started |
+| purchase | Purchase completed |
+| refund | Refund processed |
+
+### Dining Events
+| Event Name | Description |
+|------------|-------------|
+| dining_booking_start | Dining booking initiated |
+| dining_hotel_select | Hotel selected for dining |
+| dining_restaurant_select | Restaurant selected |
+| dining_step0_view ~ dining_step4_view | Dining booking steps |
+| dining_book | Dining reservation completed |
+| dining_menu_view_click | Menu viewed |
+| dining_search_home | Dining search from home |
+
+### Package & Event Events
+| Event Name | Description |
+|------------|-------------|
+| package_list_view | Package listing viewed |
+| event_list_view | Event listing viewed |
+| event_see_detail | Event detail clicked |
+| theme_pkg_detail | Theme package detail clicked |
+| pageview_theme_pkg | Theme package page viewed |
+| bookmark_promotion | Package/event bookmarked |
+| event_share | Event shared (Kakao/email/SMS/URL) |
+| massPromotion_detail | Mass promotion detail viewed |
+
+### Membership Events
+| Event Name | Description |
+|------------|-------------|
+| memberED2_list_view | Membership list viewed |
+| memberED2_join | Membership join started |
+| memberED2_detail_{TIER} | Tier detail viewed (BLACK/GOLD/PLATINUM/PREMIER/GRANDJOSUN) |
+| memberED2_detail_share | Membership shared |
+| memberED2_inquiry | Membership inquiry |
+
+### Navigation & Site Events
+| Event Name | Description |
+|------------|-------------|
+| GNB_all_menu | All menu opened |
+| GNB_sub_menu_click | Sub menu clicked |
+| main_select_hotel | Hotel selected from main |
+| main_room_booking | Room booking from main |
+| main_dining_booking | Dining booking from main |
+| hotel_layer_view | Hotel info layer viewed |
+| login_click | Login clicked |
+| join_click | Join clicked |
+| lang_change | Language changed |
+
+### E-commerce Events (GA4 Standard)
+| Event Name | Description |
+|------------|-------------|
+| view_item_list | Item list viewed |
+| view_item | Item detail viewed |
+| add_to_cart | Added to cart |
+| add_to_wishlist | Added to wishlist |
+| remove_from_wishlist | Removed from wishlist |
+| begin_checkout | Checkout started |
+| purchase | Purchase completed |
+| refund | Refund |

custom-skills/62-gtm-validator/code/SKILL.md

@@ -0,0 +1,225 @@
+---
+name: gtm-validator
+description: >
+  GTM QA and validation toolkit. Verifies tags fire correctly on live pages,
+  tests trigger conditions against actual DOM, validates dataLayer schemas,
+  checks naming conventions, compares cross-platform events, and runs QA checklists.
+  Uses Chrome DevTools MCP for live page testing.
+  Triggers on "validate tags", "check triggers", "verify tracking", "QA GTM",
+  "test events", "debug GTM", "troubleshoot", "naming conventions",
+  "GTM question", "GTM best practice", "compare versions".
+  NOT for auditing (use gtm-audit) or creating/modifying (use gtm-editor).
+---
+
+# GTM Validator Skill
+
+Verify GTM implementations work correctly on live pages. Test triggers, validate dataLayer, check naming conventions.
+
+## Available Tools
+
+### Browser Testing (Chrome DevTools MCP)
+- `navigate_page` — Load page to test
+- `evaluate_script` — Check dataLayer state, test selectors, verify globals
+- `list_network_requests` — Verify tag firing after interactions
+- `click` / `hover` — Simulate user actions to trigger events
+- `list_console_messages` — Check for JS errors
+- `take_screenshot` — Document test results
+
+### GTM Container (DTM Agent MCP)
+- `dtm_status` — Check active container
+- `dtm_list_tags` / `dtm_get_tag` — Get tag configurations
+- `dtm_list_triggers` / `dtm_get_trigger` — Get trigger conditions
+- `dtm_list_variables` / `dtm_get_variable` — Get variable definitions
+- `dtm_list_versions` / `dtm_get_live_version` — Compare versions
+
+## Validation Modes
+
+### 1. Tag Firing Verification
+
+Test that specific tags fire on the correct pages and interactions.
+
+**Steps:**
+1. `dtm_list_tags` — get all active tags with their triggers
+2. `navigate_page` to target URL
+3. `list_network_requests` — capture initial tag firings
+4. For click triggers: `click` the element, then check `list_network_requests` again
+5. Compare: expected tags (from GTM config) vs actual network requests
+
+**Verification script for specific tag:**
+```javascript
+// Check if GA4 event fired
+(function(){
+  var dl = window.dataLayer || [];
+  var events = dl.filter(function(e){return e.event && e.event !== 'gtm.js' && e.event !== 'gtm.dom' && e.event !== 'gtm.load';});
+  return JSON.stringify(events.map(function(e){return {event: e.event, params: Object.keys(e).filter(function(k){return k !== 'event' && !k.startsWith('gtm.')})}}));
+})()
+```
+
+### 2. Trigger Condition Testing
+
+Verify trigger CSS selectors and conditions match the actual page DOM.
+
+**Steps:**
+1. `dtm_get_trigger` — get trigger filter/autoEventFilter
+2. Extract CSS selectors from trigger config
+3. `evaluate_script` — test if selectors match elements on page:
+
+```javascript
+// Test CSS selector
+(function(selector){
+  var els = document.querySelectorAll(selector);
+  return JSON.stringify({
+    selector: selector,
+    matchCount: els.length,
+    elements: Array.from(els).slice(0,5).map(function(el){
+      return {tag: el.tagName, id: el.id, classes: el.className, text: (el.textContent||'').trim().substring(0,30)};
+    })
+  });
+})('.hero a.btn')
+```
+
+4. If selector matches 0 elements → trigger will NEVER fire → **CRITICAL issue**
+5. If selector matches too many elements → trigger may fire incorrectly → **WARNING**
+
+### 3. DataLayer Schema Validation
+
+Verify dataLayer pushes contain required fields with correct types.
+
+**GA4 Recommended Event Schemas:**
+
+| Event | Required Fields |
+|-------|----------------|
+| `page_view` | (automatic) |
+| `generate_lead` | — (value, currency optional) |
+| `purchase` | transaction_id, value, currency, items[] |
+| `add_to_cart` | items[] (item_id, item_name, price, quantity) |
+| `form_start` | form_id, form_name |
+| `form_submit` | form_id, form_name |
+
+**Validation script:**
+```javascript
+// Check dataLayer for specific event schema
+(function(eventName){
+  var dl = window.dataLayer || [];
+  var events = dl.filter(function(e){return e.event === eventName;});
+  if(events.length === 0) return JSON.stringify({found: false, event: eventName});
+  var e = events[events.length-1];
+  return JSON.stringify({found: true, event: eventName, keys: Object.keys(e), data: e});
+})('generate_lead')
+```
+
+### 4. Naming Convention Check
+
+Verify all GTM resources follow D.intelligence naming standards.
+
+**Tag naming:**
+```
+[Platform] - [event_name] [context]
+Examples:
+  GA4 - generate_lead (contact form)
+  sGTM - purchase
+  cHTML - Contact Form dataLayer Events
+  FB_CONVERSIONS_API-PIXEL_ID-Web-Tag-GA4_Event
+```
+
+**Trigger naming:**
+```
+[Type] - [description] Trigger
+Examples:
+  Click - Hero CTA (consult)
+  CE - contact_form_submit
+  Form Submit - contact-form
+  Scroll - 50pct Depth
+  PV - consult booking Trigger
+```
+
+**Variable naming:**
+```
+[prefix] - [description]
+Prefixes: dlv (dataLayer), cjs (Custom JS), aev (Auto-Event),
+          jsv (JS Variable), URL query, cookie, c (Constant)
+Examples:
+  dlv - contact_form.request_type
+  cjs - Social platform
+  aev - click url hostname
+```
+
+**Validation steps:**
+1. `dtm_list_tags` / `dtm_list_triggers` / `dtm_list_variables`
+2. Check each name against patterns above
+3. Flag violations: missing prefix, wrong case, unclear description
+
+### 5. Cross-Platform Event Mapping Verification
+
+Verify the same user action sends consistent events to all platforms.
+
+| User Action | GA4 | Meta (FB) | Google Ads | Kakao | Naver |
+|------------|-----|-----------|------------|-------|-------|
+| Page view | page_view | PageView | — | pageView | — |
+| Product view | view_item | ViewContent | — | viewContent | — |
+| Add to cart | add_to_cart | AddToCart | — | addToCart | — |
+| Purchase | purchase | Purchase | purchase | purchase | — |
+| Lead form | generate_lead | Lead | submit_lead_form | participation | — |
+
+**Steps:**
+1. Trigger a user action (click, form submit)
+2. `list_network_requests` — capture all resulting requests
+3. Check each platform received the correct event:
+   - GA4: `google-analytics.com/g/collect?en=...`
+   - Meta: `facebook.com/tr/?ev=...`
+   - Google Ads: `googleads.g.doubleclick.net/pagead/...`
+
+### 6. QA Checklist Execution
+
+Run through a standard QA checklist for GTM implementation:
+
+- [ ] GTM container snippet in `<head>` (not `<body>`)
+- [ ] GTM noscript fallback in `<body>`
+- [ ] No duplicate GTM containers on same page
+- [ ] dataLayer initialized before GTM snippet
+- [ ] All P1 tags fire on page load (GA4 config, Consent Mode)
+- [ ] Click triggers use specific selectors (not generic classes)
+- [ ] Form triggers match form IDs that exist on page
+- [ ] Custom HTML tags use ES5 syntax only
+- [ ] No console errors related to GTM/tags
+- [ ] Consent Mode properly blocks tags before consent
+- [ ] sGTM endpoint responding (no SSL errors)
+- [ ] Cross-domain tracking configured if needed
+
+### 7. Version Comparison
+
+Compare tags between two container versions to identify changes.
+
+1. `dtm_list_versions` — get version list
+2. `dtm_get_live_version` — get current live version with all tags
+3. Compare tag counts, trigger counts, new/modified/deleted items
+4. Report changes since last publish
+
+## Reference Files
+
+| File | Content |
+|------|---------|
+| `references/datalayer-schema.md` | GA4 recommended event schemas |
+| `references/platform-mapping.md` | GA4 ↔ Meta ↔ Kakao ↔ Ads event mapping |
+| `references/naming-conventions.md` | Tag/trigger/variable naming rules |
+| `references/qa-checklist.md` | Full QA checklist |
+
+## Workflow
+
+1. **Receive** tag list from gtm-editor (or run `dtm_list_tags`)
+2. **Navigate** to the target page via Chrome DevTools
+3. **Test** each trigger's CSS selector matches actual DOM elements
+4. **Simulate** user actions (clicks, form submits, scrolls)
+5. **Capture** network requests after each action
+6. **Verify** correct events fired to correct platforms
+7. **Report** pass/fail with evidence (screenshots, network logs)
+
+## Rules
+
+- Always test on the LIVE published version, not preview (unless debugging)
+- Test on both desktop and mobile viewports when possible
+- Check consent mode state before flagging missing tags
+- Document every test result with screenshots or network request evidence
+- **When a trigger uses CSS selectors instead of IDs, flag it as a fragility risk** — recommend adding `id` attributes to the HTML
+- If a trigger selector doesn't match, suggest adding an ID to the element first (not a different CSS selector) and hand off to gtm-editor
+- GTM questions, best practices, and architecture advice are also in scope

custom-skills/62-gtm-validator/code/references/datalayer-schema.md

@@ -0,0 +1,193 @@
+# DataLayer Schema Reference
+
+GA4 권장 이벤트 기반 DataLayer 스키마 정의.
+
+## Core Principles
+
+1. GTM 스니펫 이전에 dataLayer 초기화
+2. 이벤트 발생 시점에 push (사전 아님)
+3. ecommerce 객체는 push 전 clear 필수
+4. PII 데이터 직접 수집 금지
+
+## Base Structure
+
+### Page Load
+```javascript
+window.dataLayer = window.dataLayer || [];
+dataLayer.push({
+  'event': 'page_data',
+  'page': {
+    'type': 'home|category|product|cart|checkout|thankyou|content|search',
+    'name': 'Page Name',
+    'category': 'Category/Subcategory',
+    'language': 'ko'
+  },
+  'user': {
+    'status': 'logged_in|logged_out',
+    'id': 'hashed_user_id',           // SHA256, 로그인 시에만
+    'type': 'new|returning|member|guest',
+    'loginMethod': 'email|kakao|naver|google'
+  }
+});
+```
+
+## E-commerce Events
+
+### view_item
+```javascript
+dataLayer.push({ ecommerce: null });
+dataLayer.push({
+  'event': 'view_item',
+  'ecommerce': {
+    'currency': 'KRW',
+    'value': 29000,
+    'items': [{
+      'item_id': 'SKU_12345',
+      'item_name': 'Product Name',
+      'item_brand': 'Brand Name',
+      'item_category': 'Category',
+      'item_variant': 'Blue / Large',
+      'price': 29000,
+      'quantity': 1
+    }]
+  }
+});
+```
+
+### add_to_cart
+```javascript
+dataLayer.push({ ecommerce: null });
+dataLayer.push({
+  'event': 'add_to_cart',
+  'ecommerce': {
+    'currency': 'KRW',
+    'value': 29000,
+    'items': [{
+      'item_id': 'SKU_12345',
+      'item_name': 'Product Name',
+      'price': 29000,
+      'quantity': 1
+    }]
+  }
+});
+```
+
+### begin_checkout
+```javascript
+dataLayer.push({ ecommerce: null });
+dataLayer.push({
+  'event': 'begin_checkout',
+  'ecommerce': {
+    'currency': 'KRW',
+    'value': 58000,
+    'coupon': 'WELCOME10',
+    'items': [/* cart items */]
+  }
+});
+```
+
+### purchase
+```javascript
+dataLayer.push({ ecommerce: null });
+dataLayer.push({
+  'event': 'purchase',
+  'ecommerce': {
+    'transaction_id': 'T_20250115_001',
+    'affiliation': 'Store Name',
+    'value': 53000,
+    'tax': 4818,
+    'shipping': 3000,
+    'currency': 'KRW',
+    'coupon': 'WELCOME10',
+    'items': [{
+      'item_id': 'SKU_12345',
+      'item_name': 'Product Name',
+      'price': 29000,
+      'quantity': 1
+    }]
+  }
+});
+```
+
+## Lead Gen Events
+
+### generate_lead
+```javascript
+dataLayer.push({
+  'event': 'generate_lead',
+  'currency': 'KRW',
+  'value': 50000,
+  'lead': {
+    'source': 'contact_form|landing_page',
+    'type': 'inquiry|quote_request'
+  }
+});
+```
+
+### form_submit
+```javascript
+dataLayer.push({
+  'event': 'form_submit',
+  'form': {
+    'id': 'contact_form',
+    'name': 'Contact Us Form',
+    'type': 'contact',
+    'success': true
+  }
+});
+```
+
+## Engagement Events
+
+### login / sign_up
+```javascript
+dataLayer.push({
+  'event': 'login',  // or 'sign_up'
+  'method': 'email|kakao|naver|google'
+});
+```
+
+### search
+```javascript
+dataLayer.push({
+  'event': 'search',
+  'search_term': 'user search query',
+  'search': {
+    'results_count': 42,
+    'category': 'product|content'
+  }
+});
+```
+
+## Item Object Reference
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| item_id | string | Yes | SKU |
+| item_name | string | Yes | 상품명 |
+| price | number | Yes | 단가 |
+| quantity | number | Yes | 수량 |
+| item_brand | string | No | 브랜드명 |
+| item_category | string | No | 카테고리 |
+| item_category2-5 | string | No | 하위 카테고리 |
+| item_variant | string | No | 옵션 |
+| coupon | string | No | 쿠폰 코드 |
+| discount | number | No | 할인 금액 |
+| index | number | No | 목록 위치 |
+
+## Validation Rules
+
+```javascript
+// ✅ Correct
+'price': 29000        // number
+'quantity': 1         // number
+'currency': 'KRW'     // uppercase
+
+// ❌ Wrong
+'price': '29000'      // string
+'currency': 'krw'     // lowercase
+```
+
+### Array Limits
+- items[]: 최대 200개
+- 초과 시 분할 전송

custom-skills/62-gtm-validator/code/references/naming-conventions.md

@@ -0,0 +1,130 @@
+# GTM Naming Conventions
+
+일관된 GTM 컨테이너 관리를 위한 네이밍 규칙.
+
+## Tag Naming
+
+### Pattern
+```
+[Platform] - [Type] - [Description]
+```
+
+### Examples
+| Platform | Type | Description | Tag Name |
+|----------|------|-------------|----------|
+| GA4 | Config | Main | GA4 - Config - Main |
+| GA4 | Event | purchase | GA4 - Event - purchase |
+| GAds | Conversion | Purchase | GAds - Conversion - Purchase |
+| Meta | Event | Purchase | Meta - Event - Purchase |
+| Kakao | Event | purchase | Kakao - Event - purchase |
+
+## Trigger Naming
+
+### Pattern
+```
+[Type] - [Condition] - [Context]
+```
+
+### Type Codes
+| Code | Type | Example |
+|------|------|---------|
+| PV | Page View | PV - All Pages |
+| DL | DataLayer Event | DL - purchase |
+| Click | Click | Click - CTA Button |
+| Form | Form Submit | Form - Contact |
+| Scroll | Scroll Depth | Scroll - 75% |
+| Vis | Element Visibility | Vis - Video Player |
+
+### Examples
+```
+PV - All Pages
+PV - Thank You Page
+DL - purchase
+DL - add_to_cart
+Click - CTA Button - Hero
+Form - Contact Form
+Scroll - 90%
+```
+
+## Variable Naming
+
+### Pattern
+```
+[Type] - [Name/Path]
+```
+
+### Type Codes
+| Code | Type | Example |
+|------|------|---------|
+| DLV | DataLayer Variable | DLV - ecommerce.value |
+| CJS | Custom JavaScript | CJS - Item IDs Array |
+| Const | Constant | Const - GA4 Measurement ID |
+| LT | Lookup Table | LT - Page Type Mapping |
+| URL | URL Variable | URL - Path |
+| DOM | DOM Element | DOM - Product Title |
+
+### Examples
+```
+DLV - event
+DLV - ecommerce.transaction_id
+DLV - ecommerce.items
+CJS - Items for Meta
+CJS - Formatted Price
+Const - GA4 Measurement ID
+Const - Meta Pixel ID
+LT - Payment Method Mapping
+```
+
+## Folder Structure
+
+```
+📁 01. Configuration
+📁 02. GA4 Events
+📁 03. Google Ads
+📁 04. Meta Pixel
+📁 05. Kakao Pixel
+📁 06. Other Platforms
+📁 07. Utilities
+📁 99. Deprecated
+```
+
+## Built-in Variables to Enable
+
+```
+Pages: ✅ Page URL, Path, Hostname, Referrer
+Utilities: ✅ Event, Container ID, Random Number
+Clicks: ✅ Element, Classes, ID, URL, Text
+Forms: ✅ Element, Classes, ID, URL, Text
+History: ✅ New/Old History Fragment/State
+Videos: ✅ All YouTube variables
+Scrolling: ✅ Depth Threshold, Units, Direction
+Visibility: ✅ Percent Visible, On-Screen Duration
+```
+
+## Anti-patterns
+
+```
+❌ Tag 1, New Tag, Test
+❌ GA4 purchase event (일관성 없음)
+❌ G4-E-Pch (과도한 약어)
+❌ Very Long Tag Name for Purchase Complete Event (너무 김)
+
+✅ GA4 - Event - purchase
+✅ DL - purchase
+✅ CJS - Items for Meta
+```
+
+## Version Notes
+
+```
+v[Major].[Minor] - [Description]
+예: v12.1 - Added form_submit event
+
+## Changes
+- Added: 
+- Modified: 
+- Removed: 
+
+## Reason
+[변경 이유]
+```

custom-skills/62-gtm-validator/code/references/phase6-audit.md

@@ -0,0 +1,215 @@
+# Phase 6: Progressive Audit & Update
+
+설정된 GTM Container에 대한 주기적 진단, 유효성 검증, 마이너 업데이트 및 태그 추가.
+
+## Objectives
+
+1. GTM 컨테이너 건강 상태 점검
+2. 태그 발화 및 데이터 정합성 검증
+3. 최신 요구사항 반영 업데이트
+4. D.intelligence GTM Toolkit 연계 자동화
+
+## Audit Schedule
+
+| Frequency | Scope | Trigger |
+|-----------|-------|---------|
+| Weekly | Tag firing validation | 자동 스케줄 |
+| Monthly | Full container review | 월간 리포트 |
+| Quarterly | Architecture review | 분기 회의 |
+| Ad-hoc | Issue investigation | 이슈 발생 시 |
+
+## Audit Checklist
+
+### 1. Container Health Check
+- [ ] 버전 히스토리 확인 (최근 변경사항)
+- [ ] 미사용 태그/트리거/변수 식별
+- [ ] 명명 규칙 준수 여부
+- [ ] 폴더 구조 정리 상태
+
+### 2. Tag Firing Validation
+- [ ] 모든 P1 태그 정상 발화
+- [ ] 트리거 조건 정확성
+- [ ] 변수 값 정확성
+- [ ] 차단 트리거 작동
+
+### 3. Data Quality
+- [ ] GA4 Realtime 데이터 확인
+- [ ] 전환 데이터 정합성
+- [ ] 파라미터 값 검증
+- [ ] 이상치 탐지
+
+### 4. Platform Sync
+- [ ] GA4 ↔ GTM 동기화
+- [ ] Google Ads 전환 데이터
+- [ ] Meta Events Manager 상태
+- [ ] Kakao Pixel 상태
+
+## D.intelligence GTM Toolkit Integration
+
+### Repository
+```
+https://github.com/ourdigital/dintel-gtm-toolkit
+```
+
+### Capabilities
+
+| Feature | Description | Use Case |
+|---------|-------------|----------|
+| Container Analysis | JSON 파싱, 구조 분석 | 컨테이너 리뷰 |
+| Dependency Mapping | 태그↔트리거↔변수 관계 | 영향도 분석 |
+| Version Diff | 버전 간 변경사항 비교 | 변경 추적 |
+| Tag Validation | 발화 상태 자동 검증 | 정기 감사 |
+
+### Integration Workflow
+
+```
+1. GTM Container Export
+   └── JSON 파일 다운로드
+
+2. D.intel Toolkit Analysis
+   ├── python analyze_container.py container.json
+   ├── Dependency graph 생성
+   └── Issue detection
+
+3. Report Generation
+   └── Markdown/HTML 리포트
+
+4. GTM Guardian Update
+   └── Notion에 리포트 저장
+```
+
+### Sample Toolkit Commands
+
+```bash
+# Container 분석
+python analyze_container.py GTM-XXXXXX.json --output report.md
+
+# 버전 비교
+python diff_versions.py v1.json v2.json --output diff.md
+
+# 태그 검증
+python validate_tags.py container.json --events events.csv
+
+# 미사용 요소 탐지
+python find_unused.py container.json --type all
+```
+
+## Audit Report Template
+
+```markdown
+# GTM Audit Report
+
+## Summary
+- **Container**: GTM-XXXXXX
+- **Audit Date**: YYYY-MM-DD
+- **Version Reviewed**: XX
+- **Overall Status**: ✅ Healthy / ⚠️ Needs Attention / ❌ Critical
+
+## Findings
+
+### ✅ Passing
+- [항목]
+
+### ⚠️ Warnings
+| Issue | Impact | Recommendation |
+|-------|--------|----------------|
+
+### ❌ Critical
+| Issue | Impact | Action Required |
+|-------|--------|-----------------|
+
+## Tag Firing Status
+
+| Tag | Expected | Actual | Status |
+|-----|----------|--------|--------|
+| GA4 - Event - purchase | Thank You | Thank You | ✅ |
+
+## Data Quality Check
+
+| Metric | Expected | Actual | Variance |
+|--------|----------|--------|----------|
+| Daily Purchases | ~50 | 48 | -4% |
+
+## Recommendations
+1. 
+2. 
+
+## Next Steps
+- [ ] 
+- [ ] 
+
+## Appendix
+- Container JSON snapshot
+- D.intel Toolkit output
+```
+
+## Update Procedures
+
+### Minor Update (태그 수정)
+```
+1. 변경 필요 태그 식별
+2. Preview 모드에서 수정
+3. 테스트 완료
+4. Publish with version note
+5. Notion 문서 업데이트
+```
+
+### Major Update (신규 태그 추가)
+```
+1. Phase 3-4 문서 업데이트
+2. DataLayer 요구사항 개발팀 전달
+3. GTM 태그/트리거/변수 설정
+4. QA 체크리스트 수행
+5. 단계적 배포
+6. Notion 문서 업데이트
+```
+
+### Emergency Fix
+```
+1. 이슈 원인 파악
+2. 최소 변경으로 수정
+3. Publish (emergency version note)
+4. 근본 원인 분석
+5. 영구 수정 계획
+```
+
+## Versioning Best Practices
+
+### Version Naming
+```
+v[Major].[Minor] - [Description]
+예: v12.1 - Added form_submit event
+```
+
+### Version Notes Template
+```
+## Changes
+- Added: [새로 추가된 항목]
+- Modified: [수정된 항목]
+- Removed: [삭제된 항목]
+
+## Reason
+[변경 이유]
+
+## Testing
+- [테스트 항목 및 결과]
+
+## Rollback Plan
+[롤백 필요 시 절차]
+```
+
+## Monitoring Setup
+
+### GA4 Alerts
+- 일일 전환 수 급감 (>30%)
+- 세션 수 급감 (>50%)
+- 이벤트 수집 오류
+
+### Custom Monitoring
+- DataLayer 오류 로깅
+- Tag Manager 오류 추적
+- 서버 사이드 태그 상태 (sGTM 시)
+
+## Next Phase
+
+주기적 감사 완료 후 → Phase 7: Lookup App (필요 시)

custom-skills/62-gtm-validator/code/references/phase7-lookup-app.md

@@ -0,0 +1,283 @@
+# Phase 7: Event Lookup & Parameter Library Web App
+
+Google Apps Script를 활용한 Event Taxonomy Sheet 기반 업무 지원용 앱 배포.
+
+## Objectives
+
+1. Event Taxonomy 데이터 조회 앱
+2. 실시간 파라미터 참조 도구
+3. 비개발자용 Self-service 도구
+4. 팀 간 일관된 이벤트 정보 공유
+
+## App Architecture
+
+```
+┌─────────────────┐     ┌─────────────────┐     ┌─────────────────┐
+│  Google Sheets  │────▶│  Apps Script    │────▶│   Web App       │
+│  (Taxonomy DB)  │     │  (Backend)      │     │  (Frontend)     │
+└─────────────────┘     └─────────────────┘     └─────────────────┘
+```
+
+## Google Sheets Data Source
+
+### Required Sheets
+- Events Master
+- Parameters Reference
+- Custom Definitions
+- Platform Mapping
+
+### Column Requirements
+→ Phase 4 참조: [phase4-taxonomy.md](phase4-taxonomy.md)
+
+## Apps Script Setup
+
+### 1. Project Creation
+```
+1. Google Sheets 열기
+2. Extensions > Apps Script
+3. 프로젝트 이름 설정
+```
+
+### 2. Core Functions
+
+#### Data Retrieval
+```javascript
+function getEventsData() {
+  const sheet = SpreadsheetApp.getActiveSpreadsheet()
+    .getSheetByName('Events Master');
+  const data = sheet.getDataRange().getValues();
+  const headers = data[0];
+  
+  return data.slice(1).map(row => {
+    const obj = {};
+    headers.forEach((header, i) => {
+      obj[header] = row[i];
+    });
+    return obj;
+  });
+}
+
+function getParametersData() {
+  const sheet = SpreadsheetApp.getActiveSpreadsheet()
+    .getSheetByName('Parameters Reference');
+  const data = sheet.getDataRange().getValues();
+  const headers = data[0];
+  
+  return data.slice(1).map(row => {
+    const obj = {};
+    headers.forEach((header, i) => {
+      obj[header] = row[i];
+    });
+    return obj;
+  });
+}
+```
+
+#### Search Function
+```javascript
+function searchEvents(query) {
+  const events = getEventsData();
+  const searchTerm = query.toLowerCase();
+  
+  return events.filter(event => 
+    event.event_name.toLowerCase().includes(searchTerm) ||
+    event.event_category.toLowerCase().includes(searchTerm) ||
+    event.notes.toLowerCase().includes(searchTerm)
+  );
+}
+
+function getEventDetails(eventName) {
+  const events = getEventsData();
+  const params = getParametersData();
+  
+  const event = events.find(e => e.event_name === eventName);
+  if (!event) return null;
+  
+  const eventParams = event.parameters.split(',').map(p => p.trim());
+  const paramDetails = params.filter(p => 
+    eventParams.includes(p.parameter_name)
+  );
+  
+  return {
+    event: event,
+    parameters: paramDetails
+  };
+}
+```
+
+### 3. Web App Handler
+
+```javascript
+function doGet(e) {
+  return HtmlService.createHtmlOutputFromFile('index')
+    .setTitle('GTM Event Lookup')
+    .setXFrameOptionsMode(HtmlService.XFrameOptionsMode.ALLOWALL);
+}
+
+function doPost(e) {
+  const action = e.parameter.action;
+  
+  switch(action) {
+    case 'search':
+      return ContentService.createTextOutput(
+        JSON.stringify(searchEvents(e.parameter.query))
+      ).setMimeType(ContentService.MimeType.JSON);
+      
+    case 'details':
+      return ContentService.createTextOutput(
+        JSON.stringify(getEventDetails(e.parameter.eventName))
+      ).setMimeType(ContentService.MimeType.JSON);
+      
+    default:
+      return ContentService.createTextOutput(
+        JSON.stringify({error: 'Invalid action'})
+      ).setMimeType(ContentService.MimeType.JSON);
+  }
+}
+```
+
+### 4. HTML Frontend (index.html)
+
+```html
+<!DOCTYPE html>
+<html>
+<head>
+  <base target="_top">
+  <style>
+    body { font-family: 'Roboto', sans-serif; padding: 20px; max-width: 800px; margin: 0 auto; }
+    .search-box { width: 100%; padding: 12px; font-size: 16px; margin-bottom: 20px; }
+    .event-card { border: 1px solid #ddd; padding: 16px; margin: 10px 0; border-radius: 8px; }
+    .event-name { font-size: 18px; font-weight: bold; color: #1a73e8; }
+    .param-badge { background: #e8f0fe; color: #1967d2; padding: 4px 8px; border-radius: 4px; margin: 2px; display: inline-block; }
+    .category { color: #5f6368; font-size: 14px; }
+    .priority-p1 { border-left: 4px solid #ea4335; }
+    .priority-p2 { border-left: 4px solid #fbbc04; }
+    .priority-p3 { border-left: 4px solid #34a853; }
+  </style>
+</head>
+<body>
+  <h1>🏷️ GTM Event Lookup</h1>
+  <input type="text" class="search-box" id="searchInput" placeholder="이벤트명 또는 카테고리 검색...">
+  <div id="results"></div>
+  
+  <script>
+    const searchInput = document.getElementById('searchInput');
+    const results = document.getElementById('results');
+    
+    searchInput.addEventListener('input', debounce(function() {
+      const query = this.value;
+      if (query.length < 2) {
+        results.innerHTML = '';
+        return;
+      }
+      
+      google.script.run
+        .withSuccessHandler(displayResults)
+        .searchEvents(query);
+    }, 300));
+    
+    function displayResults(events) {
+      results.innerHTML = events.map(event => `
+        <div class="event-card priority-${event.priority.toLowerCase()}">
+          <div class="event-name">${event.event_name}</div>
+          <div class="category">${event.event_category} | ${event.priority}</div>
+          <div style="margin-top: 10px;">
+            ${event.parameters.split(',').map(p => 
+              `<span class="param-badge">${p.trim()}</span>`
+            ).join('')}
+          </div>
+          <div style="margin-top: 10px; color: #5f6368;">${event.notes}</div>
+        </div>
+      `).join('');
+    }
+    
+    function debounce(func, wait) {
+      let timeout;
+      return function(...args) {
+        clearTimeout(timeout);
+        timeout = setTimeout(() => func.apply(this, args), wait);
+      };
+    }
+  </script>
+</body>
+</html>
+```
+
+## Deployment
+
+### 1. Deploy as Web App
+```
+1. Deploy > New deployment
+2. Type: Web app
+3. Execute as: Me
+4. Access: Anyone within organization (또는 Anyone)
+5. Deploy
+```
+
+### 2. Get Web App URL
+```
+배포 후 제공되는 URL 복사
+https://script.google.com/macros/s/[ID]/exec
+```
+
+### 3. Share with Team
+- URL을 Notion/Slack에 공유
+- 북마크 권장
+
+## Features Roadmap
+
+### Phase 1 (MVP)
+- [x] 이벤트 검색
+- [x] 파라미터 조회
+- [x] 우선순위 필터
+
+### Phase 2
+- [ ] DataLayer 코드 스니펫 복사
+- [ ] 플랫폼별 코드 예시
+- [ ] 최근 조회 히스토리
+
+### Phase 3
+- [ ] 이벤트 추가/수정 폼
+- [ ] 변경 이력 추적
+- [ ] Slack 알림 연동
+
+## Maintenance
+
+### Data Update
+1. Google Sheets 원본 데이터 수정
+2. Web App 자동 반영 (실시간)
+
+### Code Update
+1. Apps Script 수정
+2. Deploy > Manage deployments
+3. New version 배포
+
+### Backup
+- Google Sheets 자동 버전 히스토리
+- 주기적 수동 백업 권장
+
+## Access Control
+
+| Role | Access Level |
+|------|--------------|
+| Admin | 시트 편집 + 스크립트 수정 |
+| Editor | 시트 편집 |
+| Viewer | Web App 조회만 |
+
+## Troubleshooting
+
+| Issue | Solution |
+|-------|----------|
+| 앱 로딩 느림 | 데이터 캐싱 구현 |
+| 검색 결과 없음 | 검색어 확인, 데이터 존재 확인 |
+| 권한 오류 | 배포 설정에서 접근 권한 확인 |
+| 데이터 미반영 | 시트 새로고침, 캐시 클리어 |
+
+## Integration with Notion
+
+Web App URL을 Notion에 embed:
+```
+/embed [Web App URL]
+```
+
+또는 iframe으로 직접 삽입.

custom-skills/62-gtm-validator/code/references/platform-mapping.md

@@ -0,0 +1,125 @@
+# Platform Event Mapping Reference
+
+GA4, Google Ads, Meta Pixel, Kakao Pixel 간 이벤트 매핑.
+
+## E-commerce Events
+
+| User Action | GA4 | Meta | Kakao | Google Ads |
+|-------------|-----|------|-------|------------|
+| 상품 목록 조회 | view_item_list | ViewContent | viewContent | - |
+| 상품 상세 조회 | view_item | ViewContent | viewContent | - |
+| 상품 검색 | search | Search | search | - |
+| 장바구니 담기 | add_to_cart | AddToCart | addToCart | - |
+| 위시리스트 | add_to_wishlist | AddToWishlist | addToWishlist | - |
+| 결제 시작 | begin_checkout | InitiateCheckout | beginCheckout | - |
+| 배송정보 입력 | add_shipping_info | - | - | - |
+| 결제정보 입력 | add_payment_info | AddPaymentInfo | addPaymentInfo | - |
+| 구매 완료 | purchase | Purchase | purchase | purchase |
+
+## Lead Gen Events
+
+| User Action | GA4 | Meta | Kakao | Google Ads |
+|-------------|-----|------|-------|------------|
+| 회원가입 | sign_up | CompleteRegistration | completeRegistration | sign_up |
+| 로그인 | login | - | login | - |
+| 리드 생성 | generate_lead | Lead | participation | submit_lead_form |
+
+## Engagement Events
+
+| User Action | GA4 | Meta | Kakao | Google Ads |
+|-------------|-----|------|-------|------------|
+| 페이지 조회 | page_view | PageView | pageView | page_view |
+| 검색 | search | Search | search | - |
+| 공유 | share | - | - | - |
+
+## Parameter Transformation
+
+### GA4 → Meta
+```javascript
+// GA4 items[] → Meta content_ids[]
+const contentIds = items.map(item => item.item_id);
+
+// Meta Purchase
+fbq('track', 'Purchase', {
+  content_ids: contentIds,
+  content_type: 'product',
+  value: ecommerce.value,
+  currency: 'KRW',
+  num_items: items.length
+});
+```
+
+### GA4 → Kakao
+```javascript
+// GA4 items[] → Kakao products[]
+const products = items.map(item => ({
+  id: item.item_id,
+  name: item.item_name,
+  price: item.price,
+  quantity: item.quantity
+}));
+
+// Kakao purchase
+kakaoPixel('PIXEL_ID').purchase({
+  total_price: ecommerce.value,
+  currency: 'KRW',
+  products: products
+});
+```
+
+## GTM Variables
+
+### CJS - Item IDs for Meta
+```javascript
+function() {
+  var items = {{DLV - ecommerce.items}} || [];
+  return items.map(function(item) {
+    return item.item_id;
+  });
+}
+```
+
+### CJS - Products for Kakao
+```javascript
+function() {
+  var items = {{DLV - ecommerce.items}} || [];
+  return items.map(function(item) {
+    return {
+      id: item.item_id,
+      name: item.item_name,
+      price: item.price,
+      quantity: item.quantity
+    };
+  });
+}
+```
+
+## Deduplication
+
+### Event ID Pattern
+```javascript
+var eventId = 'evt_' + Date.now() + '_' + Math.random().toString(36).substr(2, 9);
+
+// Client-side
+fbq('track', 'Purchase', {...}, {eventID: eventId});
+
+// Server-side (CAPI)
+// 동일한 eventId 사용 → Meta 자동 중복 제거
+```
+
+## Platform-specific Notes
+
+### Meta Pixel
+- content_type: 'product' (상품) / 'product_group' (변형)
+- currency: ISO 4217 필수
+- value: 숫자 (소수점 가능)
+
+### Kakao Pixel
+- Server-side 미지원 (Client-only)
+- products[]: 최대 10개 권장
+- total_price: 숫자
+
+### Google Ads
+- Enhanced Conversions 권장
+- transaction_id 필수 (중복 제거용)
+- value: KRW 정수

custom-skills/62-gtm-validator/code/references/qa-checklist.md

@@ -0,0 +1,149 @@
+# GTM Implementation QA Checklist
+
+태깅 구현 품질 검증 체크리스트.
+
+## 1. Pre-Implementation
+
+### Documentation
+- [ ] Tagging Plan 승인 완료
+- [ ] DataLayer 스키마 개발팀 공유
+- [ ] 이벤트 택소노미 합의 완료
+
+### Access
+- [ ] GTM 컨테이너 접근 권한
+- [ ] GA4 속성 접근 권한
+- [ ] 광고 플랫폼 접근 권한
+
+### Tools
+- [ ] GTM Preview 모드 정상
+- [ ] GA4 DebugView 활성화
+- [ ] Chrome DevTools 준비
+
+## 2. DataLayer Validation
+
+### Base Setup
+- [ ] GTM 스니펫 이전 dataLayer 초기화
+- [ ] 페이지 로드 시 기본 데이터 push
+- [ ] pageType, userId 등 기본 변수 존재
+
+### Data Types
+- [ ] 숫자 값이 Number 타입
+- [ ] 금액에 통화 코드 포함 (KRW)
+- [ ] transaction_id 유니크
+
+### E-commerce
+- [ ] ecommerce: null 선행 push
+- [ ] items[] 배열 구조 정확
+- [ ] 필수 파라미터 완비
+
+### Console Check
+```javascript
+console.log(window.dataLayer);
+dataLayer.filter(e => e.event === 'purchase');
+```
+
+## 3. Tag Firing
+
+### GA4
+| Tag | Trigger | Status |
+|-----|---------|--------|
+| Config | All Pages | [ ] |
+| view_item | Product page | [ ] |
+| add_to_cart | Add button | [ ] |
+| begin_checkout | Checkout start | [ ] |
+| purchase | Thank you | [ ] |
+
+### Google Ads
+| Conversion | Trigger | Status |
+|------------|---------|--------|
+| Purchase | DL - purchase | [ ] |
+| Lead | DL - generate_lead | [ ] |
+
+### Meta Pixel
+| Event | Trigger | Status |
+|-------|---------|--------|
+| PageView | All Pages | [ ] |
+| ViewContent | Product | [ ] |
+| AddToCart | Add | [ ] |
+| Purchase | Thank you | [ ] |
+
+### Kakao Pixel
+| Event | Trigger | Status |
+|-------|---------|--------|
+| pageView | All Pages | [ ] |
+| purchase | Thank you | [ ] |
+
+## 4. Network Validation
+
+### Endpoints
+```
+GA4: google-analytics.com/g/collect
+GAds: googleads.g.doubleclick.net/pagead/conversion/
+Meta: facebook.com/tr/
+```
+
+### Check Points
+- [ ] 요청 전송됨
+- [ ] 파라미터 정확
+- [ ] 응답 성공 (200/204)
+
+## 5. Cross-browser Testing
+
+### Desktop
+- [ ] Chrome
+- [ ] Safari
+- [ ] Firefox
+- [ ] Edge
+
+### Mobile
+- [ ] iOS Safari
+- [ ] iOS Chrome
+- [ ] Android Chrome
+
+## 6. Data Validation (Platform)
+
+### GA4
+- [ ] Realtime 보고서 이벤트 표시
+- [ ] 파라미터 정확히 수집
+- [ ] E-commerce 보고서 정확
+
+### Google Ads
+- [ ] 전환 액션 데이터 유입
+- [ ] 전환 값 정확
+
+### Meta
+- [ ] Events Manager 수신 확인
+- [ ] Event match quality 확인
+
+## 7. Edge Cases
+
+- [ ] 빈 장바구니 결제 시작 처리
+- [ ] 0개 구매 처리
+- [ ] 쿠폰 없는 구매
+- [ ] 게스트 체크아웃
+- [ ] 새로고침 시 중복 방지
+- [ ] 뒤로가기 시 처리
+
+## 8. Performance & Privacy
+
+### Performance
+- [ ] 태그 로딩이 렌더링 차단 안 함
+- [ ] 비동기 로딩
+
+### Privacy
+- [ ] 동의 없이 태그 미발화 (CMP 시)
+- [ ] PII 직접 수집 없음
+
+## Sign-off
+
+| Role | Name | Date | ✓ |
+|------|------|------|---|
+| QA Lead | | | |
+| Analytics Lead | | | |
+| Dev Lead | | | |
+
+## Issues Log
+
+| # | Issue | Severity | Status |
+|---|-------|----------|--------|
+| 1 | | High/Med/Low | Open/Resolved |

custom-skills/92-mac-optimizer/.claude-plugin/plugin.json

@@ -0,0 +1,45 @@
+{
+  "name": "mac-optimizer",
+  "version": "1.0.0",
+  "description": "Modular macOS system health toolkit with read-only audits, cleanup, and security checks",
+  "author": {
+    "name": "OurDigital"
+  },
+  "keywords": [
+    "macos",
+    "system",
+    "optimization",
+    "cleanup",
+    "security",
+    "homebrew",
+    "packages",
+    "disk-space"
+  ],
+  "license": "MIT",
+  "commands": [
+    {
+      "name": "mac-doctor",
+      "description": "Full macOS system health check — runs all 5 audit modules and presents unified findings"
+    },
+    {
+      "name": "mac-packages",
+      "description": "Audit package managers (Homebrew, npm, pip, pyenv) for outdated packages and issues"
+    },
+    {
+      "name": "mac-environment",
+      "description": "Audit shell environment — PATH, symlinks, shell configs, and startup time"
+    },
+    {
+      "name": "mac-security",
+      "description": "Security posture assessment — SIP, Gatekeeper, Firewall, FileVault, SSH, ports"
+    },
+    {
+      "name": "mac-cleanup",
+      "description": "Scan and clean caches, logs, and clutter — shows sizes first, cleans only with consent"
+    },
+    {
+      "name": "mac-resources",
+      "description": "Monitor CPU, memory, disk, battery, and identify resource-hungry processes"
+    }
+  ]
+}

custom-skills/92-mac-optimizer/commands/mac-cleanup.md

@@ -0,0 +1,53 @@
+---
+allowed-tools: Bash(bash *audit_cleanup.sh*), Bash(bash *cleanup_execute.sh*), Bash(du *), Bash(brew *), Bash(npm *), Bash(pip *), Bash(docker *), Bash(rm *)
+description: Scan and clean caches, logs, and clutter — shows sizes first, cleans only with consent
+---
+
+## Your task
+
+Scan for reclaimable disk space and offer cleanup.
+
+### Step 1 — Run the audit
+
+```bash
+bash $CLAUDE_PLUGIN_ROOT/skills/mac-optimizer/scripts/audit_cleanup.sh
+```
+
+### Step 2 — Report
+
+Parse JSON output and present as a table sorted by size (largest first):
+
+| Category | Size | Risk | Target |
+|---|---|---|---|
+
+Show the total reclaimable space.
+
+### Step 3 — Ask for consent
+
+Ask which categories to clean. Group by risk level (Safe / Moderate / Risky).
+
+### Step 4 — Dry run first
+
+For approved targets, always run dry-run first:
+
+```bash
+bash $CLAUDE_PLUGIN_ROOT/skills/mac-optimizer/scripts/cleanup_execute.sh --dry-run <targets>
+```
+
+Show the output and ask for final confirmation.
+
+### Step 5 — Execute
+
+Only after explicit confirmation:
+
+```bash
+bash $CLAUDE_PLUGIN_ROOT/skills/mac-optimizer/scripts/cleanup_execute.sh --execute <targets>
+```
+
+### Safety rules
+
+- Never execute cleanup without explicit user approval
+- Always show sizes before deleting anything
+- Always run --dry-run before --execute
+- Docker cleanup uses `docker system prune`, never direct file deletion
+- No sudo by default — if an action needs sudo, state why and ask first

custom-skills/92-mac-optimizer/commands/mac-doctor.md

@@ -0,0 +1,60 @@
+---
+allowed-tools: Bash(bash *audit_*.sh*), Bash(bash *cleanup_execute.sh*), Bash(du *), Bash(df *), Bash(brew *), Bash(npm *), Bash(pip *), Bash(docker *), Bash(cp *)
+description: Full macOS system health check — runs all 5 audit modules and presents unified findings
+---
+
+## Your task
+
+Run a full macOS system health check using all 5 audit modules. Follow this workflow exactly:
+
+### Step 1 — Run all audits
+
+Run these scripts sequentially, collecting all JSON output:
+
+```bash
+bash $CLAUDE_PLUGIN_ROOT/skills/mac-optimizer/scripts/audit_packages.sh
+bash $CLAUDE_PLUGIN_ROOT/skills/mac-optimizer/scripts/audit_environment.sh
+bash $CLAUDE_PLUGIN_ROOT/skills/mac-optimizer/scripts/audit_security.sh
+bash $CLAUDE_PLUGIN_ROOT/skills/mac-optimizer/scripts/audit_cleanup.sh
+bash $CLAUDE_PLUGIN_ROOT/skills/mac-optimizer/scripts/audit_resources.sh
+```
+
+If a script exits non-zero, report the error and continue with other modules.
+
+### Step 2 — Parse and report
+
+Parse all JSON lines. Each has: `{"module":"...","severity":"...","finding":"...","action":"...","details":"..."}`
+
+Present findings grouped by severity (critical first, then warning, then info) as markdown tables:
+
+```
+### Critical
+| Module | Finding | Recommended Action |
+|---|---|---|
+
+### Warning
+| Module | Finding | Recommended Action |
+|---|---|---|
+
+### Info
+| Module | Finding | Recommended Action |
+|---|---|---|
+```
+
+### Step 3 — Ask for consent
+
+STOP and ask: "Which actions would you like me to perform? You can approve by category (e.g., 'update packages and clean caches') or review each item."
+
+### Step 4 — Execute approved actions only
+
+For cleanup actions, always run `--dry-run` first and show what will happen before running `--execute`.
+
+### Safety rules
+
+- Never execute cleanup without explicit user approval
+- Always show sizes before deleting anything
+- Security module is read-only — present findings and remediation guidance only
+- Back up shell configs before modifying: `cp ~/.zshrc ~/.config/mac-optimizer-backups/.zshrc.$(date +%s)`
+- Process deny-list: never suggest killing kernel_task, launchd, WindowServer, loginwindow, mds, mds_stores, opendirectoryd, coreaudiod, SystemUIServer, Finder, Dock
+- No sudo by default — if an action needs sudo, state why and ask first
+- Docker cleanup uses `docker system prune`, never direct file deletion

custom-skills/92-mac-optimizer/commands/mac-environment.md

@@ -0,0 +1,30 @@
+---
+allowed-tools: Bash(bash *audit_environment.sh*), Bash(echo *), Bash(cp *)
+description: Audit shell environment — PATH, symlinks, shell configs, and startup time
+---
+
+## Your task
+
+Audit the shell environment on this Mac.
+
+### Step 1 — Run the audit
+
+```bash
+bash $CLAUDE_PLUGIN_ROOT/skills/mac-optimizer/scripts/audit_environment.sh
+```
+
+### Step 2 — Report
+
+Parse JSON output and present as a severity-ranked markdown table:
+
+| Severity | Finding | Recommended Action | Details |
+|---|---|---|---|
+
+### Step 3 — Ask for consent
+
+If there are fixable issues (duplicate PATH entries, broken symlinks, non-existent directories), list them and ask which to fix.
+
+### Safety rules
+
+- Back up shell configs before modifying: `cp ~/.zshrc ~/.config/mac-optimizer-backups/.zshrc.$(date +%s)`
+- Present PATH consolidation suggestions but don't auto-modify

custom-skills/92-mac-optimizer/commands/mac-packages.md

@@ -0,0 +1,32 @@
+---
+allowed-tools: Bash(bash *audit_packages.sh*), Bash(brew *), Bash(npm *), Bash(pip *), Bash(nvm *), Bash(pyenv *)
+description: Audit package managers (Homebrew, npm, pip, pyenv) for outdated packages and issues
+---
+
+## Your task
+
+Audit all package managers on this Mac.
+
+### Step 1 — Run the audit
+
+```bash
+bash $CLAUDE_PLUGIN_ROOT/skills/mac-optimizer/scripts/audit_packages.sh
+```
+
+### Step 2 — Report
+
+Parse JSON output and present as a severity-ranked markdown table:
+
+| Severity | Finding | Recommended Action | Details |
+|---|---|---|---|
+
+### Step 3 — Ask for consent
+
+List available update actions grouped by risk. Ask which actions to perform.
+
+### Safety notes
+
+- `brew upgrade` is generally safe but can break projects pinned to specific versions
+- Global npm packages are version-independent from project dependencies
+- pip upgrades can break dependency chains — suggest `--dry-run` first
+- Only audit pyenv-managed environments (not system Python)

custom-skills/92-mac-optimizer/commands/mac-resources.md

@@ -0,0 +1,29 @@
+---
+allowed-tools: Bash(bash *audit_resources.sh*), Bash(ps *), Bash(kill *), Bash(df *)
+description: Monitor CPU, memory, disk, battery, and identify resource-hungry processes
+---
+
+## Your task
+
+Check system resource usage on this Mac.
+
+### Step 1 — Run the audit
+
+```bash
+bash $CLAUDE_PLUGIN_ROOT/skills/mac-optimizer/scripts/audit_resources.sh
+```
+
+### Step 2 — Report
+
+Parse JSON output and present as a severity-ranked markdown table:
+
+| Severity | Finding | Recommended Action | Details |
+|---|---|---|---|
+
+### Step 3 — Offer actions
+
+If high-resource processes are found, offer to help. But respect the deny-list:
+
+**Never suggest killing**: kernel_task, launchd, WindowServer, loginwindow, mds, mds_stores, opendirectoryd, coreaudiod, SystemUIServer, Finder, Dock
+
+For user processes consuming excessive resources, ask before terminating.

custom-skills/92-mac-optimizer/commands/mac-security.md

@@ -0,0 +1,25 @@
+---
+allowed-tools: Bash(bash *audit_security.sh*)
+description: Security posture assessment — SIP, Gatekeeper, Firewall, FileVault, SSH, ports
+---
+
+## Your task
+
+Run a read-only security posture assessment.
+
+### Step 1 — Run the audit
+
+```bash
+bash $CLAUDE_PLUGIN_ROOT/skills/mac-optimizer/scripts/audit_security.sh
+```
+
+### Step 2 — Report
+
+Parse JSON output and present as a severity-ranked markdown table:
+
+| Severity | Finding | Recommended Action | Details |
+|---|---|---|---|
+
+### Step 3 — Guidance only
+
+The security module is **read-only**. Present findings and remediation guidance. Do NOT attempt to change security settings. Explain how the user can fix issues themselves via System Settings or Terminal commands.

custom-skills/92-mac-optimizer/skills/mac-optimizer/SKILL.md

@@ -0,0 +1,44 @@
+---
+name: mac-optimizer
+description: macOS system health toolkit — use when user mentions system optimization, cleanup, packages, security audit, disk space, performance, brew updates, cache clearing, or system health on Mac
+version: 1.0.0
+---
+
+# Mac Optimizer
+
+Modular macOS system health toolkit. Runs read-only audits first, then recommends actions with user consent.
+
+## Module Routing
+
+| Keywords | Command |
+|---|---|
+| brew, homebrew, npm, nvm, pip, pyenv, packages, update, outdated | /mac-packages |
+| path, shell, zshrc, environment, env, config, symlink | /mac-environment |
+| security, firewall, sip, gatekeeper, filevault, ports, ssh | /mac-security |
+| cache, cleanup, clean, logs, clutter, disk space, free space, trash | /mac-cleanup |
+| cpu, memory, ram, disk, battery, processes, resources, slow | /mac-resources |
+| doctor, audit, health, full check, everything, system check | /mac-doctor (all) |
+
+Default to **/mac-doctor** when the request is ambiguous.
+
+When the user's request matches a specific module, suggest the appropriate slash command. When the request is broad (e.g., "check my system", "run a health check"), use /mac-doctor.
+
+## Execution Model
+
+Every module follows this flow:
+
+1. **Audit** — run the module's script (read-only)
+2. **Report** — parse JSON output, present findings as a severity-ranked table
+3. **Recommend** — list available actions grouped by risk
+4. **Consent** — ask user which actions to approve
+5. **Act** — execute only approved actions
+
+## Safety Rules
+
+- **Never execute cleanup without explicit user approval**
+- **Always show sizes before deleting anything**
+- **Security module is read-only** — present findings and remediation guidance only
+- **Back up shell configs** before modifying
+- **Process deny-list**: never suggest killing kernel_task, launchd, WindowServer, loginwindow, mds, mds_stores, opendirectoryd, coreaudiod, SystemUIServer, Finder, Dock
+- **No sudo by default** — if an action needs sudo, state why and ask first
+- Docker cleanup uses `docker system prune`, never direct file deletion

custom-skills/92-mac-optimizer/skills/mac-optimizer/references/cleanup-targets.md

@@ -0,0 +1,74 @@
+# Cleanup Targets Reference
+
+## Risk Ratings
+
+| Risk | Meaning |
+|---|---|
+| Safe | Can be deleted without consequence; regenerated automatically |
+| Moderate | Review before deleting; may lose useful data |
+| Risky | May break applications; requires careful inspection |
+| Info only | Report size but do not offer deletion |
+
+## Target Details
+
+### User Logs (Safe)
+- **Path**: `~/Library/Logs/`
+- **Cleanup target**: `user-logs`
+- **Notes**: Application crash reports and debug logs. Regenerated as needed.
+
+### System Logs (Moderate, requires sudo)
+- **Path**: `/var/log/`
+- **Cleanup target**: not available via cleanup_execute.sh (requires sudo)
+- **Notes**: System-level logs. Only clean old/rotated files. Active logs should not be deleted.
+
+### User Caches (Safe, per-app)
+- **Path**: `~/Library/Caches/`
+- **Cleanup target**: `user-caches`
+- **Notes**: App caches regenerated on next use. Some apps may need to re-download data. Browser caches can be large.
+
+### Homebrew Cache (Safe)
+- **Path**: `$(brew --cache)` (typically `~/Library/Caches/Homebrew/`)
+- **Cleanup target**: `brew-cache`
+- **Notes**: Downloaded bottles and source archives. `brew cleanup` handles this properly.
+
+### npm Cache (Safe)
+- **Path**: `~/.npm/_cacache/`
+- **Cleanup target**: `npm-cache`
+- **Notes**: Package download cache. `npm cache clean --force` is the proper way to clear.
+
+### pip Cache (Safe)
+- **Path**: `~/Library/Caches/pip/`
+- **Cleanup target**: `pip-cache`
+- **Notes**: Downloaded wheel/sdist cache. `pip cache purge` is the proper way to clear.
+
+### Xcode DerivedData (Safe)
+- **Path**: `~/Library/Developer/Xcode/DerivedData/`
+- **Cleanup target**: `xcode-derived`
+- **Notes**: Build artifacts and indexes. Rebuilt on next Xcode build. Can grow very large.
+
+### Xcode Archives (Moderate)
+- **Path**: `~/Library/Developer/Xcode/Archives/`
+- **Cleanup target**: `xcode-archives`
+- **Notes**: App Store submission archives. May be needed for symbolication of crash reports. Review before deleting.
+
+### iOS DeviceSupport (Safe)
+- **Path**: `~/Library/Developer/Xcode/iOS DeviceSupport/`
+- **Cleanup target**: `ios-support`
+- **Notes**: Debug symbols for connected iOS devices. Re-downloaded when device connects again.
+
+### Docker (Moderate)
+- **Cleanup target**: `docker`
+- **Notes**: Uses `docker system prune -f`. Removes stopped containers, unused networks, dangling images. Does NOT remove named volumes. Never delete Docker's filesystem directly.
+
+### Trash (Safe)
+- **Path**: `~/.Trash/`
+- **Cleanup target**: `trash`
+- **Notes**: Items in Trash. User has already "deleted" these.
+
+### Old Downloads (Info only)
+- **Path**: `~/Downloads/` (files >90 days old)
+- **Notes**: Report only. User should review manually. Never auto-delete downloads.
+
+### Application Support Remnants (Risky)
+- **Path**: `~/Library/Application Support/` orphaned directories
+- **Notes**: Report only. Directories from uninstalled apps. Difficult to determine automatically which are truly orphaned. Manual review required.

custom-skills/92-mac-optimizer/skills/mac-optimizer/references/packages.md

@@ -0,0 +1,52 @@
+# Package Manager Reference
+
+## Homebrew
+
+### Update workflow
+```bash
+brew update                    # Update Homebrew itself and formulae list
+brew outdated                  # List outdated formulae
+brew outdated --cask           # List outdated casks
+brew upgrade                   # Upgrade all outdated formulae
+brew upgrade <name>            # Upgrade specific formula
+brew upgrade --cask            # Upgrade all casks
+brew cleanup --prune=0         # Remove all cached downloads
+brew autoremove                # Remove orphaned dependencies
+brew doctor                    # Diagnose issues
+```
+
+### Safety notes
+- `brew upgrade` is generally safe but can break projects pinned to specific versions
+- Always check `brew doctor` warnings — some are cosmetic, some indicate real issues
+- `brew autoremove` only removes packages not depended on by anything
+
+## npm / nvm
+
+### Update workflow
+```bash
+nvm ls                         # List installed Node versions
+nvm install --lts              # Install latest LTS
+npm outdated -g                # Check global packages
+npm update -g                  # Update all global packages
+npm cache clean --force        # Clear npm cache
+```
+
+### Safety notes
+- Global npm packages are version-independent from project dependencies
+- Updating global packages won't affect project-level node_modules
+
+## Python / pyenv
+
+### Update workflow
+```bash
+pyenv versions                 # List installed versions
+pyenv install --list           # Available versions
+pip list --outdated            # Outdated packages in current env
+pip install --upgrade <pkg>    # Upgrade specific package
+pip cache purge                # Clear pip cache
+```
+
+### Safety notes
+- Only audit pyenv-managed environments (not system Python)
+- pip upgrades can break dependency chains — suggest `--dry-run` first
+- Virtual environments in project directories are not scanned (out of scope v1)

custom-skills/92-mac-optimizer/skills/mac-optimizer/references/security-checks.md

@@ -0,0 +1,53 @@
+# Security Checks Reference
+
+## SIP (System Integrity Protection)
+- **Check**: `csrutil status`
+- **Expected**: "System Integrity Protection status: enabled."
+- **Remediation**: Reboot to Recovery Mode (Cmd+R), open Terminal, run `csrutil enable`
+- **Severity**: Critical if disabled
+
+## Gatekeeper
+- **Check**: `spctl --status`
+- **Expected**: "assessments enabled"
+- **Remediation**: `sudo spctl --master-enable`
+- **Severity**: Critical if disabled
+
+## Firewall
+- **Check**: `/usr/libexec/ApplicationFirewall/socketfilterfw --getglobalstate`
+- **Fallback**: `defaults read /Library/Preferences/com.apple.alf globalstate` (0=off, 1=on, 2=essential)
+- **Remediation**: System Settings > Network > Firewall > Turn On
+- **Severity**: Critical if disabled
+
+## FileVault
+- **Check**: `fdesetup status`
+- **Expected**: "FileVault is On."
+- **Remediation**: System Settings > Privacy & Security > FileVault > Turn On
+- **Severity**: Critical if disabled (disk not encrypted)
+
+## Open Ports
+- **Check**: `lsof -iTCP -sTCP:LISTEN -nP`
+- **Review**: unexpected services listening on all interfaces (0.0.0.0 or *)
+- **Severity**: Info (review needed, not automatically bad)
+
+## SSH Configuration
+- **Check**: `/etc/ssh/sshd_config`
+- **Flags**: `PasswordAuthentication yes`, `PermitRootLogin yes`
+- **Remediation**: Set to `no` and restart sshd
+- **Severity**: Warning
+
+## Remote Services
+- **Remote Login**: `systemsetup -getremotelogin`
+- **Remote Management**: `defaults read /Library/Preferences/com.apple.RemoteManagement ARD_AllLocalUsers`
+- **Remediation**: Disable in System Settings > General > Sharing
+- **Severity**: Info/Warning depending on context
+
+## Software Updates
+- **Check**: `softwareupdate -l` (can be slow, 30s timeout)
+- **Remediation**: System Settings > General > Software Update
+- **Severity**: Warning if updates available
+
+## Screen Lock
+- **Check**: `defaults -currentHost read com.apple.screensaver idleTime`
+- **Check**: `defaults read com.apple.screensaver askForPassword`
+- **Remediation**: System Settings > Lock Screen
+- **Severity**: Warning if password not required

custom-skills/92-mac-optimizer/skills/mac-optimizer/scripts/audit_cleanup.sh

@@ -0,0 +1,160 @@
+#!/usr/bin/env bash
+# audit_cleanup.sh — Scan caches, logs, and clutter on macOS, report sizes
+# Output: JSON lines to stdout, one per finding
+set -euo pipefail
+
+json_escape() { printf '%s' "$1" | sed 's/\\/\\\\/g; s/"/\\"/g; s/\t/\\t/g' | tr '\n' ' '; }
+
+json_finding() {
+  local severity="$1" finding action details
+  finding=$(json_escape "$2")
+  action=$(json_escape "$3")
+  details=$(json_escape "$4")
+  printf '{"module":"cleanup","severity":"%s","finding":"%s","action":"%s","details":"%s"}\n' \
+    "$severity" "$finding" "$action" "$details"
+}
+
+# Get directory size in human-readable and bytes
+dir_size() {
+  local path="$1"
+  if [ -d "$path" ]; then
+    local bytes=$(du -sk "$path" 2>/dev/null | awk '{print $1}')
+    local human=$(du -sh "$path" 2>/dev/null | awk '{print $1}')
+    echo "${bytes:-0}|${human:-0B}"
+  else
+    echo "0|0B"
+  fi
+}
+
+classify_size() {
+  local kb="$1"
+  if [ "$kb" -gt 1048576 ] 2>/dev/null; then  # > 1GB
+    echo "warning"
+  else
+    echo "info"
+  fi
+}
+
+total_reclaimable_kb=0
+
+# --- User logs ---
+result=$(dir_size "$HOME/Library/Logs")
+IFS='|' read -r kb human <<< "$result"
+total_reclaimable_kb=$((total_reclaimable_kb + kb))
+severity=$(classify_size "$kb")
+json_finding "$severity" "User logs: ${human}" "clean" "~/Library/Logs/ [safe, no sudo]"
+
+# --- System logs ---
+result=$(dir_size "/var/log" 2>/dev/null || echo "0|0B")
+IFS='|' read -r kb human <<< "$result"
+if [ "$kb" -gt 0 ] 2>/dev/null; then
+  severity=$(classify_size "$kb")
+  json_finding "$severity" "System logs: ${human}" "clean" "/var/log/ [moderate, requires sudo]"
+fi
+
+# --- User caches ---
+result=$(dir_size "$HOME/Library/Caches")
+IFS='|' read -r kb human <<< "$result"
+total_reclaimable_kb=$((total_reclaimable_kb + kb))
+severity=$(classify_size "$kb")
+json_finding "$severity" "User caches: ${human}" "clean" "~/Library/Caches/ [safe, per-app]"
+
+# --- Homebrew cache ---
+if command -v brew &>/dev/null; then
+  brew_cache=$(brew --cache 2>/dev/null || echo "")
+  if [ -n "$brew_cache" ] && [ -d "$brew_cache" ]; then
+    result=$(dir_size "$brew_cache")
+    IFS='|' read -r kb human <<< "$result"
+    total_reclaimable_kb=$((total_reclaimable_kb + kb))
+    severity=$(classify_size "$kb")
+    json_finding "$severity" "Homebrew cache: ${human}" "brew cleanup" "$brew_cache [safe]"
+  fi
+fi
+
+# --- npm cache ---
+npm_cache="$HOME/.npm/_cacache"
+if [ -d "$npm_cache" ]; then
+  result=$(dir_size "$npm_cache")
+  IFS='|' read -r kb human <<< "$result"
+  total_reclaimable_kb=$((total_reclaimable_kb + kb))
+  severity=$(classify_size "$kb")
+  json_finding "$severity" "npm cache: ${human}" "npm cache clean --force" "$npm_cache [safe]"
+fi
+
+# --- pip cache ---
+pip_cache="$HOME/Library/Caches/pip"
+if [ -d "$pip_cache" ]; then
+  result=$(dir_size "$pip_cache")
+  IFS='|' read -r kb human <<< "$result"
+  total_reclaimable_kb=$((total_reclaimable_kb + kb))
+  severity=$(classify_size "$kb")
+  json_finding "$severity" "pip cache: ${human}" "pip cache purge" "$pip_cache [safe]"
+fi
+
+# --- Xcode derived data ---
+xcode_derived="$HOME/Library/Developer/Xcode/DerivedData"
+if [ -d "$xcode_derived" ]; then
+  result=$(dir_size "$xcode_derived")
+  IFS='|' read -r kb human <<< "$result"
+  total_reclaimable_kb=$((total_reclaimable_kb + kb))
+  severity=$(classify_size "$kb")
+  json_finding "$severity" "Xcode DerivedData: ${human}" "clean" "$xcode_derived [safe]"
+fi
+
+# --- Xcode archives ---
+xcode_archives="$HOME/Library/Developer/Xcode/Archives"
+if [ -d "$xcode_archives" ]; then
+  result=$(dir_size "$xcode_archives")
+  IFS='|' read -r kb human <<< "$result"
+  total_reclaimable_kb=$((total_reclaimable_kb + kb))
+  severity=$(classify_size "$kb")
+  json_finding "$severity" "Xcode Archives: ${human}" "clean" "$xcode_archives [moderate - check before deleting]"
+fi
+
+# --- iOS Device Support ---
+ios_support="$HOME/Library/Developer/Xcode/iOS DeviceSupport"
+if [ -d "$ios_support" ]; then
+  result=$(dir_size "$ios_support")
+  IFS='|' read -r kb human <<< "$result"
+  total_reclaimable_kb=$((total_reclaimable_kb + kb))
+  severity=$(classify_size "$kb")
+  json_finding "$severity" "iOS DeviceSupport: ${human}" "clean" "$ios_support [safe]"
+fi
+
+# --- Docker ---
+if command -v docker &>/dev/null; then
+  docker_df=$(docker system df 2>/dev/null || echo "")
+  if [ -n "$docker_df" ]; then
+    reclaimable=$(echo "$docker_df" | grep -i "reclaimable" | head -1 || echo "")
+    json_finding "info" "Docker space usage detected" "docker system prune" "Run docker system df for details [use docker system prune to clean]"
+  fi
+else
+  # Skip silently if docker not installed
+  true
+fi
+
+# --- Trash ---
+trash_dir="$HOME/.Trash"
+if [ -d "$trash_dir" ]; then
+  result=$(dir_size "$trash_dir")
+  IFS='|' read -r kb human <<< "$result"
+  total_reclaimable_kb=$((total_reclaimable_kb + kb))
+  if [ "$kb" -gt 0 ] 2>/dev/null; then
+    severity=$(classify_size "$kb")
+    json_finding "$severity" "Trash: ${human}" "empty trash" "$trash_dir [safe]"
+  fi
+fi
+
+# --- Old downloads (report only) ---
+if [ -d "$HOME/Downloads" ]; then
+  old_files=$(find "$HOME/Downloads" -maxdepth 1 -mtime +90 -type f 2>/dev/null | wc -l | tr -d ' ')
+  if [ "$old_files" -gt 0 ] 2>/dev/null; then
+    old_size=$(find "$HOME/Downloads" -maxdepth 1 -mtime +90 -type f -exec du -ck {} + 2>/dev/null | tail -1 | awk '{print $1}')
+    old_human=$(echo "$old_size" | awk '{printf "%.1fM", $1/1024}')
+    json_finding "info" "${old_files} files in Downloads older than 90 days (${old_human})" "review" "Info only - review manually"
+  fi
+fi
+
+# --- Total summary ---
+total_human=$(echo "$total_reclaimable_kb" | awk '{if($1>1048576) printf "%.1fG",$1/1048576; else if($1>1024) printf "%.1fM",$1/1024; else printf "%dK",$1}')
+json_finding "info" "Total scannable space: ${total_human}" "review" "Approx reclaimable across all categories"

custom-skills/92-mac-optimizer/skills/mac-optimizer/scripts/audit_environment.sh

@@ -0,0 +1,127 @@
+#!/usr/bin/env bash
+# audit_environment.sh — Audit shell environment and paths on macOS
+# Output: JSON lines to stdout, one per finding
+set -euo pipefail
+
+json_escape() { printf '%s' "$1" | sed 's/\\/\\\\/g; s/"/\\"/g; s/\t/\\t/g' | tr '\n' ' '; }
+
+json_finding() {
+  local severity="$1" finding action details
+  finding=$(json_escape "$2")
+  action=$(json_escape "$3")
+  details=$(json_escape "$4")
+  printf '{"module":"environment","severity":"%s","finding":"%s","action":"%s","details":"%s"}\n' \
+    "$severity" "$finding" "$action" "$details"
+}
+
+# --- PATH analysis ---
+IFS=':' read -ra path_dirs <<< "$PATH"
+total_dirs=${#path_dirs[@]}
+
+# Duplicate detection (compatible with bash 3)
+duplicates=()
+for i in "${!path_dirs[@]}"; do
+  dir="${path_dirs[$i]}"
+  is_dup=false
+  for j in "${!path_dirs[@]}"; do
+    if [ "$j" -lt "$i" ] && [ "${path_dirs[$j]}" = "$dir" ]; then
+      is_dup=true
+      break
+    fi
+  done
+  if $is_dup; then
+    duplicates+=("$dir")
+  fi
+done
+
+if [ ${#duplicates[@]} -gt 0 ]; then
+  dup_list=$(printf '%s, ' "${duplicates[@]}" | sed 's/, $//')
+  json_finding "warning" "${#duplicates[@]} duplicate PATH entries" "deduplicate" "$dup_list"
+else
+  json_finding "info" "No duplicate PATH entries" "none" "${total_dirs} directories in PATH"
+fi
+
+# Non-existent directories
+missing=()
+for dir in "${path_dirs[@]}"; do
+  if [ ! -d "$dir" ]; then
+    missing+=("$dir")
+  fi
+done
+
+if [ ${#missing[@]} -gt 0 ]; then
+  missing_list=$(printf '%s, ' "${missing[@]}" | sed 's/, $//')
+  json_finding "warning" "${#missing[@]} non-existent directories in PATH" "remove" "$missing_list"
+fi
+
+# --- Broken symlinks ---
+broken_symlinks=()
+for check_dir in /usr/local/bin "$HOME/.local/bin"; do
+  if [ -d "$check_dir" ]; then
+    while IFS= read -r link; do
+      broken_symlinks+=("$link")
+    done < <(find "$check_dir" -maxdepth 1 -type l ! -exec test -e {} \; -print 2>/dev/null || true)
+  fi
+done
+
+if [ ${#broken_symlinks[@]} -gt 0 ]; then
+  broken_list=$(printf '%s, ' "${broken_symlinks[@]}" | sed 's/, $//')
+  json_finding "warning" "${#broken_symlinks[@]} broken symlinks found" "remove" "$broken_list"
+else
+  json_finding "info" "No broken symlinks in bin directories" "none" ""
+fi
+
+# --- Shell config analysis ---
+shell_configs=()
+for cfg in "$HOME/.zshrc" "$HOME/.zprofile" "$HOME/.zshenv" "$HOME/.bash_profile" "$HOME/.bashrc"; do
+  if [ -f "$cfg" ]; then
+    shell_configs+=("$(basename "$cfg")")
+  fi
+done
+json_finding "info" "Shell configs found: ${shell_configs[*]}" "none" ""
+
+# Check for PATH modifications across multiple files
+path_mods=0
+for cfg in "$HOME/.zshrc" "$HOME/.zprofile" "$HOME/.zshenv" "$HOME/.bash_profile" "$HOME/.bashrc"; do
+  if [ -f "$cfg" ]; then
+    count=$(grep -c -E 'export PATH|PATH=' "$cfg" 2>/dev/null || echo 0)
+    count=$(echo "$count" | tr -d '[:space:]')
+    path_mods=$((path_mods + count))
+  fi
+done
+
+if [ "$path_mods" -gt 5 ]; then
+  json_finding "warning" "PATH modified ${path_mods} times across shell configs" "consolidate" "Consider consolidating PATH modifications"
+fi
+
+# --- Environment variable checks ---
+if [ -z "${ANTHROPIC_API_KEY:-}" ]; then
+  json_finding "info" "ANTHROPIC_API_KEY not set" "none" "Set if using Claude API"
+fi
+
+if [ -n "${JAVA_HOME:-}" ] && [ ! -d "$JAVA_HOME" ]; then
+  json_finding "warning" "JAVA_HOME points to non-existent directory" "fix" "$JAVA_HOME"
+fi
+
+# --- Shell startup time ---
+if command -v zsh &>/dev/null; then
+  startup_time=$( { time zsh -i -c exit; } 2>&1 | grep real | awk '{print $2}' || echo "unknown")
+  # Parse the time - handle both formats like "0m0.123s" and "0.123"
+  if echo "$startup_time" | grep -q 'm'; then
+    seconds=$(echo "$startup_time" | sed 's/.*m//' | sed 's/s//')
+  else
+    seconds="$startup_time"
+  fi
+
+  if command -v python3 &>/dev/null; then
+    is_slow=$(python3 -c "print('slow' if float('${seconds}') > 0.5 else 'ok')" 2>/dev/null || echo "ok")
+  else
+    is_slow="ok"
+  fi
+
+  if [ "$is_slow" = "slow" ]; then
+    json_finding "warning" "Shell startup is slow (${startup_time})" "optimize" "Consider profiling with zsh -xv"
+  else
+    json_finding "info" "Shell startup time: ${startup_time}" "none" ""
+  fi
+fi

custom-skills/92-mac-optimizer/skills/mac-optimizer/scripts/audit_packages.sh

@@ -0,0 +1,118 @@
+#!/usr/bin/env bash
+# audit_packages.sh — Audit package managers on macOS
+# Output: JSON lines to stdout, one per finding
+set -euo pipefail
+
+json_escape() { printf '%s' "$1" | sed 's/\\/\\\\/g; s/"/\\"/g; s/\t/\\t/g' | tr '\n' ' '; }
+
+json_finding() {
+  local severity="$1" finding action details
+  finding=$(json_escape "$2")
+  action=$(json_escape "$3")
+  details=$(json_escape "$4")
+  printf '{"module":"packages","severity":"%s","finding":"%s","action":"%s","details":"%s"}\n' \
+    "$severity" "$finding" "$action" "$details"
+}
+
+# --- Homebrew ---
+if command -v brew &>/dev/null; then
+  echo '{"module":"packages","severity":"info","finding":"Homebrew detected","action":"none","details":"'$(brew --version | head -1)'"}'
+
+  # brew update
+  brew update --quiet 2>/dev/null || true
+
+  # outdated formulae
+  outdated=$(brew outdated --json=v2 2>/dev/null || echo '{}')
+  formula_count=$(echo "$outdated" | python3 -c "import sys,json; d=json.load(sys.stdin); print(len(d.get('formulae',[])))" 2>/dev/null || echo 0)
+  cask_count=$(echo "$outdated" | python3 -c "import sys,json; d=json.load(sys.stdin); print(len(d.get('casks',[])))" 2>/dev/null || echo 0)
+
+  if [ "$formula_count" -gt 0 ] 2>/dev/null; then
+    formula_list=$(echo "$outdated" | python3 -c "
+import sys,json
+d=json.load(sys.stdin)
+names=[f['name'] for f in d.get('formulae',[])]
+print(', '.join(names[:10]))
+if len(names)>10: print(f'... and {len(names)-10} more')
+" 2>/dev/null || echo "")
+    json_finding "warning" "${formula_count} Homebrew formulae outdated" "brew upgrade" "$formula_list"
+  fi
+
+  if [ "$cask_count" -gt 0 ] 2>/dev/null; then
+    json_finding "warning" "${cask_count} Homebrew casks outdated" "brew upgrade --cask" ""
+  fi
+
+  if [ "$formula_count" -eq 0 ] && [ "$cask_count" -eq 0 ] 2>/dev/null; then
+    json_finding "info" "All Homebrew packages up to date" "none" ""
+  fi
+
+  # brew doctor
+  doctor_output=$(brew doctor 2>&1 || true)
+  doctor_warnings=$(echo "$doctor_output" | grep -c "Warning:" 2>/dev/null || echo 0)
+  if [ "$doctor_warnings" -gt 0 ] 2>/dev/null; then
+    json_finding "warning" "brew doctor found ${doctor_warnings} warning(s)" "brew doctor" "Run brew doctor for details"
+  fi
+
+  # autoremove candidates
+  autoremove_output=$(brew autoremove --dry-run 2>/dev/null || echo "")
+  orphan_count=$(echo "$autoremove_output" | grep -c "^=" 2>/dev/null || echo 0)
+  if echo "$autoremove_output" | grep -q "would remove" 2>/dev/null; then
+    json_finding "info" "Orphaned Homebrew dependencies found" "brew autoremove" "$autoremove_output"
+  fi
+else
+  json_finding "info" "Homebrew not installed" "none" "Consider installing from https://brew.sh"
+fi
+
+# --- npm / nvm ---
+if command -v nvm &>/dev/null || [ -d "$HOME/.nvm" ]; then
+  # Source nvm if available
+  export NVM_DIR="${NVM_DIR:-$HOME/.nvm}"
+  [ -s "$NVM_DIR/nvm.sh" ] && source "$NVM_DIR/nvm.sh" 2>/dev/null
+
+  if command -v nvm &>/dev/null; then
+    node_versions=$(nvm ls --no-colors 2>/dev/null | grep -c "v[0-9]" || echo 0)
+    current_node=$(nvm current 2>/dev/null || echo "none")
+    json_finding "info" "nvm detected: ${node_versions} version(s), current: ${current_node}" "none" ""
+  fi
+fi
+
+if command -v npm &>/dev/null; then
+  json_finding "info" "npm detected" "none" "$(npm --version 2>/dev/null)"
+
+  npm_outdated=$(npm outdated -g --json 2>/dev/null || echo '{}')
+  npm_outdated_count=$(echo "$npm_outdated" | python3 -c "import sys,json; print(len(json.load(sys.stdin)))" 2>/dev/null || echo 0)
+
+  if [ "$npm_outdated_count" -gt 0 ] 2>/dev/null; then
+    json_finding "warning" "${npm_outdated_count} global npm packages outdated" "npm update -g" ""
+  fi
+else
+  json_finding "info" "npm not installed" "none" ""
+fi
+
+# --- Python / pyenv ---
+if command -v pyenv &>/dev/null; then
+  pyenv_versions=$(pyenv versions --bare 2>/dev/null | wc -l | tr -d ' ')
+  current_python=$(pyenv version-name 2>/dev/null || echo "system")
+  json_finding "info" "pyenv detected: ${pyenv_versions} version(s), current: ${current_python}" "none" ""
+
+  # Check pip outdated for current environment
+  if command -v pip &>/dev/null || command -v pip3 &>/dev/null; then
+    pip_cmd=$(command -v pip3 || command -v pip)
+    pip_outdated=$($pip_cmd list --outdated --format=json 2>/dev/null || echo '[]')
+    pip_count=$(echo "$pip_outdated" | python3 -c "import sys,json; print(len(json.load(sys.stdin)))" 2>/dev/null || echo 0)
+
+    if [ "$pip_count" -gt 0 ] 2>/dev/null; then
+      json_finding "warning" "${pip_count} pip packages outdated in current env" "pip install --upgrade" ""
+    fi
+  fi
+elif command -v python3 &>/dev/null; then
+  py_version=$(python3 --version 2>/dev/null || echo "unknown")
+  json_finding "info" "System Python: ${py_version} (no pyenv)" "none" ""
+fi
+
+# --- Other package managers (presence detection only) ---
+for mgr in yarn pnpm cargo go gem composer; do
+  if command -v "$mgr" &>/dev/null; then
+    version=$($mgr --version 2>/dev/null | head -1 || echo "unknown")
+    json_finding "info" "${mgr} detected: ${version}" "none" "Presence check only"
+  fi
+done

custom-skills/92-mac-optimizer/skills/mac-optimizer/scripts/audit_resources.sh

@@ -0,0 +1,143 @@
+#!/usr/bin/env bash
+# audit_resources.sh — Monitor CPU, memory, disk, battery on macOS
+# Output: JSON lines to stdout, one per finding
+set -euo pipefail
+
+json_escape() { printf '%s' "$1" | sed 's/\\/\\\\/g; s/"/\\"/g; s/\t/\\t/g' | tr '\n' ' '; }
+
+json_finding() {
+  local severity="$1" finding action details
+  finding=$(json_escape "$2")
+  action=$(json_escape "$3")
+  details=$(json_escape "$4")
+  printf '{"module":"resources","severity":"%s","finding":"%s","action":"%s","details":"%s"}\n' \
+    "$severity" "$finding" "$action" "$details"
+}
+
+# Process deny-list (never suggest termination)
+DENY_LIST="kernel_task|launchd|WindowServer|loginwindow|mds|mds_stores|opendirectoryd|coreaudiod|SystemUIServer|Finder|Dock"
+
+# --- CPU ---
+load_avg=$(sysctl -n vm.loadavg 2>/dev/null | tr -d '{}' | awk '{print $1}')
+cpu_count=$(sysctl -n hw.ncpu 2>/dev/null || echo 1)
+
+if command -v python3 &>/dev/null; then
+  cpu_severity=$(python3 -c "
+load=$load_avg; cores=$cpu_count
+if load > cores * 2: print('critical')
+elif load > cores: print('warning')
+else: print('info')
+" 2>/dev/null || echo "info")
+else
+  cpu_severity="info"
+fi
+
+json_finding "$cpu_severity" "Load average: ${load_avg} (${cpu_count} cores)" "review" ""
+
+# Top CPU-consuming processes (excluding deny-list from action suggestions)
+top_cpu=$(ps aux | sort -nrk 3 | head -5 || echo "")
+if [ -n "$top_cpu" ]; then
+  while IFS= read -r line; do
+    proc_name=$(echo "$line" | awk '{print $11}' | xargs basename 2>/dev/null || echo "unknown")
+    cpu_pct=$(echo "$line" | awk '{print $3}')
+    mem_pct=$(echo "$line" | awk '{print $4}')
+    pid=$(echo "$line" | awk '{print $2}')
+
+    # Skip low-usage processes
+    is_high=$(python3 -c "print('yes' if float('${cpu_pct}') > 10 else 'no')" 2>/dev/null || echo "no")
+    if [ "$is_high" = "yes" ]; then
+      if echo "$proc_name" | grep -qE "$DENY_LIST"; then
+        json_finding "info" "High CPU: ${proc_name} (${cpu_pct}% CPU, PID ${pid})" "none" "System process - do not terminate"
+      else
+        json_finding "warning" "High CPU: ${proc_name} (${cpu_pct}% CPU, PID ${pid})" "quit" "User process - can be terminated"
+      fi
+    fi
+  done <<< "$top_cpu"
+fi
+
+# --- Memory ---
+vm_stat_output=$(vm_stat 2>/dev/null || echo "")
+if [ -n "$vm_stat_output" ]; then
+  page_size=$(vm_stat | head -1 | grep -o '[0-9]*' || echo 16384)
+
+  free_pages=$(echo "$vm_stat_output" | grep "Pages free" | awk '{print $3}' | tr -d '.')
+  active_pages=$(echo "$vm_stat_output" | grep "Pages active" | awk '{print $3}' | tr -d '.')
+  inactive_pages=$(echo "$vm_stat_output" | grep "Pages inactive" | awk '{print $3}' | tr -d '.')
+  wired_pages=$(echo "$vm_stat_output" | grep "Pages wired" | awk '{print $4}' | tr -d '.')
+  compressed_pages=$(echo "$vm_stat_output" | grep "Pages stored in compressor" | awk '{print $5}' | tr -d '.' || echo 0)
+
+  if command -v python3 &>/dev/null; then
+    mem_summary=$(python3 -c "
+ps=${page_size}
+free_mb = int(${free_pages:-0}) * ps / 1048576
+active_mb = int(${active_pages:-0}) * ps / 1048576
+inactive_mb = int(${inactive_pages:-0}) * ps / 1048576
+wired_mb = int(${wired_pages:-0}) * ps / 1048576
+compressed_mb = int(${compressed_pages:-0}) * ps / 1048576
+used_mb = active_mb + wired_mb + compressed_mb
+total_mb = free_mb + active_mb + inactive_mb + wired_mb + compressed_mb
+pct = used_mb / total_mb * 100 if total_mb > 0 else 0
+print(f'{used_mb:.0f}MB used / {total_mb:.0f}MB total ({pct:.0f}%)')
+if pct > 90: print('SEVERITY:critical')
+elif pct > 75: print('SEVERITY:warning')
+else: print('SEVERITY:info')
+" 2>/dev/null || echo "unknown")
+    mem_severity=$(echo "$mem_summary" | grep "SEVERITY:" | cut -d: -f2)
+    mem_info=$(echo "$mem_summary" | head -1)
+    json_finding "${mem_severity:-info}" "Memory: ${mem_info}" "review" ""
+  fi
+fi
+
+# --- Swap ---
+swap_info=$(sysctl vm.swapusage 2>/dev/null || echo "")
+if [ -n "$swap_info" ]; then
+  swap_used=$(echo "$swap_info" | grep -o "used = [0-9.]*M" | awk '{print $3}' | tr -d 'M')
+  if [ -n "$swap_used" ] && command -v python3 &>/dev/null; then
+    swap_severity=$(python3 -c "
+s=float('${swap_used}')
+if s > 4096: print('warning')
+elif s > 1024: print('info')
+else: print('info')
+" 2>/dev/null || echo "info")
+    json_finding "$swap_severity" "Swap: ${swap_used}MB used" "review" "$swap_info"
+  fi
+fi
+
+# --- Disk usage ---
+disk_info=$(df -h / 2>/dev/null | tail -1)
+if [ -n "$disk_info" ]; then
+  disk_used_pct=$(echo "$disk_info" | awk '{print $5}' | tr -d '%')
+  disk_avail=$(echo "$disk_info" | awk '{print $4}')
+  disk_total=$(echo "$disk_info" | awk '{print $2}')
+
+  if [ "$disk_used_pct" -gt 90 ] 2>/dev/null; then
+    json_finding "critical" "Disk ${disk_used_pct}% full (${disk_avail} free of ${disk_total})" "cleanup" "Consider running cleanup module"
+  elif [ "$disk_used_pct" -gt 75 ] 2>/dev/null; then
+    json_finding "warning" "Disk ${disk_used_pct}% full (${disk_avail} free of ${disk_total})" "monitor" ""
+  else
+    json_finding "info" "Disk ${disk_used_pct}% full (${disk_avail} free of ${disk_total})" "none" ""
+  fi
+fi
+
+# --- Large directories (top 5 in home) ---
+if command -v du &>/dev/null; then
+  large_dirs=$(du -sh "$HOME"/*/ "$HOME"/.[!.]* 2>/dev/null | sort -hr | head -5 || echo "")
+  if [ -n "$large_dirs" ]; then
+    dir_summary=$(echo "$large_dirs" | awk '{printf "%s (%s), ", $2, $1}' | sed 's/, $//')
+    json_finding "info" "Largest directories in home" "review" "$dir_summary"
+  fi
+fi
+
+# --- Battery (laptops only) ---
+battery_info=$(system_profiler SPPowerDataType 2>/dev/null || echo "")
+if echo "$battery_info" | grep -q "Cycle Count"; then
+  cycle_count=$(echo "$battery_info" | grep "Cycle Count" | awk '{print $NF}')
+  condition=$(echo "$battery_info" | grep "Condition" | awk '{print $NF}')
+  max_capacity=$(echo "$battery_info" | grep "Maximum Capacity" | awk '{print $NF}' || echo "unknown")
+
+  if [ "$condition" = "Normal" ]; then
+    json_finding "info" "Battery: ${condition}, ${cycle_count} cycles, ${max_capacity} capacity" "none" ""
+  else
+    json_finding "warning" "Battery: ${condition}, ${cycle_count} cycles, ${max_capacity} capacity" "review" "Battery may need service"
+  fi
+fi

custom-skills/92-mac-optimizer/skills/mac-optimizer/scripts/audit_security.sh

@@ -0,0 +1,122 @@
+#!/usr/bin/env bash
+# audit_security.sh — Security posture assessment for macOS (read-only)
+# Output: JSON lines to stdout, one per finding
+set -euo pipefail
+
+json_escape() { printf '%s' "$1" | sed 's/\\/\\\\/g; s/"/\\"/g; s/\t/\\t/g' | tr '\n' ' '; }
+
+json_finding() {
+  local severity="$1" finding action details
+  finding=$(json_escape "$2")
+  action=$(json_escape "$3")
+  details=$(json_escape "$4")
+  printf '{"module":"security","severity":"%s","finding":"%s","action":"%s","details":"%s"}\n' \
+    "$severity" "$finding" "$action" "$details"
+}
+
+# --- SIP (System Integrity Protection) ---
+sip_status=$(csrutil status 2>/dev/null || echo "unknown")
+if echo "$sip_status" | grep -q "enabled"; then
+  json_finding "info" "SIP enabled" "none" ""
+elif echo "$sip_status" | grep -q "disabled"; then
+  json_finding "critical" "SIP is disabled" "report" "System Integrity Protection should be enabled"
+else
+  json_finding "warning" "SIP status unknown" "report" "$sip_status"
+fi
+
+# --- Gatekeeper ---
+gatekeeper_status=$(spctl --status 2>/dev/null || echo "unknown")
+if echo "$gatekeeper_status" | grep -q "assessments enabled"; then
+  json_finding "info" "Gatekeeper enabled" "none" ""
+elif echo "$gatekeeper_status" | grep -q "assessments disabled"; then
+  json_finding "critical" "Gatekeeper is disabled" "report" "Enable via: sudo spctl --master-enable"
+else
+  json_finding "warning" "Gatekeeper status unknown" "report" "$gatekeeper_status"
+fi
+
+# --- Firewall ---
+fw_tool="/usr/libexec/ApplicationFirewall/socketfilterfw"
+if [ -x "$fw_tool" ]; then
+  fw_status=$("$fw_tool" --getglobalstate 2>/dev/null || echo "unknown")
+  if echo "$fw_status" | grep -qi "enabled"; then
+    json_finding "info" "Firewall enabled" "none" ""
+  else
+    json_finding "critical" "Firewall is disabled" "report" "Enable in System Settings > Network > Firewall"
+  fi
+else
+  # Fallback to defaults
+  fw_default=$(defaults read /Library/Preferences/com.apple.alf globalstate 2>/dev/null || echo "unknown")
+  case "$fw_default" in
+    0) json_finding "critical" "Firewall is disabled" "report" "Enable in System Settings > Network > Firewall" ;;
+    1|2) json_finding "info" "Firewall enabled" "none" "" ;;
+    *) json_finding "warning" "Firewall status unknown" "report" "" ;;
+  esac
+fi
+
+# --- FileVault ---
+fv_status=$(fdesetup status 2>/dev/null || echo "unknown")
+if echo "$fv_status" | grep -q "FileVault is On"; then
+  json_finding "info" "FileVault enabled (disk encryption)" "none" ""
+elif echo "$fv_status" | grep -q "FileVault is Off"; then
+  json_finding "critical" "FileVault is off (disk not encrypted)" "report" "Enable in System Settings > Privacy and Security > FileVault"
+else
+  json_finding "warning" "FileVault status unknown" "report" "$fv_status"
+fi
+
+# --- Open listening ports ---
+listening_ports=$(lsof -iTCP -sTCP:LISTEN -nP 2>/dev/null | tail -n +2 || echo "")
+port_count=$(echo "$listening_ports" | grep -c . 2>/dev/null || echo 0)
+
+if [ "$port_count" -gt 0 ]; then
+  # Extract unique port/process combos
+  port_summary=$(echo "$listening_ports" | awk '{print $1":"$9}' | sort -u | head -10 | tr '\n' ', ' | sed 's/,$//')
+  json_finding "info" "${port_count} listening TCP connections" "review" "$port_summary"
+fi
+
+# --- SSH config ---
+ssh_config="/etc/ssh/sshd_config"
+if [ -f "$ssh_config" ]; then
+  # Check password auth
+  if grep -qi "^PasswordAuthentication yes" "$ssh_config" 2>/dev/null; then
+    json_finding "warning" "SSH password authentication enabled" "report" "Consider key-based auth only"
+  fi
+  # Check root login
+  if grep -qi "^PermitRootLogin yes" "$ssh_config" 2>/dev/null; then
+    json_finding "warning" "SSH root login permitted" "report" "Consider disabling root SSH login"
+  fi
+fi
+
+# --- Remote login ---
+remote_login=$(systemsetup -getremotelogin 2>/dev/null || echo "unknown")
+if echo "$remote_login" | grep -qi "on"; then
+  json_finding "info" "Remote Login (SSH) is enabled" "review" "Disable if not needed: System Settings > General > Sharing"
+fi
+
+# --- Remote management ---
+remote_mgmt=$(defaults read /Library/Preferences/com.apple.RemoteManagement ARD_AllLocalUsers 2>/dev/null || echo "not configured")
+if [ "$remote_mgmt" = "1" ]; then
+  json_finding "warning" "Remote Management enabled for all users" "review" "Check System Settings > General > Sharing"
+fi
+
+# --- Software updates ---
+# Just check if updates are available (this can be slow, so we time-limit it)
+# macOS lacks GNU timeout — use perl alarm as a portable alternative
+update_check=$(perl -e 'alarm 30; exec @ARGV' -- softwareupdate -l 2>&1 || echo "timeout or error")
+if echo "$update_check" | grep -q "No new software available"; then
+  json_finding "info" "macOS software is up to date" "none" ""
+elif echo "$update_check" | grep -q "timeout or error"; then
+  json_finding "info" "Software update check timed out" "none" "Run softwareupdate -l manually"
+else
+  update_count=$(echo "$update_check" | grep -c "^\*" 2>/dev/null || echo 0)
+  json_finding "warning" "${update_count} software update(s) available" "softwareupdate" "Run: softwareupdate -l for details"
+fi
+
+# --- Screen lock ---
+screen_lock_delay=$(defaults -currentHost read com.apple.screensaver idleTime 2>/dev/null || echo "not set")
+ask_password=$(defaults read com.apple.screensaver askForPassword 2>/dev/null || echo "unknown")
+
+if [ "$ask_password" = "0" ]; then
+  json_finding "warning" "Screen lock password not required" "report" "Enable in System Settings > Lock Screen"
+elif [ "$screen_lock_delay" != "not set" ] && [ "$screen_lock_delay" -gt 300 ] 2>/dev/null; then
+  json_finding "info" "Screen lock delay: ${screen_lock_delay}s (consider reducing)" "report" ""
+fi

custom-skills/92-mac-optimizer/skills/mac-optimizer/scripts/cleanup_execute.sh

@@ -0,0 +1,169 @@
+#!/usr/bin/env bash
+# cleanup_execute.sh — Execute cleanup actions on macOS
+# Usage: cleanup_execute.sh [--dry-run|--execute] <target> [<target>...]
+# Targets: user-logs, user-caches, brew-cache, npm-cache, pip-cache,
+#          xcode-derived, xcode-archives, ios-support, docker, trash
+set -euo pipefail
+
+MODE="dry-run"
+TARGETS=()
+BACKUP_DIR="${BACKUP_DIR:-$HOME/.config/mac-optimizer-backups}"
+
+usage() {
+  echo "Usage: $0 [--dry-run|--execute] <target> [<target>...]"
+  echo ""
+  echo "Options:"
+  echo "  --dry-run   Show what would be deleted (default)"
+  echo "  --execute   Actually perform cleanup"
+  echo ""
+  echo "Targets:"
+  echo "  user-logs       ~/Library/Logs/"
+  echo "  user-caches     ~/Library/Caches/"
+  echo "  brew-cache      Homebrew download cache"
+  echo "  npm-cache       npm cache"
+  echo "  pip-cache       pip cache"
+  echo "  xcode-derived   Xcode DerivedData"
+  echo "  xcode-archives  Xcode Archives"
+  echo "  ios-support     iOS DeviceSupport files"
+  echo "  docker          Docker system prune"
+  echo "  trash           Empty Trash"
+  exit 1
+}
+
+# Parse args
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --dry-run) MODE="dry-run"; shift ;;
+    --execute) MODE="execute"; shift ;;
+    --help|-h) usage ;;
+    *) TARGETS+=("$1"); shift ;;
+  esac
+done
+
+if [ ${#TARGETS[@]} -eq 0 ]; then
+  echo "Error: No targets specified"
+  usage
+fi
+
+log_action() {
+  local target="$1" action="$2" size="$3"
+  echo "[${MODE}] ${target}: ${action} (${size})"
+}
+
+clean_dir() {
+  local name="$1" path="$2"
+  if [ ! -d "$path" ]; then
+    echo "[skip] ${name}: directory not found (${path})"
+    return
+  fi
+  local size=$(du -sh "$path" 2>/dev/null | awk '{print $1}')
+  if [ "$MODE" = "dry-run" ]; then
+    log_action "$name" "would remove contents of ${path}" "$size"
+  else
+    log_action "$name" "removing contents of ${path}" "$size"
+    find "$path" -mindepth 1 -delete 2>/dev/null || {
+      # Fallback: remove what we can
+      find "$path" -mindepth 1 -maxdepth 1 -exec rm -rf {} + 2>/dev/null || true
+    }
+    echo "[done] ${name}: cleaned"
+  fi
+}
+
+for target in "${TARGETS[@]}"; do
+  case "$target" in
+    user-logs)
+      clean_dir "User Logs" "$HOME/Library/Logs"
+      ;;
+    user-caches)
+      clean_dir "User Caches" "$HOME/Library/Caches"
+      ;;
+    brew-cache)
+      if command -v brew &>/dev/null; then
+        brew_cache=$(brew --cache 2>/dev/null || echo "")
+        if [ -n "$brew_cache" ]; then
+          size=$(du -sh "$brew_cache" 2>/dev/null | awk '{print $1}')
+          if [ "$MODE" = "dry-run" ]; then
+            log_action "Homebrew Cache" "would run brew cleanup" "$size"
+          else
+            log_action "Homebrew Cache" "running brew cleanup" "$size"
+            brew cleanup --prune=0 2>/dev/null || true
+            echo "[done] Homebrew Cache: cleaned"
+          fi
+        fi
+      else
+        echo "[skip] brew-cache: Homebrew not installed"
+      fi
+      ;;
+    npm-cache)
+      if command -v npm &>/dev/null; then
+        npm_cache="$HOME/.npm/_cacache"
+        if [ -d "$npm_cache" ]; then
+          size=$(du -sh "$npm_cache" 2>/dev/null | awk '{print $1}')
+          if [ "$MODE" = "dry-run" ]; then
+            log_action "npm Cache" "would run npm cache clean --force" "$size"
+          else
+            log_action "npm Cache" "running npm cache clean" "$size"
+            npm cache clean --force 2>/dev/null || true
+            echo "[done] npm Cache: cleaned"
+          fi
+        fi
+      else
+        echo "[skip] npm-cache: npm not installed"
+      fi
+      ;;
+    pip-cache)
+      pip_cache="$HOME/Library/Caches/pip"
+      if [ -d "$pip_cache" ]; then
+        size=$(du -sh "$pip_cache" 2>/dev/null | awk '{print $1}')
+        if [ "$MODE" = "dry-run" ]; then
+          log_action "pip Cache" "would run pip cache purge" "$size"
+        else
+          log_action "pip Cache" "running pip cache purge" "$size"
+          pip3 cache purge 2>/dev/null || pip cache purge 2>/dev/null || true
+          echo "[done] pip Cache: cleaned"
+        fi
+      else
+        echo "[skip] pip-cache: no pip cache found"
+      fi
+      ;;
+    xcode-derived)
+      clean_dir "Xcode DerivedData" "$HOME/Library/Developer/Xcode/DerivedData"
+      ;;
+    xcode-archives)
+      clean_dir "Xcode Archives" "$HOME/Library/Developer/Xcode/Archives"
+      ;;
+    ios-support)
+      clean_dir "iOS DeviceSupport" "$HOME/Library/Developer/Xcode/iOS DeviceSupport"
+      ;;
+    docker)
+      if command -v docker &>/dev/null; then
+        if [ "$MODE" = "dry-run" ]; then
+          echo "[dry-run] Docker: would run docker system prune"
+          docker system df 2>/dev/null || echo "  (Docker not running)"
+        else
+          echo "[execute] Docker: running docker system prune -f"
+          docker system prune -f 2>/dev/null || echo "  Docker prune failed (is Docker running?)"
+        fi
+      else
+        echo "[skip] docker: Docker not installed"
+      fi
+      ;;
+    trash)
+      trash_dir="$HOME/.Trash"
+      if [ -d "$trash_dir" ]; then
+        size=$(du -sh "$trash_dir" 2>/dev/null | awk '{print $1}')
+        if [ "$MODE" = "dry-run" ]; then
+          log_action "Trash" "would empty Trash" "$size"
+        else
+          log_action "Trash" "emptying Trash" "$size"
+          rm -rf "$trash_dir"/* 2>/dev/null || true
+          rm -rf "$trash_dir"/.[!.]* 2>/dev/null || true
+          echo "[done] Trash: emptied"
+        fi
+      fi
+      ;;
+    *)
+      echo "[error] Unknown target: ${target}"
+      ;;
+  esac
+done

custom-skills/93-tui-designer/README.md

@@ -0,0 +1,28 @@
+# 93-tui-designer
+
+Build Norton Commander / Gopher style TUI wizard interfaces for any Python CLI tool using Rich.
+
+## Purpose
+
+Reusable patterns and battle-tested gotchas for building retro-style terminal wizards with:
+- Dual-panel layout (status + content)
+- Stack-based Gopher navigation (numbered menus, Back, Home)
+- Arrow-key list selector for long option lists
+- Bilingual i18n with runtime toggle
+- Keyboard-driven input (F-keys with alphanumeric fallbacks)
+- Three-tier responsive layout (wide/narrow/single panel)
+
+## Structure
+
+```
+93-tui-designer/
+  code/SKILL.md              # Main skill (architecture, patterns, gotchas)
+  shared/references/
+    dtm-wizard-reference.md  # DTM Agent implementation reference
+  docs/                      # Future: logs, lessons learned
+```
+
+## First Implementation
+
+DTM Agent TUI Wizard — 20 files, 21 screens, 29 tests.
+See `shared/references/dtm-wizard-reference.md` for details.

custom-skills/93-tui-designer/code/SKILL.md

@@ -0,0 +1,303 @@
+---
+name: tui-designer
+description: Build Norton Commander / Gopher style TUI wizard interfaces for CLI tools using Python Rich. Covers architecture, components, keyboard input, bilingual i18n, and battle-tested gotchas.
+version: 1.0.0
+triggers:
+  - "build TUI", "TUI wizard", "terminal UI", "CLI wizard"
+  - "Norton Commander style", "Gopher style", "retro TUI"
+  - "Rich TUI", "interactive CLI", "keyboard navigation"
+  - "dual panel interface", "terminal wizard"
+tools:
+  - Read
+  - Write
+  - Edit
+  - Bash
+  - Grep
+  - Glob
+---
+
+# TUI Designer
+
+Build retro-style terminal wizard interfaces (Norton Commander + Gopher) for any Python CLI tool using the Rich library. No new dependencies — Rich + stdlib only.
+
+## When to Use
+
+- Building an interactive CLI wizard or setup flow
+- Adding keyboard-driven navigation to an existing CLI tool
+- Creating dual-panel terminal interfaces with status + menus
+- Building bilingual (or multi-language) terminal interfaces
+
+## Architecture Blueprint
+
+### Component Structure
+
+```
+src/{project}/tui/
+  __init__.py          # Public API: launch_tui()
+  i18n.py              # String registry with runtime language toggle
+  input.py             # Raw tty/termios keypress reader + escape parser
+  themes.py            # Color scheme + NO_COLOR support
+  widgets.py           # Shared primitives (status icons, mini-tables)
+  breadcrumb.py        # Top navigation path bar
+  function_bar.py      # Bottom F-key shortcut bar
+  status_panel.py      # Left panel: system health / status
+  menu.py              # Right panel: numbered menu items
+  dialog.py            # Modal overlays (confirm, input, error)
+  core.py              # Layout engine (assembles frame)
+  runner.py            # Main event loop + screen stack
+  selector.py          # Arrow-key list selector for long lists
+  renderers.py         # Content renderers for leaf screens
+  screens/
+    __init__.py         # Screen/MenuItem/Action dataclasses + registry
+    home.py             # Root screen
+    {category}.py       # One file per menu category
+```
+
+### Data Flow
+
+```
+User keypress
+  -> input.py (parse_key_bytes -> normalize_key)
+  -> runner.py (_handle_key dispatches)
+     -> Navigation: ScreenStack push/pop
+     -> F-keys: toggle language, refresh, help, quit
+     -> Digits: jump cursor or push screen
+     -> Arrows: ListSelector cursor movement
+     -> Enter: confirm selection via key_handler callback
+  -> core.py (render_frame assembles panels)
+  -> Console output
+```
+
+## Screen System
+
+### Screen Dataclass
+
+```python
+@dataclass
+class Screen:
+    id: str                          # "setup.credentials"
+    title: str                       # i18n key
+    breadcrumb: list[str]            # i18n key path
+    menu_items: list[MenuItem]       # For menu screens
+    content_renderer: Callable | None  # For leaf screens: (console, status_data) -> str
+    key_handler: Callable | None     # For interactive leaves: (app, key) -> bool
+    on_enter: Callable | None        # Runs when screen is pushed
+```
+
+### Navigation Model (Gopher-style stack)
+
+```
+ScreenStack (LIFO):
+  [1-9]  = push screen (menu) or jump cursor (leaf)
+  [B]    = pop (back)
+  [H]    = clear to root
+  [Q]    = quit with confirm
+  Enter  = confirm selection on leaf screens
+  Up/Down = navigate ListSelector items
+```
+
+### Screen Registration Pattern
+
+```python
+# screens/setup.py
+from myapp.tui.screens import Screen, MenuItem, register_screen
+from myapp.tui.renderers import render_credentials, handle_credential_key
+
+register_screen(Screen(
+    id="setup.credentials",
+    title="setup.credentials",
+    breadcrumb=["nav.home", "home.setup", "setup.credentials"],
+    content_renderer=render_credentials,
+    key_handler=handle_credential_key,  # For interactive leaves
+))
+```
+
+## Keyboard Input
+
+### Escape Sequence Parser
+
+```python
+# input.py — stdlib only, no dependencies
+import tty, termios, select, sys, os
+
+def read_key() -> str:
+    fd = sys.stdin.fileno()
+    old = termios.tcgetattr(fd)
+    try:
+        tty.setraw(fd)
+        first = os.read(fd, 1)
+        if first == b"\x1b":
+            ready, _, _ = select.select([fd], [], [], 0.05)  # 50ms timeout
+            if ready:
+                rest = os.read(fd, 5)
+                return parse_escape(first + rest)
+            return "escape"
+        return parse_single(first)
+    finally:
+        termios.tcsetattr(fd, termios.TCSADRAIN, old)
+```
+
+### F-key Alphanumeric Fallbacks
+
+Always provide fallbacks — terminals intercept F-keys unpredictably:
+
+| F-key | Fallback | Action |
+|-------|----------|--------|
+| F1 | ? | Help |
+| F3 | l | Language toggle |
+| F5 | r | Refresh |
+| F10 | q | Quit |
+
+## ListSelector Component
+
+For screens with 10+ selectable items, use `ListSelector` instead of number-only input:
+
+```python
+selector = ListSelector(
+    items=[SelectableItem(label="model-name", status="ready", data={...})],
+    on_select=my_callback,
+    header="Select model:",     # str or Callable[[], str] for dynamic headers
+    footer="Hint text",
+)
+# In content_renderer: return selector.render()
+# In key_handler: return selector.handle_key(app, key)
+```
+
+- Arrow Up/Down moves visible `>` cursor
+- Enter/Space confirms selection
+- 1-9 jumps cursor (does NOT auto-select — user must press Enter)
+- Sections headers group items visually
+- Callable headers re-evaluate on each render (for dynamic "Active:" display)
+
+## Line Input Mode
+
+For screens requiring text input (file paths, names, search), use `read_line()`:
+
+```python
+from myapp.tui.input import read_line
+
+# In a key_handler:
+def handle_my_key(app, key):
+    if key == "p":
+        app.console.print("Enter file path: ", end="")
+        path = read_line()
+        if path is None:  # Escape pressed
+            return True
+        # Use the path...
+        return True
+```
+
+### Implementation pattern
+
+```python
+def read_line(prompt: str = "") -> str | None:
+    """Read a full line in raw mode. Returns None on Escape/Ctrl-C."""
+    # Uses tty.setraw() same as read_key()
+    # Accumulates chars in buffer, prints each as typed
+    # Handles: Enter (return string), Escape (return None),
+    #          Ctrl-C (return None), Backspace (delete last)
+    # Escape sequences (arrow keys pressed during input) are consumed and ignored
+```
+
+### Line Input Gotchas
+
+| Gotcha | Problem | Fix |
+|--------|---------|-----|
+| Pasted paths with quotes | Users paste `'/path/to/file'` with quotes | Strip outer quotes: `path.strip("'\"")`  |
+| Tilde expansion | `~/.config/...` not expanded | Use `Path(path).expanduser()` |
+| Raw mode echo | Characters not visible while typing | Manually `sys.stdout.write(ch)` each keystroke |
+| Escape during input | Arrow keys produce garbage in buffer | Detect `0x1B`, consume rest of sequence, ignore |
+| Module-level imports for testability | `import select` inside function can't be patched | Import `select`, `termios`, `tty` at module level (in `try/except`) |
+
+## Bilingual i18n
+
+Simple dict registry — no framework needed:
+
+```python
+STRINGS = {
+    "nav.back": {"en": "Back", "ko": "뒤로"},
+    ...
+}
+_lang = "en"
+
+def t(key: str) -> str:
+    return STRINGS.get(key, {}).get(_lang, key)
+
+def toggle_language():
+    global _lang
+    _lang = "ko" if _lang == "en" else "en"
+```
+
+On toggle, clear ALL cached screen content so every screen re-renders.
+
+## Three-Tier Responsive Layout
+
+```python
+if cols >= 100:  # Full dual-panel
+    Columns([status_panel, content_panel], padding=(0, 1))
+elif cols >= 80:  # Narrow status
+    Columns([narrow_status, content_panel], padding=(0, 1))
+else:            # Single panel (status line + content stacked)
+    console.print(f"Status: {health}")
+    console.print(content)
+```
+
+Use `rich.columns.Columns` (NOT `rich.layout.Layout`) — Columns auto-fits content height.
+
+---
+
+## Gotchas (Battle-Tested)
+
+### Rich Library
+
+| Gotcha | Problem | Fix |
+|--------|---------|-----|
+| `Panel(box=None)` | `AttributeError: NoneType has no attribute substitute` | Use `box=SIMPLE` from `rich.box` |
+| `Layout` stretches panels | Panels expand to fill available height with empty space | Use `Columns` with `expand=False` instead |
+| `Status` spinner nesting | "Only one live display may be active at once" crash | Never nest `Status()` inside other Rich output. Use plain `console.print("Loading...")` |
+| `[1]` in markup | Rich interprets `[1]` as a potential style tag | Escape: `\[1]` |
+| Rich + raw stdin | `tty.setraw()` conflicts with Rich's terminal state | Always restore termios in `finally` block |
+| `NO_COLOR` env var | Must respect `NO_COLOR` and `DTM_NO_COLOR` | Check env vars, return plain theme dict |
+
+### Keyboard Input
+
+| Gotcha | Problem | Fix |
+|--------|---------|-----|
+| F-key escape sequences | Vary between Terminal.app, iTerm2, VS Code | Map multiple sequences per key + provide alphanumeric fallbacks |
+| Items 10+ unreachable | Pressing `1` then `0` selects item 1 immediately | Digits jump cursor only, Enter confirms. Items 10+ use arrows |
+| `Ctrl+C` in raw mode | Crashes without terminal restoration | Wrap main loop in `try/except KeyboardInterrupt` |
+| Non-interactive detection | Piped input hangs on `read_key()` | Check `sys.stdin.isatty()` before entering TUI mode |
+
+### Content & Caching
+
+| Gotcha | Problem | Fix |
+|--------|---------|-----|
+| API calls per render | `content_renderer` called on every keystroke | Cache rendered content in `_cached_content[screen.id]`; clear on F5 |
+| Stale cached content | Model/account change doesn't update display | `invalidate_screen()` clears cache; use callable headers for dynamic data |
+| Config has null names | `set_active_account(id)` saves id but not name | Resolve names from API as fallback; backfill to config on success |
+| Korean char alignment | `{label:<12}` misaligns CJK double-width chars | Calculate display width: `sum(2 if ord(c) > 0x7F else 1 for c in s)` |
+| Language toggle stale | Screens show old language after F3 | Clear ALL `_cached_content` on language toggle, not just current screen |
+
+### UX Patterns
+
+| Pattern | Why |
+|---------|-----|
+| Confirmation panels (0.8s delay) | Users need visual feedback that their action took effect |
+| `<< active` markers | Users must see which item is currently selected at a glance |
+| Section headers in lists | Group related items (Recommended / Installed / LM Studio) |
+| Guidance hints at bottom | Tell users how to reach features that require other steps first |
+| Breadcrumb path always visible | Users always know where they are in the hierarchy |
+
+## Checklist for New TUI Projects
+
+- [ ] `from __future__ import annotations` in all TUI files
+- [ ] `_is_interactive()` guard before entering TUI mode
+- [ ] `--no-tui` and `--legacy` CLI flags for fallback
+- [ ] Non-TTY detection falls back to plain text
+- [ ] `NO_COLOR` / `FORCE_COLOR` env var support
+- [ ] F-key alphanumeric fallbacks defined
+- [ ] `KeyboardInterrupt` handled in main loop
+- [ ] Escape sequences for F1-F10, arrows mapped
+- [ ] Content cached, invalidated on refresh/change
+- [ ] All user-facing strings through `t()` i18n function
+- [ ] Tests for: i18n, input parser, screen registry, navigation stack

custom-skills/93-tui-designer/shared/references/dtm-wizard-reference.md

@@ -0,0 +1,84 @@
+# DTM Wizard — Reference Implementation
+
+The DTM Agent TUI wizard is the first project built with this skill's patterns.
+
+## Repository
+- **Project**: D.intelligence Tag Manager Agent
+- **Location**: `github.com/D-intelligence/dintel-gtm-agent`
+- **TUI code**: `src/dtm/tui/` (20 files, ~2500 lines)
+- **Tests**: `tools/tests/unit/test_tui_*.py` (29 tests)
+
+## File Inventory
+
+| File | Lines | Purpose |
+|------|-------|---------|
+| `__init__.py` | 13 | Public API |
+| `i18n.py` | 93 | 60+ bilingual EN/KR strings |
+| `input.py` | 93 | Escape sequence parser |
+| `themes.py` | 48 | Norton Commander color scheme |
+| `widgets.py` | 35 | Status icons, mini-tables |
+| `breadcrumb.py` | 22 | Navigation path bar |
+| `function_bar.py` | 33 | F-key shortcut bar |
+| `status_panel.py` | 85 | Left panel health display |
+| `menu.py` | 35 | Gopher-style numbered menu |
+| `dialog.py` | 70 | Modal overlays |
+| `core.py` | 100 | Three-tier layout engine |
+| `runner.py` | 170 | Event loop + ScreenStack |
+| `selector.py` | 156 | Arrow-key list selector |
+| `renderers.py` | ~1100 | 15 leaf screen content renderers |
+| `screens/*.py` | ~250 | 21 screen definitions |
+
+## Screen Hierarchy (21 screens)
+
+```
+home
+  setup
+    setup.credentials
+    setup.account
+      setup.account.containers  (dynamic sub-screen)
+    setup.ai
+    setup.connectivity
+  operations
+    ops.workflow
+    ops.container_analysis
+    ops.ai_analysis
+    ops.performance
+  configuration
+    config.review
+    config.change_account
+    config.change_container
+    config.export
+  diagnostics
+    diag.health
+    diag.test
+    diag.recommendations
+```
+
+## PRs and Evolution
+
+| PR | Title | Key Changes |
+|----|-------|-------------|
+| #10 | Core TUI redesign | 19 modules, 28 tests |
+| #11 | 7 usability fixes | Panel height, no-color, bilingual icons |
+| #12 | Interactive selection | Account/container by number, help screen |
+| #13 | Name resolution | Resolve IDs to names from API |
+| #14 | Loading spinners | Visual feedback during API calls |
+| #15 | AI model selector | Ollama + LM Studio detection |
+| #16 | Batch UX fixes | ListSelector, export formats, crash fixes |
+
+## External Service Detection Pattern
+
+```python
+def _detect_lm_studio() -> dict:
+    """Detect LM Studio on localhost:1234."""
+    import requests
+    try:
+        resp = requests.get("http://localhost:1234/v1/models", timeout=3)
+        if resp.status_code == 200:
+            return {"available": True, "models": [m["id"] for m in resp.json().get("data", [])]}
+    except Exception:
+        pass
+    return {"available": False, "models": []}
+```
+
+This pattern works for any OpenAI-compatible local LLM server.