agileflow 3.3.0 → 3.4.1

package/src/core/commands/ads/health.md

@@ -0,0 +1,327 @@
+---
+description: Unified marketing health scorecard — runs ads, SEO, landing page, and tracking audits in parallel to produce a combined score with cross-domain insights
+argument-hint: "<account-data-and-url> [SCOPE=all]"
+compact_context:
+  priority: high
+  preserve_rules:
+    - "ACTIVE COMMAND: /agileflow:ads:health - Unified marketing health scorecard"
+    - "CRITICAL: Deploy ads audit + SEO audit + landing page analysis IN PARALLEL"
+    - "CRITICAL: Combine scores into unified Marketing Health Score with domain weights"
+    - "Domain weights: Ads 40%, SEO 25%, Landing Pages 20%, Tracking 15%"
+    - "Cross-domain insights: tracking gaps affect ads + SEO, landing page quality affects ad ROAS"
+  state_fields:
+    - ads_score
+    - seo_score
+    - landing_score
+    - tracking_score
+    - unified_score
+---
+
+# /agileflow:ads:health
+
+Unified marketing health scorecard that orchestrates ads, SEO, landing page, and tracking audits in parallel, then synthesizes into a single Marketing Health Score with cross-domain insights.
+
+---
+
+## Quick Reference
+
+```
+/agileflow:ads:health <account-data> <landing-page-url>               # Full health check
+/agileflow:ads:health <account-data> SCOPE=ads,seo                    # Ads + SEO only
+/agileflow:ads:health <account-data> SCOPE=ads,landing                # Ads + landing pages only
+```
+
+---
+
+## How It Works
+
+```
++-------------------------------------------------------------------+
+|                    /agileflow:ads:health                            |
+|                                                                     |
+|  1. Parse inputs (ad data + URLs)                                  |
+|  2. Deploy domain audits IN PARALLEL                                |
+|  3. Collect all domain scores                                       |
+|  4. Cross-reference findings across domains                         |
+|  5. Calculate unified Marketing Health Score                        |
+|  6. Generate shareable scorecard                                    |
++-------------------------------------------------------------------+
+
+    +-----------+    +----------+    +-----------+    +----------+
+    |   Ads     |    |   SEO    |    |  Landing  |    | Tracking |
+    |  Audit    |    |  Audit   |    |  Page     |    |  Audit   |
+    | (6 agents)|    |(6 agents)|    | Analysis  |    | (shared) |
+    +-----+-----+    +----+-----+    +-----+-----+    +----+-----+
+          |               |               |               |
+          +---------------+---------------+---------------+
+                                |
+                    +-----------+-----------+
+                    |  Health Score         |
+                    |  Synthesis &          |
+                    |  Cross-Domain         |
+                    |  Insights             |
+                    +-----------------------+
+```
+
+---
+
+## Arguments
+
+| Argument | Values | Default | Description |
+|----------|--------|---------|-------------|
+| account-data | Text, file, or description | Required for ads | Ad account data for ads audit |
+| URL | Landing page URL(s) | Optional | URLs for SEO + landing page analysis |
+| SCOPE | all, ads, seo, landing, tracking | all | Which domains to include |
+
+---
+
+## Step-by-Step Process
+
+### STEP 1: Parse Inputs
+
+Accept a combination of:
+- **Ad account data** (pasted, file, or described) — triggers ads audit
+- **URL(s)** — triggers SEO audit + landing page analysis
+- **Both** — triggers full health check
+
+If insufficient data provided:
+
+```xml
+<invoke name="AskUserQuestion">
+<parameter name="questions">[
+  {
+    "question": "What data do you have for the health check? More data = more comprehensive score.",
+    "header": "Data Sources",
+    "multiSelect": true,
+    "options": [
+      {"label": "Ad account data (Recommended)", "description": "Paste from Google Ads, Meta Ads Manager — enables ads audit (40% of score)"},
+      {"label": "Website/landing page URL", "description": "Your main URL for SEO + landing page analysis (45% of score)"},
+      {"label": "Tracking setup description", "description": "Describe your GTM, pixels, conversion events (15% of score)"}
+    ]
+  }
+]</parameter>
+</invoke>
+```
+
+### STEP 2: Deploy Domain Audits in Parallel
+
+**CRITICAL**: Deploy ALL applicable audits in a SINGLE message with multiple Task calls using `run_in_background: true`.
+
+#### Ads Audit (if ad data provided)
+
+```xml
+<invoke name="Task">
+<parameter name="description">Ads audit for health scorecard</parameter>
+<parameter name="prompt">Run a complete ads audit on this account data. Apply all checks from all 6 analyzers (Google, Meta, Budget, Creative, Tracking, Compliance). Calculate the Ads Health Score.
+
+ACCOUNT DATA:
+{account_data}
+
+OUTPUT: Your Ads Health Score X/100 with category breakdown and top 5 findings by severity.</parameter>
+<parameter name="subagent_type">ads-consensus</parameter>
+<parameter name="run_in_background">true</parameter>
+</invoke>
+```
+
+#### SEO Audit (if URL provided)
+
+```xml
+<invoke name="Task">
+<parameter name="description">SEO audit for health scorecard</parameter>
+<parameter name="prompt">Run a complete SEO audit on this URL. Apply all checks from all 6 analyzers (Technical, Content, Schema, Performance, Images, Sitemap). Calculate the SEO Health Score.
+
+URL: {url}
+
+OUTPUT: Your SEO Health Score X/100 with category breakdown and top 5 findings by severity.</parameter>
+<parameter name="subagent_type">seo-consensus</parameter>
+<parameter name="run_in_background">true</parameter>
+</invoke>
+```
+
+#### Landing Page Analysis (if URL provided)
+
+```xml
+<invoke name="Task">
+<parameter name="description">Landing page analysis for health scorecard</parameter>
+<parameter name="prompt">Analyze this landing page for conversion optimization. Score across these dimensions:
+
+URL: {url}
+
+## Landing Page Scoring (100 points total)
+
+### Above-the-Fold (30 points)
+- Clear headline matching ad intent (10)
+- Visible CTA above fold (10)
+- Social proof visible without scrolling (5)
+- Load time under 3 seconds (5)
+
+### Message Match (25 points)
+- Headline matches ad copy themes (10)
+- Value proposition clarity (10)
+- Single clear conversion goal (5)
+
+### Trust & Proof (20 points)
+- Customer testimonials/logos (8)
+- Security badges/certifications (4)
+- Clear contact information (4)
+- Privacy policy linked (4)
+
+### Form/CTA Optimization (15 points)
+- Minimal form fields for stage (5)
+- CTA button contrast and copy (5)
+- Multiple CTAs on long pages (5)
+
+### Mobile Experience (10 points)
+- Responsive layout (4)
+- Touch-friendly buttons (3)
+- Fast mobile load (3)
+
+OUTPUT: Landing Page Score X/100 with breakdown and top 5 recommendations.</parameter>
+<parameter name="subagent_type">general-purpose</parameter>
+<parameter name="run_in_background">true</parameter>
+</invoke>
+```
+
+#### Tracking Audit (always runs if any data provided)
+
+The tracking score is extracted from the ads audit (if run) or assessed independently from the URL/description.
+
+### STEP 3: Collect Results
+
+Wait for all background tasks to complete using TaskOutput with `block: true`.
+
+### STEP 4: Cross-Domain Insights
+
+After collecting all scores, identify cross-domain correlations:
+
+| Pattern | Domains | Insight |
+|---------|---------|---------|
+| Tracking broken + low ads ROAS | Tracking + Ads | "Your ROAS numbers are unreliable — fix tracking first" |
+| Slow landing page + high CPC | Landing + Ads | "Slow pages increase bounce rate, raising your CPC" |
+| Missing schema + low organic | SEO + Landing | "No structured data means fewer rich snippets in SERPs" |
+| Ad copy mismatch + low CVR | Ads + Landing | "Your ads promise X but landing page delivers Y" |
+| No retargeting pixel + high bounce | Tracking + Landing | "Losing bounced visitors with no way to retarget them" |
+
+### STEP 5: Calculate Unified Score
+
+```
+Marketing Health Score = sum(Domain Score * Domain Weight)
+```
+
+**Domain Weights:**
+| Domain | Weight | Why |
+|--------|--------|-----|
+| Ads | 40% | Direct spend efficiency — highest dollar impact |
+| SEO | 25% | Organic acquisition — compounding long-term value |
+| Landing Pages | 20% | Conversion rate — multiplier for all traffic |
+| Tracking | 15% | Data quality — foundation for all optimization |
+
+**If a domain is excluded** (not in SCOPE or no data), redistribute its weight proportionally to included domains.
+
+**Grade Scale:**
+| Grade | Score | Meaning |
+|-------|-------|---------|
+| A | 90-100 | Excellent — optimized marketing funnel |
+| B | 80-89 | Good — minor improvements available |
+| C | 70-79 | Needs Work — significant gaps in the funnel |
+| D | 60-69 | Poor — major issues across multiple domains |
+| F | < 60 | Critical — fundamental problems, likely wasting significant spend |
+
+### STEP 6: Generate Scorecard
+
+Output a compact, shareable scorecard:
+
+```markdown
+# Marketing Health Scorecard
+
+**Generated**: {YYYY-MM-DD}
+**Account**: {name/description}
+**Scope**: {domains audited}
+
+---
+
+## Marketing Health Score: {X}/100 ({grade})
+
+```
+Ads:      ████████████████████░░░░░░  78/100 (40%)
+SEO:      ██████████████░░░░░░░░░░░░  58/100 (25%)
+Landing:  ████████████████████████░░  92/100 (20%)
+Tracking: ██████░░░░░░░░░░░░░░░░░░░░  25/100 (15%)
+          ──────────────────────────
+Overall:  ██████████████████░░░░░░░░  71/100 (C)
+```
+
+| Domain | Score | Grade | Top Issue |
+|--------|-------|-------|-----------|
+| **Ads** | {X}/100 | {grade} | {top finding} |
+| **SEO** | {X}/100 | {grade} | {top finding} |
+| **Landing Pages** | {X}/100 | {grade} | {top finding} |
+| **Tracking** | {X}/100 | {grade} | {top finding} |
+
+---
+
+## Cross-Domain Insights
+
+1. **{insight title}** ({domains affected})
+   {description and impact}
+
+2. **{insight title}** ({domains affected})
+   {description and impact}
+
+---
+
+## Priority Actions (by estimated $ impact)
+
+| # | Action | Domain | Impact | Effort |
+|---|--------|--------|--------|--------|
+| 1 | {action} | {domain} | {$$} | {Low/Med/High} |
+| 2 | {action} | {domain} | {$$} | {Low/Med/High} |
+| 3 | {action} | {domain} | {$$} | {Low/Med/High} |
+
+---
+
+## Domain Deep-Dives
+
+Run individual audits for detailed findings:
+- `/agileflow:ads:audit` — Full 190-check ads analysis
+- `/agileflow:seo:audit` — Full 6-analyzer SEO audit
+- `/agileflow:ads:landing` — Detailed landing page optimization
+```
+
+Save scorecard to `docs/08-project/health-scorecards/health-scorecard-{YYYYMMDD}.md`.
+
+### STEP 7: Present Results
+
+```xml
+<invoke name="AskUserQuestion">
+<parameter name="questions">[{
+  "question": "Marketing Health Score: {X}/100 ({grade}). Lowest domain: {domain} ({score}/100). {N} cross-domain insights found.",
+  "header": "Next steps",
+  "multiSelect": false,
+  "options": [
+    {"label": "Fix {lowest_domain} issues first (Recommended)", "description": "{top_issue} — estimated ${impact}/mo impact"},
+    {"label": "Deep-dive ads audit", "description": "Run full /agileflow:ads:audit for 190-check analysis"},
+    {"label": "Deep-dive SEO audit", "description": "Run full /agileflow:seo:audit for comprehensive SEO analysis"},
+    {"label": "Generate fix artifacts", "description": "Auto-generate corrected ad copy, schema markup, and meta tags"}
+  ]
+}]</parameter>
+</invoke>
+```
+
+---
+
+<!-- COMPACT_SUMMARY_START -->
+## Compact Summary
+
+**Command**: `/agileflow:ads:health` - Unified marketing health scorecard
+
+**What It Does**: Deploy ads + SEO + landing page + tracking audits in parallel -> cross-domain insights -> Marketing Health Score 0-100
+
+**Domain Weights**: Ads 40%, SEO 25%, Landing Pages 20%, Tracking 15%
+
+**Output**: Shareable scorecard with bar chart, cross-domain insights, and priority actions
+
+**Usage**: `/agileflow:ads:health <account-data> <url> [SCOPE=all]`
+
+**File**: `docs/08-project/health-scorecards/health-scorecard-{YYYYMMDD}.md`
+<!-- COMPACT_SUMMARY_END -->

package/src/core/commands/ads/landing.md

@@ -0,0 +1,119 @@
+---
+description: Landing page optimization audit for ad campaigns - Core Web Vitals, CTA effectiveness, trust signals, mobile experience, and message match
+argument-hint: "<URL>"
+compact_context:
+  priority: medium
+  preserve_rules:
+    - "ACTIVE COMMAND: /agileflow:ads:landing - Landing page optimization"
+    - "Use WebFetch to analyze the actual landing page"
+    - "Check CWV, CTA, trust signals, mobile, message match"
+  state_fields:
+    - target_url
+    - landing_score
+---
+
+# /agileflow:ads:landing
+
+Audit a landing page for paid advertising effectiveness. Analyzes the page for conversion rate optimization factors that directly impact ad campaign performance.
+
+---
+
+## Quick Reference
+
+```
+/agileflow:ads:landing https://example.com/offer           # Audit landing page
+```
+
+---
+
+## Process
+
+### STEP 1: Fetch Landing Page
+
+Use WebFetch to retrieve the target URL. Extract:
+- Page structure (H1, form, CTA buttons)
+- Load performance indicators
+- Trust signals (testimonials, badges, reviews)
+- Mobile responsiveness indicators
+- Form fields and friction points
+
+### STEP 2: Run 15 Checks
+
+| # | Check | Severity | Pass Criteria |
+|---|-------|----------|---------------|
+| LP-1 | Page loads < 3 seconds | HIGH | LCP < 2.5s, FCP < 1.8s |
+| LP-2 | Single clear CTA | HIGH | One primary CTA visible above fold |
+| LP-3 | Headline matches ad copy | CRITICAL | H1 reflects the ad's promise |
+| LP-4 | Mobile responsive | HIGH | Viewport meta + responsive design |
+| LP-5 | Form friction | HIGH | < 5 form fields for lead gen |
+| LP-6 | Trust signals present | MEDIUM | Testimonials, reviews, badges, logos |
+| LP-7 | No navigation distractions | MEDIUM | Minimal or no top navigation |
+| LP-8 | Social proof | MEDIUM | Customer count, ratings, case studies |
+| LP-9 | Urgency element | LOW | Deadline, limited availability (if genuine) |
+| LP-10 | Phone number visible | MEDIUM | Click-to-call for service businesses |
+| LP-11 | Privacy policy linked | HIGH | Required for ad platform compliance |
+| LP-12 | SSL certificate | CRITICAL | HTTPS required |
+| LP-13 | No broken images/links | HIGH | All resources load correctly |
+| LP-14 | Thank you page/confirmation | MEDIUM | Post-conversion confirmation page |
+| LP-15 | Tracking pixels present | CRITICAL | GTM/Pixel/tag detected on page |
+
+### STEP 3: Score and Report
+
+```markdown
+## Landing Page Audit: {URL}
+
+**Landing Page Score**: {X}/100
+
+| Check | Status | Severity | Notes |
+|-------|--------|----------|-------|
+| LP-1 Page speed | PASS/FAIL | HIGH | {LCP time} |
+| ... | ... | ... | ... |
+
+### Critical Issues
+{List any CRITICAL failures}
+
+### Quick Wins
+{Easy fixes that improve conversion rate}
+
+### Message Match Analysis
+- **Ad headline**: {if provided}
+- **Landing page H1**: {extracted}
+- **Match quality**: {Strong/Weak/Mismatch}
+
+### Conversion Rate Optimization Suggestions
+1. {Specific suggestion with expected impact}
+2. {Suggestion}
+3. {Suggestion}
+```
+
+### STEP 4: Offer Next Steps
+
+```xml
+<invoke name="AskUserQuestion">
+<parameter name="questions">[{
+  "question": "Landing page score: {X}/100. {N} issues found. What would you like to do?",
+  "header": "Next steps",
+  "multiSelect": false,
+  "options": [
+    {"label": "Fix critical issues (Recommended)", "description": "{top issue}"},
+    {"label": "Run full ads audit", "description": "Check ad account + landing page together"},
+    {"label": "Test another landing page", "description": "Compare multiple landing pages"},
+    {"label": "Optimize for specific platform", "description": "Platform-specific landing page requirements"}
+  ]
+}]</parameter>
+</invoke>
+```
+
+---
+
+<!-- COMPACT_SUMMARY_START -->
+## Compact Summary
+
+**Command**: `/agileflow:ads:landing` - Landing page optimization for ads
+
+**Input**: URL of landing page
+
+**Output**: 15-check audit with CRO suggestions
+
+**Quick Usage**: `/agileflow:ads:landing <URL>`
+<!-- COMPACT_SUMMARY_END -->

package/src/core/commands/ads/linkedin.md

@@ -0,0 +1,112 @@
+---
+description: LinkedIn Ads audit with 9 checks for lead gen forms, audience targeting, budget efficiency, and CRM integration
+argument-hint: "<account-data>"
+compact_context:
+  priority: medium
+  preserve_rules:
+    - "ACTIVE COMMAND: /agileflow:ads:linkedin - LinkedIn Ads audit"
+    - "Inline command - 9 checks, no separate agent needed"
+    - "Min budget: $50/day campaign, $25/day ad group"
+  state_fields:
+    - linkedin_score
+---
+
+# /agileflow:ads:linkedin
+
+Run an inline audit on a LinkedIn Ads account with 9 focused checks. LinkedIn has the highest CPCs in paid social, so efficiency is critical.
+
+---
+
+## Quick Reference
+
+```
+/agileflow:ads:linkedin <account-data>                # LinkedIn Ads audit
+```
+
+---
+
+## The 9 Checks
+
+| # | Check | Severity | Pass Criteria |
+|---|-------|----------|---------------|
+| LI-1 | Insight Tag installed | CRITICAL | LinkedIn Insight Tag on all pages |
+| LI-2 | Lead Gen Forms vs landing pages | HIGH | Lead Gen Forms tested (typically 2-5x better CVR) |
+| LI-3 | Audience size appropriate | HIGH | 50K-500K for Sponsored Content |
+| LI-4 | Company/title targeting precision | HIGH | Targeting by job title or function, not just industry |
+| LI-5 | Budget meets minimum | CRITICAL | Minimum $50/day per campaign |
+| LI-6 | CRM integration active | HIGH | Leads syncing to CRM within 24 hours |
+| LI-7 | Content type mix | MEDIUM | Single image + carousel + video tested |
+| LI-8 | Matched Audiences | MEDIUM | Website retargeting + company list + LAL active |
+| LI-9 | ABM alignment | LOW | Account-Based Marketing lists for enterprise |
+
+---
+
+## Process
+
+### STEP 1: Apply All 9 Checks
+
+Review the account data against each check. For LinkedIn specifically:
+
+**Budget reality check**: LinkedIn CPCs are $5-15 for Sponsored Content. With $50/day minimum:
+- Daily clicks: ~3-10
+- Monthly clicks: ~100-300
+- At 5% conversion rate: ~5-15 leads/month
+- **Minimum viable budget for lead gen: $100/day recommended**
+
+**Lead Gen Forms vs Landing Pages**:
+- Lead Gen Forms: 10-30% conversion rate (pre-filled data)
+- Landing Pages: 2-5% conversion rate
+- Always test Lead Gen Forms first on LinkedIn
+
+### STEP 2: Score
+
+```
+LinkedIn Score = 100 - sum(severity_deductions)
+```
+
+Deductions: CRITICAL (-15), HIGH (-8), MEDIUM (-4), LOW (-2)
+
+### STEP 3: Output
+
+```markdown
+## LinkedIn Ads Audit
+
+**LinkedIn Score**: {X}/100
+
+| Check | Status | Notes |
+|-------|--------|-------|
+| LI-1 Insight Tag | PASS/FAIL | {details} |
+| LI-2 Lead Gen Forms | PASS/FAIL | {details} |
+| LI-3 Audience size | PASS/FAIL | {size estimate} |
+| LI-4 Targeting precision | PASS/FAIL | {targeting method} |
+| LI-5 Budget minimum | PASS/FAIL | ${daily}/day |
+| LI-6 CRM integration | PASS/FAIL | {sync status} |
+| LI-7 Content types | PASS/FAIL | {formats in use} |
+| LI-8 Matched Audiences | PASS/FAIL | {audience types} |
+| LI-9 ABM alignment | PASS/FAIL | {ABM status} |
+
+### Key Recommendations
+1. {Top priority fix}
+2. {Second priority}
+3. {Third priority}
+
+### LinkedIn-Specific Tips
+- Use Lead Gen Forms for B2B lead generation (2-5x better CVR)
+- Minimum audience size 50K for Sponsored Content
+- Test Document Ads for thought leadership
+- Message Ads have highest response rate but lowest scale
+```
+
+---
+
+<!-- COMPACT_SUMMARY_START -->
+## Compact Summary
+
+**Command**: `/agileflow:ads:linkedin` - LinkedIn Ads audit
+
+**Checks**: 9 (inline, no separate agent)
+
+**Key**: Min $50/day, Lead Gen Forms > Landing Pages, 50K-500K audience
+
+**Quick Usage**: `/agileflow:ads:linkedin <account-data>`
+<!-- COMPACT_SUMMARY_END -->

package/src/core/commands/ads/meta.md

@@ -0,0 +1,91 @@
+---
+description: Meta/Facebook Ads deep-dive audit with 46 deterministic checks across Pixel/CAPI tracking, creative strategy, account structure, and audience targeting
+argument-hint: "<account-data>"
+compact_context:
+  priority: medium
+  preserve_rules:
+    - "ACTIVE COMMAND: /agileflow:ads:meta - Meta Ads deep-dive"
+    - "Delegate to ads-audit-meta agent for 46 checks"
+    - "Quality gates: Pixel required, domain verified, learning phase, Special Ad Categories"
+  state_fields:
+    - meta_score
+---
+
+# /agileflow:ads:meta
+
+Run a deep-dive audit on a Meta/Facebook Ads account using the `ads-audit-meta` agent with 46 deterministic checks across 4 categories.
+
+---
+
+## Quick Reference
+
+```
+/agileflow:ads:meta <account-data>                    # Full Meta Ads audit
+```
+
+---
+
+## Process
+
+### STEP 1: Validate Input
+
+If no account data provided, ask the user to paste or describe their Meta Ads setup including:
+- Pixel and CAPI setup
+- Campaign objectives and structure
+- Audience targeting (LAL, custom, interest)
+- Creative assets and formats
+- Budget and performance metrics
+
+### STEP 2: Deploy Meta Ads Analyzer
+
+```xml
+<invoke name="Task">
+<parameter name="description">Meta Ads deep-dive audit</parameter>
+<parameter name="prompt">TASK: Run a comprehensive Meta/Facebook Ads audit.
+
+ACCOUNT DATA:
+{account_data}
+
+Apply ALL 46 checks across 4 weighted categories:
+- Pixel & CAPI Tracking (30%) - 12 checks
+- Creative Strategy (25%) - 14 checks
+- Account Structure (25%) - 10 checks
+- Audience Targeting (20%) - 10 checks
+
+Enforce ALL quality gates:
+1. Pixel installed and firing
+2. Domain verified
+3. Learning phase healthy (50 conversions/week)
+4. Special Ad Categories declared
+
+OUTPUT: Full findings with Meta Ads Score X/100</parameter>
+<parameter name="subagent_type">ads-audit-meta</parameter>
+</invoke>
+```
+
+### STEP 3: Present Results
+
+Show the Meta Ads Score and key findings, then offer next steps.
+
+---
+
+## 46 Checks Overview
+
+| Category | Weight | Checks | Focus |
+|----------|--------|--------|-------|
+| Pixel & CAPI Tracking | 30% | 12 | Pixel, CAPI, EMQ, AEM, dedup, privacy |
+| Creative Strategy | 25% | 14 | Diversity, video, formats, refresh, DCO |
+| Account Structure | 25% | 10 | CBO, objectives, consolidation, learning phase |
+| Audience Targeting | 20% | 10 | LAL, custom, overlap, retargeting, exclusions |
+
+---
+
+<!-- COMPACT_SUMMARY_START -->
+## Compact Summary
+
+**Command**: `/agileflow:ads:meta` - Meta/Facebook Ads deep-dive audit
+
+**Agent**: `ads-audit-meta` (46 checks, 4 categories)
+
+**Quick Usage**: `/agileflow:ads:meta <account-data>`
+<!-- COMPACT_SUMMARY_END -->