Skill Chain Cookbook

Skill Chain Cookbook

10+ Ready-to-Use Recipes

This cookbook provides proven skill chain recipes you can deploy immediately. Each recipe includes:

• Use case — What problem it solves
• Skills — Which skills to chain together
• ROI — Expected time/cost savings
• Step-by-step instructions — Copy-paste examples
• Expected outcomes — What success looks like

Recipe 1: Sales Deal Qualification Pipeline

Use Case: Automatically qualify, score, and route leads with recommended next actions Skills: 5 chained skills Time: 30-60 seconds per lead (was 2-3 hours) ROI: $20K-$40K/month for 50-lead sales team

The Chain

lead_qualification → opportunity_scoring → deal_inspection →
next_best_action → content_recommender

How It Works

1. lead_qualification — Applies MEDDIC/BANT framework, determines if lead is qualified
2. opportunity_scoring — Scores qualified leads on fit, urgency, budget
3. deal_inspection — Analyzes deal health, identifies risks
4. next_best_action — Recommends specific actions for rep
5. content_recommender — Suggests relevant case studies, decks

Setup Instructions

Step 1: Install RevOps Skills

npx skills-directory install --target all --domain revops

Step 2: Configure Lead Qualification Entry Point

{
  "skill": "lead_qualification",
  "input": {
    "leadId": "{{trigger.leadId}}",
    "framework": "MEDDIC",
    "sources": ["CRM", "enrichment_data", "website_activity"]
  },
  "exit_routing": {
    "qualified": "opportunity_scoring",
    "nurture": "nurture_campaign",
    "disqualified": "archive_lead"
  }
}

Step 3: Chain to Opportunity Scoring

{
  "skill": "opportunity_scoring",
  "input": {
    "opportunityId": "{{previous.opportunityId}}",
    "qualificationData": "{{previous.output}}",
    "scoringModel": "weighted"
  },
  "exit_routing": {
    "high_score": "deal_inspection",
    "medium_score": "next_best_action",
    "low_score": "nurture_campaign"
  }
}

Step 4: Add Deal Inspection

{
  "skill": "deal_inspection",
  "input": {
    "dealId": "{{previous.dealId}}",
    "depth": "comprehensive"
  },
  "exit_routing": {
    "healthy": "next_best_action",
    "at_risk": "escalation_manager",
    "blocked": "deal_surgery"
  }
}

Step 5: Route to Next Best Action

{
  "skill": "next_best_action",
  "input": {
    "context": "{{chain.all_previous_outputs}}",
    "repProfile": "{{user.profile}}",
    "priority": "close_deal"
  },
  "exit_routing": {
    "action_recommended": "content_recommender",
    "needs_manager": "escalation_manager"
  }
}

Step 6: Recommend Content

{
  "skill": "content_recommender",
  "input": {
    "dealContext": "{{chain.context}}",
    "buyerPersona": "{{lead.persona}}",
    "dealStage": "{{deal.stage}}"
  },
  "output": "send_to_rep"
}

Testing the Chain

# Test with sample lead data
curl -X POST http://localhost:3000/api/chains/sales-qualification \
  -H "Content-Type: application/json" \
  -d '{
    "leadId": "test-lead-123",
    "leadData": {
      "company": "Acme Corp",
      "revenue": "$50M",
      "employees": 250,
      "industry": "SaaS"
    }
  }'

Expected Output

{
  "qualified": true,
  "score": 85,
  "tier": "high_value",
  "risks": [],
  "nextActions": [
    "Schedule discovery call",
    "Send ROI calculator",
    "Introduce solutions engineer"
  ],
  "recommendedContent": [
    "Case Study: Similar company in SaaS",
    "ROI Calculator: Enterprise tier",
    "Demo Video: Platform overview"
  ],
  "timeline": "Move to demo within 5 days"
}

Monitoring & Metrics

Track these KPIs:

• Lead-to-opportunity rate: Target > 25%
• Time saved per lead: Target 90%+ reduction
• Opportunity quality: Track close rates
• Rep satisfaction: Survey reps on lead quality

Expected Outcomes

• Week 1: Chain deployed, processing 10-20 leads
• Week 2: Reps report 50%+ time savings on qualification
• Month 1: 25%+ lead-to-opportunity conversion rate
• Month 3: $25K+ value delivered in time savings

Recipe 2: Customer Churn Prevention Pipeline

Use Case: Predict churn risk 60-90 days early and trigger intervention playbooks Skills: 4 chained skills Time: Real-time monitoring vs quarterly reviews ROI: $400K+ ARR saved annually

The Chain

health_scoring → churn_prediction → risk_mitigation_playbook →
escalation_manager

How It Works

1. health_scoring — Continuously monitors account health signals
2. churn_prediction — ML-based prediction of churn risk 60-90 days out
3. risk_mitigation_playbook — Executes tailored intervention strategies
4. escalation_manager — Alerts CSM and triggers manager involvement if needed

Setup Instructions

Step 1: Install Customer Success Skills

npx skills-directory install --target all --domain customer_success

Step 2: Configure Health Scoring (Continuous)

{
  "skill": "health_scoring",
  "trigger": "scheduled",
  "frequency": "daily",
  "input": {
    "accountIds": "{{all_active_accounts}}",
    "signals": [
      "product_usage",
      "support_tickets",
      "nps_score",
      "contract_value",
      "engagement_metrics"
    ]
  },
  "exit_routing": {
    "healthy": "log_and_continue",
    "at_risk": "churn_prediction",
    "critical": "immediate_escalation"
  }
}

Step 3: Chain to Churn Prediction

{
  "skill": "churn_prediction",
  "input": {
    "accountId": "{{previous.accountId}}",
    "healthData": "{{previous.healthScore}}",
    "historicalData": true,
    "predictionWindow": "90_days"
  },
  "exit_routing": {
    "high_risk": "risk_mitigation_playbook",
    "medium_risk": "risk_mitigation_playbook",
    "low_risk": "monitor_only"
  }
}

Step 4: Execute Risk Mitigation

{
  "skill": "risk_mitigation_playbook",
  "input": {
    "accountId": "{{chain.accountId}}",
    "riskLevel": "{{previous.riskScore}}",
    "riskFactors": "{{previous.factors}}",
    "playbookType": "retention"
  },
  "actions": [
    "Schedule executive business review",
    "Conduct product usage analysis",
    "Offer training/onboarding refresh",
    "Introduce customer success resources"
  ],
  "exit_routing": {
    "playbook_started": "escalation_manager",
    "needs_custom_plan": "csm_intervention"
  }
}

Step 5: Escalate if Needed

{
  "skill": "escalation_manager",
  "input": {
    "accountId": "{{chain.accountId}}",
    "context": "{{chain.all_data}}",
    "urgency": "{{previous.riskLevel}}"
  },
  "notifications": [
    "Assigned CSM",
    "CSM Manager",
    "VP Customer Success"
  ]
}

Monitoring Dashboard

Create a real-time dashboard tracking:

┌─────────────────────────────────────────────┐
│ Churn Prevention Dashboard                  │
├─────────────────────────────────────────────┤
│ Accounts Monitored: 347                     │
│ At-Risk (High): 12                          │
│ At-Risk (Medium): 28                        │
│ Playbooks Active: 18                        │
│ ARR at Risk: $450K                          │
│ ARR Saved (QTD): $180K                      │
└─────────────────────────────────────────────┘

Expected Outcomes

• Week 1: Health scoring running on all accounts
• Week 2: First at-risk accounts identified
• Month 1: 3-5 accounts saved from churn
• Quarter 1: $100K-$200K ARR saved

Recipe 3: Financial Intelligence Dashboard

Use Case: Real-time CFO dashboard with automated board reporting Skills: 5 chained skills Time: Real-time updates vs monthly 40-hour manual process ROI: $50K+/month in finance team time

The Chain

arr_waterfall → burn_rate_monitor → magic_number →
investor_metrics → scenario_planner

How It Works

1. arr_waterfall — Tracks ARR movements (new, expansion, churn, contraction)
2. burn_rate_monitor — Monitors cash burn and runway
3. magic_number — Calculates sales efficiency
4. investor_metrics — Compiles key metrics (CAC, LTV, Rule of 40)
5. scenario_planner — Models "what if" scenarios

Setup Instructions

Step 1: Install FinOps Skills

npx skills-directory install --target all --domain finops

Step 2: Configure ARR Waterfall (Real-time)

{
  "skill": "arr_waterfall",
  "trigger": "data_change",
  "input": {
    "period": "current_month",
    "sources": ["billing", "crm", "contracts"],
    "granularity": "daily"
  },
  "output_to": "burn_rate_monitor"
}

Step 3: Monitor Burn Rate

{
  "skill": "burn_rate_monitor",
  "input": {
    "arrData": "{{previous.arr}}",
    "expenses": "{{accounting.expenses}}",
    "runway_threshold": 12
  },
  "alerts": {
    "runway_below_12_months": "immediate",
    "burn_increasing_20_percent": "warning"
  },
  "output_to": "magic_number"
}

Step 4: Calculate Sales Efficiency

{
  "skill": "magic_number",
  "input": {
    "newARR": "{{arr_waterfall.new}}",
    "salesMarketing": "{{expenses.sales_marketing}}",
    "period": "quarter"
  },
  "benchmark": 1.0,
  "output_to": "investor_metrics"
}

Step 5: Compile Investor Metrics

{
  "skill": "investor_metrics",
  "input": {
    "allData": "{{chain.all_previous}}",
    "includeMetrics": [
      "ARR",
      "Net Revenue Retention",
      "CAC",
      "LTV",
      "LTV:CAC Ratio",
      "Magic Number",
      "Burn Multiple",
      "Rule of 40",
      "Gross Margin"
    ]
  },
  "output_to": "scenario_planner"
}

Step 6: Enable Scenario Planning

{
  "skill": "scenario_planner",
  "input": {
    "baselineData": "{{previous.metrics}}",
    "scenarios": [
      {
        "name": "aggressive_growth",
        "assumptions": {"headcount_increase": 30, "arr_growth": 100}
      },
      {
        "name": "profitable_growth",
        "assumptions": {"headcount_increase": 15, "arr_growth": 50}
      }
    ]
  }
}

One-Click Board Report

# Generate board report
npx skills-directory run-chain financial-intelligence \
  --output board-report \
  --format pdf

Expected Outcomes

• Day 1: Dashboard showing real-time metrics
• Week 1: CFO using for daily decision-making
• Month 1: First board report auto-generated
• Quarter 1: 90% reduction in manual financial reporting

Recipe 4: Growth Optimization Engine

Use Case: Continuous A/B testing and conversion optimization Skills: 6 chained skills Time: 10-15 experiments/month vs 2-4 ROI: 15-25% conversion lift

The Chain

signup_flow_cro → page_cro → ab_test_setup →
analytics_tracking → activation_metrics → feature_adoption

How It Works

1. signup_flow_cro — Optimizes signup conversion
2. page_cro — Optimizes landing page conversion
3. ab_test_setup — Configures and launches A/B tests
4. analytics_tracking — Tracks all metrics
5. activation_metrics — Monitors activation funnel
6. feature_adoption — Tracks feature usage

Setup Instructions

Step 1: Install Marketing/PLG Skills

npx skills-directory install --target all --domain marketing plg

Step 2: Start with Signup Flow Optimization

{
  "skill": "signup_flow_cro",
  "input": {
    "currentFlow": "{{app.signup_flow}}",
    "conversionGoal": "completed_signup",
    "optimizationFocus": ["friction_points", "form_fields", "social_proof"]
  },
  "exit_routing": {
    "recommendations_ready": "ab_test_setup"
  }
}

Step 3: Run Parallel Page Optimization

{
  "skill": "page_cro",
  "input": {
    "pages": ["homepage", "pricing", "features"],
    "goal": "trial_signup",
    "analyze": ["copy", "cta", "layout", "images"]
  },
  "exit_routing": {
    "recommendations_ready": "ab_test_setup"
  }
}

Step 4: Automated A/B Test Setup

{
  "skill": "ab_test_setup",
  "input": {
    "recommendations": "{{previous.all_recommendations}}",
    "testPlatform": "optimizely",
    "traffic_split": "50/50",
    "duration": "2_weeks",
    "min_sample_size": 1000
  },
  "exit_routing": {
    "test_launched": "analytics_tracking"
  }
}

Step 5: Track Everything

{
  "skill": "analytics_tracking",
  "input": {
    "events": [
      "page_view",
      "signup_started",
      "signup_completed",
      "feature_used",
      "trial_converted"
    ],
    "destinations": ["mixpanel", "amplitude", "datawarehouse"]
  }
}

Step 6: Monitor Activation & Adoption

{
  "skill": "activation_metrics",
  "input": {
    "activationDefinition": "{{company.aha_moment}}",
    "timeWindow": "7_days"
  }
},
{
  "skill": "feature_adoption",
  "input": {
    "features": "{{product.feature_list}}",
    "cohorts": ["week_1", "week_2", "month_1"]
  }
}

Growth Experimentation Dashboard

┌─────────────────────────────────────────────┐
│ Active Experiments                          │
├─────────────────────────────────────────────┤
│ Signup Flow: 3-step vs 1-step              │
│   Status: Running | Day 8 of 14            │
│   Winner: 1-step (+23% conversion) ✓       │
│                                             │
│ Pricing Page: New layout                   │
│   Status: Running | Day 3 of 14            │
│   Current: +8% trial signups               │
│                                             │
│ Homepage Hero: Value prop test             │
│   Status: Complete                          │
│   Winner: "Build in days" (+15%) ✓         │
└─────────────────────────────────────────────┘

Expected Outcomes

• Week 1: First 3 experiments launched
• Month 1: 10-15 tests running simultaneously
• Quarter 1: 15-25% average conversion lift
• Quarter 2: 4x increase in experiment velocity

Recipe 5: Content Marketing Automation

Use Case: End-to-end content creation, distribution, and optimization Skills: 7 chained skills Time: 2-3 hours per piece vs 8-12 hours ROI: 2.5x content volume, 40% traffic increase

The Chain

content_research_writer → copywriting → seo_audit →
social_content_generator → email_sequence →
analytics_tracking → social_listening_analyzer

How It Works

1. content_research_writer — Researches topic, generates outline & draft
2. copywriting — Refines copy, optimizes for readability
3. seo_audit — Ensures SEO best practices
4. social_content_generator — Creates social posts
5. email_sequence — Generates email promotion sequence
6. analytics_tracking — Tracks performance
7. social_listening_analyzer — Monitors engagement

Setup Instructions

Step 1: Install Marketing Skills

npx skills-directory install --target all --domain marketing

Step 2: Configure Content Research & Writing

{
  "skill": "content_research_writer",
  "input": {
    "topic": "{{user_input.topic}}",
    "audience": "{{company.buyer_persona}}",
    "contentType": "blog_post",
    "targetLength": 1500,
    "includeExamples": true
  },
  "exit_routing": {
    "draft_complete": "copywriting"
  }
}

Step 3: Refine Copy

{
  "skill": "copywriting",
  "input": {
    "draft": "{{previous.output}}",
    "tone": "professional_friendly",
    "optimizeFor": ["clarity", "engagement", "cta_conversion"]
  },
  "exit_routing": {
    "copy_refined": "seo_audit"
  }
}

Step 4: SEO Optimization

{
  "skill": "seo_audit",
  "input": {
    "content": "{{previous.output}}",
    "targetKeyword": "{{research.primary_keyword}}",
    "checks": [
      "keyword_density",
      "meta_description",
      "headings",
      "internal_links",
      "readability"
    ]
  },
  "exit_routing": {
    "seo_optimized": "social_content_generator"
  }
}

Step 5: Generate Social Content

{
  "skill": "social_content_generator",
  "input": {
    "article": "{{chain.final_content}}",
    "platforms": ["twitter", "linkedin", "facebook"],
    "postsPerPlatform": 3,
    "includeImages": true
  },
  "exit_routing": {
    "social_content_ready": "email_sequence"
  }
}

Step 6: Create Email Sequence

{
  "skill": "email_sequence",
  "input": {
    "content": "{{chain.final_content}}",
    "sequenceType": "nurture",
    "emailCount": 3,
    "spacing": "3_days"
  }
}

Step 7: Track & Listen

{
  "skill": "analytics_tracking",
  "input": {
    "contentId": "{{chain.contentId}}",
    "metrics": ["views", "time_on_page", "conversions", "social_shares"]
  }
},
{
  "skill": "social_listening_analyzer",
  "input": {
    "contentUrl": "{{chain.publish_url}}",
    "keywords": "{{chain.target_keywords}}",
    "sentiment": true
  }
}

Content Pipeline Dashboard

┌─────────────────────────────────────────────┐
│ This Month: Content Production             │
├─────────────────────────────────────────────┤
│ Published: 22 articles (↑ 2.5x)            │
│ Organic Traffic: +43%                      │
│ Social Engagement: 12K interactions        │
│ Email CTR: 4.2% (↑ 0.8%)                   │
│ Time Saved: 180 hours                      │
└─────────────────────────────────────────────┘

Expected Outcomes

• Week 1: First 3 pieces published
• Month 1: 20+ pieces published
• Quarter 1: 40% increase in organic traffic
• Quarter 2: Content team 3x more productive

Recipe 6-10: Quick Reference

Recipe 6: Customer Onboarding Automation

onboarding_health → guided_setup_wizard → milestone_celebration →
time_to_value → activation_metrics

ROI: 50% faster time-to-value, 30% higher activation

Recipe 7: Support Ticket Triage & Resolution

support_ticket_triage → support_resolution_suggester →
support_kb_gap_finder → support_bug_linker

ROI: 40% faster resolution, 60% ticket deflection

Recipe 8: Partnership Deal Flow

partner_mapping → nearbound_signal → co_sell_trigger →
deal_registration → partner_influenced_revenue

ROI: 25% more partner-sourced pipeline

Recipe 9: Pricing & Packaging Optimization

pricing_strategy → packaging_optimizer → price_experimentation →
upgrade_trigger → consumption_analyzer

ROI: 15-25% revenue per customer increase

Recipe 10: Product Analytics Intelligence

product_analytics → feature_adoption → friction_detector →
pql_scoring → expansion_playbook

ROI: 2x product-led pipeline generation

Phase 2: High-Confidence Recipes (11-28)

These recipes expand into new domains with 95%+ skill coverage validated against the library.

Recipe 11: Freemium Conversion Optimization

Use Case: Optimize trial-to-paid conversion for freemium products with automated upgrade triggers and self-serve expansion workflows Skills: 6 chained skills Time: Real-time monitoring vs manual quarterly reviews ROI: 35% trial-to-paid lift, 25% faster conversion cycle, $300K-$800K ARR increase

The Chain

pql_scoring → onboarding_health → feature_adoption →
upgrade_trigger → paywall_upgrade_cro → self_serve_expansion

How It Works

1. pql_scoring — Scores trial users based on product engagement, feature usage, and behavioral fit
2. onboarding_health — Monitors trial health and identifies at-risk users early
3. feature_adoption — Tracks which premium features drive conversion decisions
4. upgrade_trigger — Identifies optimal moments to surface upgrade prompts
5. paywall_upgrade_cro — A/B tests paywall messaging, pricing display, and call-to-action
6. self_serve_expansion — Enables frictionless self-service plan upgrades

Setup Instructions

Step 1: Install PLG & Monetization Skills

npx skills-directory install --target all --domain plg monetization

Step 2: Configure PQL Scoring

{
  "skill": "pql_scoring",
  "trigger": "user_event",
  "input": {
    "userId": "{{trigger.userId}}",
    "events": ["feature_used", "time_spent", "invites_sent", "integration_added"],
    "scoringModel": "engagement_based",
    "threshold": 70
  },
  "exit_routing": {
    "high_score": "onboarding_health",
    "low_score": "activation_campaign"
  }
}

Step 3: Monitor Onboarding Health

{
  "skill": "onboarding_health",
  "input": {
    "userId": "{{previous.userId}}",
    "pqlScore": "{{previous.score}}",
    "trialDaysRemaining": "{{user.trial_days_left}}",
    "healthSignals": ["login_frequency", "feature_usage", "team_invites", "setup_completion"]
  },
  "exit_routing": {
    "healthy": "feature_adoption",
    "at_risk": "retention_campaign",
    "churned": "win_back_campaign"
  }
}

Step 4: Track Feature Adoption

{
  "skill": "feature_adoption",
  "input": {
    "userId": "{{chain.userId}}",
    "onboardingData": "{{previous.health_data}}",
    "premiumFeatures": ["advanced_analytics", "team_collaboration", "api_access", "custom_integrations"],
    "trackingWindow": "7_days"
  },
  "exit_routing": {
    "premium_used": "upgrade_trigger",
    "basic_only": "feature_education"
  }
}

Step 5: Trigger Upgrade Prompts

{
  "skill": "upgrade_trigger",
  "input": {
    "userId": "{{chain.userId}}",
    "adoptionData": "{{previous.feature_usage}}",
    "pqlScore": "{{chain.pql_score}}",
    "triggerType": "feature_limit",
    "timing": "optimal_moment"
  },
  "exit_routing": {
    "trigger_sent": "paywall_upgrade_cro",
    "wait": "monitor_only"
  }
}

Step 6: Optimize Paywall Experience

{
  "skill": "paywall_upgrade_cro",
  "input": {
    "userId": "{{chain.userId}}",
    "context": "{{chain.all_data}}",
    "variants": ["value_focused", "urgency_focused", "social_proof", "comparison_table"],
    "testDuration": "14_days"
  },
  "exit_routing": {
    "converted": "self_serve_expansion",
    "dismissed": "follow_up_sequence"
  }
}

Step 7: Enable Self-Serve Expansion

{
  "skill": "self_serve_expansion",
  "input": {
    "userId": "{{chain.userId}}",
    "selectedPlan": "{{previous.plan_choice}}",
    "paymentMethod": "{{user.payment_method}}",
    "prorateOption": true
  },
  "output": "send_to_billing"
}

Testing the Chain

curl -X POST http://localhost:3000/api/chains/freemium-conversion \
  -H "Content-Type: application/json" \
  -d '{
    "userId": "test-user-123",
    "trialData": {
      "daysInTrial": 10,
      "featureUsage": {
        "basic": 15,
        "advanced": 3,
        "premium": 1
      },
      "teamSize": 1,
      "setupComplete": true
    }
  }'

Expected Output

{
  "converted": true,
  "pqlScore": 87,
  "onboardingHealth": "healthy",
  "premiumFeaturesUsed": ["advanced_analytics"],
  "triggerType": "feature_limit",
  "paywallVariant": "value_focused",
  "selectedPlan": "pro_monthly",
  "conversionTime": "Day 11 of 14",
  "estimatedLTV": "$2,400",
  "timeline": "Converted within optimal window"
}

Monitoring & Metrics

Track these KPIs:

• Trial-to-Paid Rate: Target > 30% (baseline ~5-10%)
• Time to Conversion: Target < 10 days (baseline ~12 days)
• Paywall Conversion Rate: Target > 15%
• Self-Serve Upgrade Rate: Track monthly expansion revenue
• PQL Score Distribution: Monitor score accuracy vs actual conversions

Expected Outcomes

• Week 1: Chain deployed, monitoring 100+ trial users
• Month 1: 35% trial-to-paid improvement vs. control group
• Quarter 1: $300K-$800K incremental ARR from improved conversions
• Quarter 2: Self-serve expansion driving 20%+ of new ARR

Recipe 12: Usage-Based Pricing Engine

Use Case: Implement consumption-based pricing with automated metering, overage prediction, and billing workflows Skills: 6 chained skills Time: Real-time usage tracking vs monthly manual reconciliation ROI: 25% revenue per customer increase, 15% churn reduction, $400K-$1M ARR lift

The Chain

usage_metering → consumption_analyzer → overage_predictor →
dunning_automation → limit_notification → invoice_explainer

How It Works

1. usage_metering — Tracks real-time product usage across all billing dimensions
2. consumption_analyzer — Analyzes usage patterns, identifies trends and anomalies
3. overage_predictor — Predicts when customers will exceed plan limits
4. dunning_automation — Automates payment collection and retry logic
5. limit_notification — Alerts customers before hitting usage limits
6. invoice_explainer — Generates detailed, easy-to-understand invoices

Setup Instructions

Step 1: Install Monetization Skills

npx skills-directory install --target all --domain monetization

Step 2: Configure Usage Metering

{
  "skill": "usage_metering",
  "trigger": "usage_event",
  "input": {
    "accountId": "{{trigger.accountId}}",
    "metricType": "{{trigger.metric}}",
    "dimensions": ["api_calls", "storage_gb", "compute_hours", "seats"],
    "aggregationWindow": "hourly",
    "granularity": "high"
  },
  "exit_routing": {
    "metered": "consumption_analyzer"
  }
}

Step 3: Analyze Consumption Patterns

{
  "skill": "consumption_analyzer",
  "input": {
    "accountId": "{{previous.accountId}}",
    "usageData": "{{previous.metrics}}",
    "analysisWindow": "30_days",
    "compareWith": ["plan_limits", "historical_usage", "cohort_avg"]
  },
  "exit_routing": {
    "within_limits": "monitor_only",
    "approaching_limit": "overage_predictor",
    "exceeded_limit": "dunning_automation"
  }
}

Step 4: Predict Overage Events

{
  "skill": "overage_predictor",
  "input": {
    "accountId": "{{chain.accountId}}",
    "consumptionTrend": "{{previous.trend}}",
    "planLimits": "{{account.plan_limits}}",
    "predictionHorizon": "7_days",
    "confidence": "high"
  },
  "exit_routing": {
    "overage_likely": "limit_notification",
    "within_buffer": "monitor_only"
  }
}

Step 5: Send Limit Notifications

{
  "skill": "limit_notification",
  "input": {
    "accountId": "{{chain.accountId}}",
    "usagePercent": "{{previous.usage_percent}}",
    "estimatedOverage": "{{previous.overage_amount}}",
    "notificationTiming": ["75_percent", "90_percent", "100_percent"],
    "includeUpgradeOptions": true
  },
  "exit_routing": {
    "notified": "dunning_automation",
    "upgraded": "usage_metering"
  }
}

Step 6: Automate Payment Collection

{
  "skill": "dunning_automation",
  "input": {
    "accountId": "{{chain.accountId}}",
    "invoiceAmount": "{{chain.total_amount}}",
    "paymentMethod": "{{account.payment_method}}",
    "retryStrategy": "exponential_backoff",
    "maxRetries": 3
  },
  "exit_routing": {
    "payment_successful": "invoice_explainer",
    "payment_failed": "billing_alert"
  }
}

Step 7: Generate Invoice Explanation

{
  "skill": "invoice_explainer",
  "input": {
    "accountId": "{{chain.accountId}}",
    "usageData": "{{chain.all_usage}}",
    "charges": "{{previous.charges}}",
    "format": "detailed_breakdown",
    "includeComparisons": true
  },
  "output": "send_to_customer"
}

Testing the Chain

curl -X POST http://localhost:3000/api/chains/usage-billing \
  -H "Content-Type: application/json" \
  -d '{
    "accountId": "test-account-456",
    "usageData": {
      "api_calls": 950000,
      "storage_gb": 450,
      "compute_hours": 1800,
      "plan_limit": 1000000
    },
    "billingPeriod": "2026-02"
  }'

Expected Output

{
  "metered": true,
  "usagePercent": 95,
  "overagePredicted": true,
  "estimatedOverage": "$250",
  "notificationSent": true,
  "paymentProcessed": true,
  "invoiceGenerated": true,
  "breakdown": {
    "base_plan": "$99",
    "overage_charges": "$250",
    "total": "$349"
  },
  "nextAction": "Monitor usage next cycle"
}

Monitoring & Metrics

Track these KPIs:

• Revenue Per Customer: Target 25% increase from usage-based pricing
• Payment Success Rate: Target > 95%
• Overage Notification Effectiveness: Track upgrade rate after notifications
• Invoice Dispute Rate: Target < 2%
• Customer Satisfaction with Billing: Track NPS on billing experience

Expected Outcomes

• Week 1: Usage metering deployed, tracking 50+ accounts
• Month 1: 25% revenue increase from usage-based charges
• Quarter 1: 15% churn reduction due to transparent pricing
• Quarter 2: $400K-$1M ARR lift from consumption pricing model

Recipe 13: Product-Led Sales Handoff

Use Case: Bridge self-serve and sales motions by automatically routing product-qualified leads to sales with full context Skills: 6 chained skills Time: Automated PQL detection vs manual review (2+ hours per lead) ROI: 3x PQL-to-opportunity conversion, $1M-$3M pipeline capture, 40% faster sales cycles

The Chain

pql_scoring → usage_depth_analyzer → expansion_playbook →
handoff_orchestration → cpq_quote_generator → deal_inspection

How It Works

1. pql_scoring — Identifies product-qualified leads based on usage patterns and engagement
2. usage_depth_analyzer — Analyzes depth of product adoption and power user behaviors
3. expansion_playbook — Recommends expansion strategies based on usage patterns
4. handoff_orchestration — Coordinates seamless handoff from product to sales
5. cpq_quote_generator — Auto-generates quotes based on usage and expansion opportunity
6. deal_inspection — Validates deal health and identifies potential blockers

Setup Instructions

Step 1: Install PLG & RevOps Skills

npx skills-directory install --target all --domain plg revops

Step 2: Configure PQL Scoring

{
  "skill": "pql_scoring",
  "trigger": "scheduled",
  "frequency": "daily",
  "input": {
    "accountIds": "{{all_active_accounts}}",
    "signals": [
      "feature_usage",
      "team_size",
      "integration_count",
      "api_usage",
      "storage_consumption"
    ],
    "threshold": 75,
    "scoringModel": "product_led"
  },
  "exit_routing": {
    "pql_qualified": "usage_depth_analyzer",
    "not_qualified": "nurture_sequence"
  }
}

Step 3: Analyze Usage Depth

{
  "skill": "usage_depth_analyzer",
  "input": {
    "accountId": "{{previous.accountId}}",
    "pqlScore": "{{previous.score}}",
    "analysisDepth": "comprehensive",
    "lookbackWindow": "90_days",
    "metrics": ["feature_breadth", "power_user_count", "collaboration_score"]
  },
  "exit_routing": {
    "expansion_ready": "expansion_playbook",
    "early_stage": "product_education"
  }
}

Step 4: Generate Expansion Playbook

{
  "skill": "expansion_playbook",
  "input": {
    "accountId": "{{chain.accountId}}",
    "usageAnalysis": "{{previous.analysis}}",
    "currentPlan": "{{account.plan}}",
    "expansionVectors": ["seats", "features", "usage_tier", "enterprise_upgrade"],
    "targetARR": "calculate"
  },
  "exit_routing": {
    "playbook_ready": "handoff_orchestration",
    "needs_enrichment": "data_enrichment"
  }
}

Step 5: Orchestrate Sales Handoff

{
  "skill": "handoff_orchestration",
  "input": {
    "accountId": "{{chain.accountId}}",
    "pqlData": "{{chain.pql_data}}",
    "expansionPlan": "{{previous.playbook}}",
    "assignmentRules": "territory_based",
    "notifyRep": true,
    "notifyCustomer": false
  },
  "exit_routing": {
    "assigned_to_sales": "cpq_quote_generator",
    "hold_for_timing": "schedule_outreach"
  }
}

Step 6: Generate Quote

{
  "skill": "cpq_quote_generator",
  "input": {
    "accountId": "{{chain.accountId}}",
    "expansionPlan": "{{chain.expansion_plan}}",
    "discountRules": "apply_pql_discount",
    "pricingModel": "usage_based",
    "includeOnboarding": true
  },
  "exit_routing": {
    "quote_generated": "deal_inspection",
    "needs_approval": "manager_review"
  }
}

Step 7: Inspect Deal Health

{
  "skill": "deal_inspection",
  "input": {
    "dealId": "{{previous.dealId}}",
    "depth": "comprehensive",
    "checkpoints": ["budget", "authority", "timeline", "competition"],
    "riskFactors": true
  },
  "output": "send_to_rep_with_insights"
}

Testing the Chain

curl -X POST http://localhost:3000/api/chains/pql-handoff \
  -H "Content-Type: application/json" \
  -d '{
    "accountId": "test-account-789",
    "usageData": {
      "seats": 15,
      "featuresUsed": 12,
      "apiCalls": 500000,
      "teamCollaboration": "high",
      "powerUsers": 5
    },
    "currentPlan": "pro"
  }'

Expected Output

{
  "pqlQualified": true,
  "pqlScore": 89,
  "usageDepth": "high",
  "expansionOpportunity": {
    "type": "enterprise_upgrade",
    "estimatedARR": "$50,000",
    "confidence": "high"
  },
  "assignedTo": "rep_john_smith",
  "quoteGenerated": true,
  "dealHealth": "healthy",
  "recommendedActions": [
    "Schedule discovery call within 48 hours",
    "Present enterprise features demo",
    "Discuss API rate limits and custom integration needs"
  ],
  "timeline": "Close within 30 days"
}

Monitoring & Metrics

Track these KPIs:

• PQL-to-Opportunity Rate: Target > 60% (baseline ~20%)
• PQL-to-Close Rate: Target > 15% (baseline ~5%)
• Sales Cycle Length: Target 30-40 days (baseline 60-90 days)
• Average Deal Size: Target $50K+ for enterprise upgrades
• Rep Satisfaction: Track rep feedback on PQL quality

Expected Outcomes

• Week 1: PQL detection running, 10-20 accounts identified
• Month 1: 3x improvement in PQL-to-opportunity conversion
• Quarter 1: $1M-$3M incremental pipeline from product-led motion
• Quarter 2: 40% reduction in sales cycle for product-led deals

Recipe 14: AI Support Deflection System

Use Case: Automate support ticket triage, classification, and resolution with AI-powered response generation and knowledge gap detection Skills: 6 chained skills Time: < 1 minute automated resolution vs 4-8 hour manual response time ROI: 70% ticket deflection, 50% support cost reduction, $150K-$300K annual savings

The Chain

ai_ticket_classifier → ai_intent_classifier → ai_response_suggester →
support_resolution_suggester → support_kb_gap_finder → support_deflector

How It Works

1. ai_ticket_classifier — Automatically classifies tickets by type, priority, and routing
2. ai_intent_classifier — Identifies customer intent and underlying issue
3. ai_response_suggester — Generates contextual AI-powered response drafts
4. support_resolution_suggester — Recommends resolution steps based on historical patterns
5. support_kb_gap_finder — Identifies missing knowledge base articles
6. support_deflector — Deflects tickets to self-serve resources when appropriate

Setup Instructions

Step 1: Install AI Ops & Support Ops Skills

npx skills-directory install --target all --domain ai_ops support_ops

Step 2: Configure AI Ticket Classification

{
  "skill": "ai_ticket_classifier",
  "trigger": "ticket_created",
  "input": {
    "ticketId": "{{trigger.ticketId}}",
    "ticketContent": "{{trigger.body}}",
    "customerContext": "{{customer.history}}",
    "classificationTypes": ["bug", "feature_request", "how_to", "billing", "technical"],
    "priorityLevels": ["urgent", "high", "normal", "low"]
  },
  "exit_routing": {
    "classified": "ai_intent_classifier",
    "needs_human": "escalate_immediately"
  }
}

Step 3: Classify Customer Intent

{
  "skill": "ai_intent_classifier",
  "input": {
    "ticketId": "{{chain.ticketId}}",
    "ticketType": "{{previous.classification}}",
    "customerMessage": "{{trigger.body}}",
    "contextualData": "{{customer.account_data}}",
    "intentCategories": ["resolve_issue", "get_information", "request_feature", "report_bug", "cancel_service"]
  },
  "exit_routing": {
    "intent_clear": "ai_response_suggester",
    "intent_ambiguous": "clarification_needed"
  }
}

Step 4: Generate AI Response

{
  "skill": "ai_response_suggester",
  "input": {
    "ticketId": "{{chain.ticketId}}",
    "intent": "{{previous.intent}}",
    "classification": "{{chain.classification}}",
    "knowledgeBase": "search",
    "tone": "professional_friendly",
    "includeLinks": true
  },
  "exit_routing": {
    "response_generated": "support_resolution_suggester",
    "kb_gaps_found": "support_kb_gap_finder"
  }
}

Step 5: Suggest Resolution Steps

{
  "skill": "support_resolution_suggester",
  "input": {
    "ticketId": "{{chain.ticketId}}",
    "intent": "{{chain.intent}}",
    "aiResponse": "{{previous.response}}",
    "historicalResolutions": "search_similar",
    "resolutionType": ["self_serve", "agent_assisted", "escalated"]
  },
  "exit_routing": {
    "self_serve_possible": "support_deflector",
    "needs_agent": "assign_to_agent",
    "needs_escalation": "escalate_to_tier2"
  }
}

Step 6: Find Knowledge Base Gaps

{
  "skill": "support_kb_gap_finder",
  "input": {
    "ticketId": "{{chain.ticketId}}",
    "ticketType": "{{chain.classification}}",
    "searchAttempts": "{{chain.kb_searches}}",
    "commonQueries": "analyze",
    "gapThreshold": 3
  },
  "exit_routing": {
    "gap_found": "create_kb_article_task",
    "no_gap": "support_deflector"
  }
}

Step 7: Deflect to Self-Serve

{
  "skill": "support_deflector",
  "input": {
    "ticketId": "{{chain.ticketId}}",
    "aiResponse": "{{chain.ai_response}}",
    "resolutionSteps": "{{previous.steps}}",
    "kbArticles": "{{chain.relevant_articles}}",
    "deflectionConfidence": "{{previous.confidence}}"
  },
  "output": "send_to_customer_or_agent"
}

Testing the Chain

curl -X POST http://localhost:3000/api/chains/support-deflection \
  -H "Content-Type: application/json" \
  -d '{
    "ticketId": "test-ticket-001",
    "customerMessage": "How do I reset my API key?",
    "customerId": "cust_123",
    "accountType": "pro"
  }'

Expected Output

{
  "ticketClassified": true,
  "classification": "how_to",
  "priority": "normal",
  "intent": "get_information",
  "aiResponseGenerated": true,
  "deflectionPossible": true,
  "kbArticles": [
    "How to Reset Your API Key",
    "API Security Best Practices"
  ],
  "resolutionSteps": [
    "Navigate to Settings > API Keys",
    "Click 'Regenerate Key'",
    "Update key in your application"
  ],
  "deflected": true,
  "estimatedResolutionTime": "< 1 minute",
  "supportCostSaved": "$25"
}

Monitoring & Metrics

Track these KPIs:

• Deflection Rate: Target > 70% of eligible tickets
• First Response Time: Target < 1 minute for AI responses
• Customer Satisfaction: Target > 4.5/5 for deflected tickets
• Support Cost Savings: Target $150K-$300K annually
• Knowledge Base Coverage: Track gap identification and article creation

Expected Outcomes

• Week 1: AI classification active on 100% of tickets
• Month 1: 70% deflection rate for how-to and informational tickets
• Quarter 1: $50K-$100K support cost savings
• Quarter 2: 90% coverage in knowledge base, minimal gaps

Recipe 15: Developer Experience Onboarding

Use Case: Accelerate developer onboarding with automated API documentation, code samples, sandbox provisioning, and integration health monitoring Skills: 6 chained skills Time: 2-4 hours to first API call vs 4-8 weeks manual process ROI: 60% faster integration time, 40% higher completion rate, 2x API adoption

The Chain

api_onboarding → code_sample_generator → sandbox_manager →
integration_health → error_explainer → changelog_tracker

How It Works

1. api_onboarding — Guides developers through API setup, authentication, and first call
2. code_sample_generator — Generates working code examples in multiple languages
3. **sandbox_m

…(truncated)