Data Engineering Data Driven Feature

1---
2name: data-engineering-data-driven-feature
3description: "Build features guided by data insights, A/B testing, and continuous measurement using specialized agents for analysis, implementation, and experimentation."
4---
5 
6# Data-Driven Feature Development
7 
8Build features guided by data insights, A/B testing, and continuous measurement using specialized agents for analysis, implementation, and experimentation.
9 
10[Extended thinking: This workflow orchestrates a comprehensive data-driven development process from initial data analysis and hypothesis formulation through feature implementation with integrated analytics, A/B testing infrastructure, and post-launch analysis. Each phase leverages specialized agents to ensure features are built based on data insights, properly instrumented for measurement, and validated through controlled experiments. The workflow emphasizes modern product analytics practices, statistical rigor in testing, and continuous learning from user behavior.]
11 
12## Use this skill when
13 
14- Working on data-driven feature development tasks or workflows
15- Needing guidance, best practices, or checklists for data-driven feature development
16 
17## Do not use this skill when
18 
19- The task is unrelated to data-driven feature development
20- You need a different domain or tool outside this scope
21 
22## Instructions
23 
24- Clarify goals, constraints, and required inputs.
25- Apply relevant best practices and validate outcomes.
26- Provide actionable steps and verification.
27- If detailed examples are required, open `resources/implementation-playbook.md`.
28 
29## Phase 1: Data Analysis and Hypothesis Formation
30 
31### 1. Exploratory Data Analysis
32- Use Task tool with subagent_type="machine-learning-ops::data-scientist"
33- Prompt: "Perform exploratory data analysis for feature: $ARGUMENTS. Analyze existing user behavior data, identify patterns and opportunities, segment users by behavior, and calculate baseline metrics. Use modern analytics tools (Amplitude, Mixpanel, Segment) to understand current user journeys, conversion funnels, and engagement patterns."
34- Output: EDA report with visualizations, user segments, behavioral patterns, baseline metrics
35 
36### 2. Business Hypothesis Development
37- Use Task tool with subagent_type="business-analytics::business-analyst"
38- Context: Data scientist's EDA findings and behavioral patterns
39- Prompt: "Formulate business hypotheses for feature: $ARGUMENTS based on data analysis. Define clear success metrics, expected impact on key business KPIs, target user segments, and minimum detectable effects. Create measurable hypotheses using frameworks like ICE scoring or RICE prioritization."
40- Output: Hypothesis document, success metrics definition, expected ROI calculations
41 
42### 3. Statistical Experiment Design
43- Use Task tool with subagent_type="machine-learning-ops::data-scientist"
44- Context: Business hypotheses and success metrics
45- Prompt: "Design statistical experiment for feature: $ARGUMENTS. Calculate required sample size for statistical power, define control and treatment groups, specify randomization strategy, and plan for multiple testing corrections. Consider Bayesian A/B testing approaches for faster decision making. Design for both primary and guardrail metrics."
46- Output: Experiment design document, power analysis, statistical test plan
47 
48## Phase 2: Feature Architecture and Analytics Design
49 
50### 4. Feature Architecture Planning
51- Use Task tool with subagent_type="data-engineering::backend-architect"
52- Context: Business requirements and experiment design
53- Prompt: "Design feature architecture for: $ARGUMENTS with A/B testing capability. Include feature flag integration (LaunchDarkly, Split.io, or Optimizely), gradual rollout strategy, circuit breakers for safety, and clean separation between control and treatment logic. Ensure architecture supports real-time configuration updates."
54- Output: Architecture diagrams, feature flag schema, rollout strategy
55 
56### 5. Analytics Instrumentation Design
57- Use Task tool with subagent_type="data-engineering::data-engineer"
58- Context: Feature architecture and success metrics
59- Prompt: "Design comprehensive analytics instrumentation for: $ARGUMENTS. Define event schemas for user interactions, specify properties for segmentation and analysis, design funnel tracking and conversion events, plan cohort analysis capabilities. Implement using modern SDKs (Segment, Amplitude, Mixpanel) with proper event taxonomy."
60- Output: Event tracking plan, analytics schema, instrumentation guide
61 
62### 6. Data Pipeline Architecture
63- Use Task tool with subagent_type="data-engineering::data-engineer"
64- Context: Analytics requirements and existing data infrastructure
65- Prompt: "Design data pipelines for feature: $ARGUMENTS. Include real-time streaming for live metrics (Kafka, Kinesis), batch processing for detailed analysis, data warehouse integration (Snowflake, BigQuery), and feature store for ML if applicable. Ensure proper data governance and GDPR compliance."
66- Output: Pipeline architecture, ETL/ELT specifications, data flow diagrams
67 
68## Phase 3: Implementation with Instrumentation
69 
70### 7. Backend Implementation
71- Use Task tool with subagent_type="backend-development::backend-architect"
72- Context: Architecture design and feature requirements
73- Prompt: "Implement backend for feature: $ARGUMENTS with full instrumentation. Include feature flag checks at decision points, comprehensive event tracking for all user actions, performance metrics collection, error tracking and monitoring. Implement proper logging for experiment analysis."
74- Output: Backend code with analytics, feature flag integration, monitoring setup
75 
76### 8. Frontend Implementation
77- Use Task tool with subagent_type="frontend-mobile-development::frontend-developer"
78- Context: Backend APIs and analytics requirements
79- Prompt: "Build frontend for feature: $ARGUMENTS with analytics tracking. Implement event tracking for all user interactions, session recording integration if applicable, performance metrics (Core Web Vitals), and proper error boundaries. Ensure consistent experience between control and treatment groups."
80- Output: Frontend code with analytics, A/B test variants, performance monitoring
81 
82### 9. ML Model Integration (if applicable)
83- Use Task tool with subagent_type="machine-learning-ops::ml-engineer"
84- Context: Feature requirements and data pipelines
85- Prompt: "Integrate ML models for feature: $ARGUMENTS if needed. Implement online inference with low latency, A/B testing between model versions, model performance tracking, and automatic fallback mechanisms. Set up model monitoring for drift detection."
86- Output: ML pipeline, model serving infrastructure, monitoring setup
87 
88## Phase 4: Pre-Launch Validation
89 
90### 10. Analytics Validation
91- Use Task tool with subagent_type="data-engineering::data-engineer"
92- Context: Implemented tracking and event schemas
93- Prompt: "Validate analytics implementation for: $ARGUMENTS. Test all event tracking in staging, verify data quality and completeness, validate funnel definitions, ensure proper user identification and session tracking. Run end-to-end tests for data pipeline."
94- Output: Validation report, data quality metrics, tracking coverage analysis
95 
96### 11. Experiment Setup
97- Use Task tool with subagent_type="cloud-infrastructure::deployment-engineer"
98- Context: Feature flags and experiment design
99- Prompt: "Configure experiment infrastructure for: $ARGUMENTS. Set up feature flags with proper targeting rules, configure traffic allocation (start with 5-10%), implement kill switches, set up monitoring alerts for key metrics. Test randomization and assignment logic."
100- Output: Experiment configuration, monitoring dashboards, rollout plan
101 
102## Phase 5: Launch and Experimentation
103 
104### 12. Gradual Rollout
105- Use Task tool with subagent_type="cloud-infrastructure::deployment-engineer"
106- Context: Experiment configuration and monitoring setup
107- Prompt: "Execute gradual rollout for feature: $ARGUMENTS. Start with internal dogfooding, then beta users (1-5%), gradually increase to target traffic. Monitor error rates, performance metrics, and early indicators. Implement automated rollback on anomalies."
108- Output: Rollout execution, monitoring alerts, health metrics
109 
110### 13. Real-time Monitoring
111- Use Task tool with subagent_type="observability-monitoring::observability-engineer"
112- Context: Deployed feature and success metrics
113- Prompt: "Set up comprehensive monitoring for: $ARGUMENTS. Create real-time dashboards for experiment metrics, configure alerts for statistical significance, monitor guardrail metrics for negative impacts, track system performance and error rates. Use tools like Datadog, New Relic, or custom dashboards."
114- Output: Monitoring dashboards, alert configurations, SLO definitions
115 
116## Phase 6: Analysis and Decision Making
117 
118### 14. Statistical Analysis
119- Use Task tool with subagent_type="machine-learning-ops::data-scientist"
120- Context: Experiment data and original hypotheses
121- Prompt: "Analyze A/B test results for: $ARGUMENTS. Calculate statistical significance with confidence intervals, check for segment-level effects, analyze secondary metrics impact, investigate any unexpected patterns. Use both frequentist and Bayesian approaches. Account for multiple testing if applicable."
122- Output: Statistical analysis report, significance tests, segment analysis
123 
124### 15. Business Impact Assessment
125- Use Task tool with subagent_type="business-analytics::business-analyst"
126- Context: Statistical analysis and business metrics
127- Prompt: "Assess business impact of feature: $ARGUMENTS. Calculate actual vs expected ROI, analyze impact on key business metrics, evaluate cost-benefit including operational overhead, project long-term value. Make recommendation on full rollout, iteration, or rollback."
128- Output: Business impact report, ROI analysis, recommendation document
129 
130### 16. Post-Launch Optimization
131- Use Task tool with subagent_type="machine-learning-ops::data-scientist"
132- Context: Launch results and user feedback
133- Prompt: "Identify optimization opportunities for: $ARGUMENTS based on data. Analyze user behavior patterns in treatment group, identify friction points in user journey, suggest improvements based on data, plan follow-up experiments. Use cohort analysis for long-term impact."
134- Output: Optimization recommendations, follow-up experiment plans
135 
136## Configuration Options
137 
138```yaml
139experiment_config:
140  min_sample_size: 10000
141  confidence_level: 0.95
142  runtime_days: 14
143  traffic_allocation: "gradual"  # gradual, fixed, or adaptive
144 
145analytics_platforms:
146  - amplitude
147  - segment
148  - mixpanel
149 
150feature_flags:
151  provider: "launchdarkly"  # launchdarkly, split, optimizely, unleash
152 
153statistical_methods:
154  - frequentist
155  - bayesian
156 
157monitoring:
158  - real_time_metrics: true
159  - anomaly_detection: true
160  - automatic_rollback: true
161```
162 
163## Success Criteria
164 
165- **Data Coverage**: 100% of user interactions tracked with proper event schema
166- **Experiment Validity**: Proper randomization, sufficient statistical power, no sample ratio mismatch
167- **Statistical Rigor**: Clear significance testing, proper confidence intervals, multiple testing corrections
168- **Business Impact**: Measurable improvement in target metrics without degrading guardrail metrics
169- **Technical Performance**: No degradation in p95 latency, error rates below 0.1%
170- **Decision Speed**: Clear go/no-go decision within planned experiment runtime
171- **Learning Outcomes**: Documented insights for future feature development
172 
173## Coordination Notes
174 
175- Data scientists and business analysts collaborate on hypothesis formation
176- Engineers implement with analytics as first-class requirement, not afterthought
177- Feature flags enable safe experimentation without full deployments
178- Real-time monitoring allows for quick iteration and rollback if needed
179- Statistical rigor balanced with business practicality and speed to market
180- Continuous learning loop feeds back into next feature development cycle
181 
182Feature to develop with data-driven approach: $ARGUMENTS
183