
Feature Analytics Framework & Insights Synthesis
Synthesize feature analytics data into actionable product insights
What You Can Do
Transform raw feature analytics into clear, actionable insights by analyzing engagement patterns, identifying performance trends, and synthesizing recommendations. You can compare feature performance across segments, detect anomalies, and generate reports that guide product decisions with data-backed confidence. This skill automates the heavy lifting of analytics interpretation so you focus on strategy.
Features
Accepts raw analytics exports from any platform and normalizes the data into a consistent format for analysis
Identifies user behavior trends like adoption curves, retention patterns, and feature usage seasonality
Compares feature performance across user segments, cohorts, and time periods to surface performance gaps
Flags unexpected drops, spikes, or deviations in key metrics that warrant investigation
Analyzes experiment results and calculates statistical significance, effect sizes, and business impact
Generates ranked, actionable recommendations with confidence levels and supporting evidence from the data
Computes derived metrics like daily active users, feature adoption rate, and user lifetime value trends
Produces formatted reports with visualizations, key findings, and next steps ready for stakeholder communication
Example Output
Feature Analytics Synthesis Example
Input: Raw Google Analytics data showing feature adoption across 3 user segments (Free, Pro, Enterprise) over 90 days
Output:
Key Findings
-
✅ Dashboard feature shows strong adoption in Pro/Enterprise (68% adoption vs 22% Free)
-
Enterprise retention: 87% after 30 days
-
Free tier drop-off: 45% after week 1
-
Recommendation: Introduce guided onboarding for Free users; consider paywalling advanced metrics
-
⚠️ Bulk export feature shows declining usage trend
-
Peak adoption: March (34% WAU)
-
Current: June (12% WAU) — 65% decline
-
Correlates with launch of API (March 15)
-
Action: Survey users who stopped using bulk export; may indicate successful API migration
-
📊 Mobile integration engagement anomaly detected
-
Expected 500 DAU; actual: 180 DAU (64% drop)
-
Spike coincides with iOS app update on June 28
-
Hypothesis: Update introduced UX regression or bug
-
Next Step: Review app release notes, check crash logs
By the Numbers
| Metric | Current | 30-Day Trend | Benchmark |
|---|---|---|---|
| Feature Adoption | 42% | +12% | 35% |
| Retention (Day 7) | 68% | Stable | 55% |
| Time to First Action | 4.2 min | -18% | <3 min |
Recommendation: Run follow-up survey on Free tier barriers; audit iOS app logs; schedule API adoption deep dive.
What's Included
- Analytics Data Template: Structured format guide for feeding your analytics data (CSV, JSON) into Claude for processing
- Engagement Analysis Framework: Step-by-step prompts to identify trends, cohort behavior, and adoption patterns from raw metrics
- Performance Comparison Playbook: Guided questions and analysis methods to benchmark features against each other and industry standards
- Anomaly Investigation Guide: Checklist and hypothesis-generation framework for identifying root causes of unexpected metric changes
- Insight Synthesis Templates: Pre-built prompts that transform data observations into clear findings and ranked recommendations
- Report Format & Distribution Guide: Formatting standards and tips for presenting insights to product, engineering, and executive stakeholders
Who It's For
- Product Managers
- Growth Analysts
- Data Analysts & BI Engineers
- UX Researchers
- Engineering Leaders
Best For
- Weekly or monthly feature performance reviews
- A/B test analysis and statistical evaluation
- Investigating unexpected metric changes or anomalies
- User segment behavior analysis and comparison
- Prioritizing features based on adoption and impact data







