Mixpanel Report Generator

Generate comprehensive, shareable reports from your Mixpanel analysis with visualizations, insights, and recommendations.

Pre-flight Check

Verify credentials and data availability:

!$(mp auth test 2>&1 || echo "No credentials configured")
!$(mp inspect tables --format table 2>/dev/null || echo "No local data")

If credentials aren't configured, suggest running /mp-auth first.

Report Types

Based on $1 or ask user to choose:

1. funnel - Conversion funnel analysis report
2. retention - Retention and cohort behavior report
3. dashboard - Executive summary dashboard
4. custom - Custom report from user specifications

---

Report 1: Funnel Analysis Report

Comprehensive conversion funnel report with drop-off analysis.

1. Gather Funnel Data

Determine data source:

• Saved funnel (Live API)
• Custom funnel from local data

Collect required information:

• Funnel steps/events
• Date range
• Segmentation (optional)

2. Execute Analysis

Run funnel query using /mp-funnel approach or direct commands.

3. Generate Report Structure

Create a markdown report with:

# Funnel Analysis Report

**Generated**: <timestamp>
**Date Range**: <from> to <to>
**Funnel**: <funnel-name or event-sequence>

## Executive Summary

- **Overall Conversion Rate**: X%
- **Total Entrants**: N users
- **Final Converters**: M users
- **Biggest Drop-off**: Step X → Step Y (Z% drop)

## Funnel Steps

| Step | Event | Users | Drop-off from Previous | Conversion from Start |
|------|-------|-------|----------------------|----------------------|
| 1 | <event1> | 10,000 | - | 100% |
| 2 | <event2> | 4,500 | 55% | 45% |
| 3 | <event3> | 3,200 | 29% | 32% |
| 4 | <event4> | 2,400 | 25% | 24% |

## Visualization

![Funnel Chart](funnel_chart.png)

## Analysis by Segment

### Top Performing Segments
- **Segment A**: X% conversion (Y% above average)
- **Segment B**: X% conversion (Y% above average)

### Underperforming Segments
- **Segment C**: X% conversion (Y% below average)
- **Segment D**: X% conversion (Y% below average)

## Key Insights

1. **High drop-off at Step X**: Z% of users abandon here
   - Possible causes: [friction point, UX issue, pricing]
   - Recommendation: [specific action]

2. **Segment variation**: Top segment converts at 2x rate of bottom
   - Analysis: [what makes them different]
   - Recommendation: [optimize for successful segment]

## Recommendations

### High Priority
1. [Action 1] - Expected impact: [estimate]
2. [Action 2] - Expected impact: [estimate]

### Medium Priority
3. [Action 3]
4. [Action 4]

## Appendix: Query Details

```sql
[Include the exact queries used]

---

Generated by Mixpanel Data Plugin

### 4. Generate Visualizations

Create funnel chart:

```python
import pandas as pd
import matplotlib.pyplot as plt

steps = ['<step1>', '<step2>', '<step3>', '<step4>']
users = [10000, 4500, 3200, 2400]
conversion_rates = [100, 45, 32, 24]

fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(16, 6))

# Funnel bar chart
colors = ['#4CAF50', '#8BC34A', '#CDDC39', '#FFEB3B']
ax1.barh(steps, users, color=colors)
ax1.set_xlabel('Number of Users')
ax1.set_title('Funnel: User Count by Step')
for i, (step, count) in enumerate(zip(steps, users)):
    ax1.text(count, i, f' {count:,}', va='center')

# Conversion rate trend
ax2.plot(steps, conversion_rates, marker='o', linewidth=2, markersize=10, color='#2196F3')
ax2.set_ylabel('Conversion Rate (%)')
ax2.set_title('Conversion Rate Trend')
ax2.grid(True, alpha=0.3)
for i, (step, rate) in enumerate(zip(steps, conversion_rates)):
    ax2.text(i, rate, f'{rate}%', ha='center', va='bottom')

plt.tight_layout()
plt.savefig('funnel_report.png', dpi=300)
print("Report visualization saved")

5. Save Report

Write to file:

# Save as markdown
<report-content> > funnel_analysis_<date>.md

# Optional: Convert to PDF using pandoc
pandoc funnel_analysis_<date>.md -o funnel_analysis_<date>.pdf

---

Report 2: Cohort & Retention Report

Comprehensive cohort analysis with retention curves and behavior patterns.

1. Gather Retention Data

Execute retention query using /mp-retention approach:

• Born event
• Return event
• Date range
• Time unit (week recommended)

2. Generate Report Structure

# Cohort & Retention Analysis Report

**Generated**: <timestamp>
**Analysis Period**: <from> to <to>
**Cohort Definition**: Users who <born-event>
**Retention Metric**: <return-event>

## Executive Summary

- **Cohorts Analyzed**: N cohorts
- **Total Users**: M users
- **Day 0 Retention**: X%
- **Week 1 Retention**: Y%
- **Long-term Retention**: Z% (stabilized)

## Retention Curve

![Retention Curve](retention_curve.png)

### Retention Benchmarks

| Metric | Your Product | Industry Benchmark | Status |
|--------|--------------|-------------------|---------|
| Day 0 | X% | 40-60% | ✅/⚠️/❌ |
| Week 1 | Y% | 25-40% | ✅/⚠️/❌ |
| Month 1 | Z% | 15-25% | ✅/⚠️/❌ |

## Cohort Comparison

![Cohort Heatmap](cohort_heatmap.png)

### Best Performing Cohorts
1. **Week of <date>**: X% retention - [Analysis of what made this cohort successful]
2. **Week of <date>**: Y% retention

### Struggling Cohorts
1. **Week of <date>**: X% retention - [Analysis of challenges]
2. **Week of <date>**: Y% retention

## Retention Insights

### Positive Signals
- ✅ Retention curve flattens after week 4 (product-market fit indicator)
- ✅ Week 1 retention above industry average
- ✅ Recent cohorts showing improved retention

### Areas of Concern
- ⚠️ Steep drop-off in first week (onboarding opportunity)
- ⚠️ Cohort X underperforming (investigate cause)
- ⚠️ No improvement trend over time (need product changes)

## Recommendations

### Immediate Actions
1. **Improve Day 0-7 Experience**
   - Current: X% retention
   - Target: Y% retention
   - Actions: [specific recommendations]

2. **Investigate Cohort X**
   - Anomaly detected: Z% lower retention
   - Possible causes: [hypotheses]
   - Next steps: [analysis to run]

### Long-term Initiatives
3. [Strategy for improving long-term retention]
4. [Plan for cohort-based optimization]

## Appendix: Detailed Data

[Include cohort-by-cohort breakdown table]

---
*Generated by Mixpanel Data Plugin*

3. Generate Visualizations

Create retention visualizations:

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

# Retention curve
fig, axes = plt.subplots(2, 2, figsize=(16, 12))

# 1. Overall retention curve
intervals = list(range(12))
retention = [100, 48, 42, 38, 35, 33, 31, 30, 29, 28, 27, 27]
axes[0, 0].plot(intervals, retention, marker='o', linewidth=2, markersize=8)
axes[0, 0].set_title('Retention Curve')
axes[0, 0].set_xlabel('Weeks Since Cohort Birth')
axes[0, 0].set_ylabel('Retention Rate (%)')
axes[0, 0].grid(True, alpha=0.3)

# 2. Cohort heatmap (example data)
cohort_data = pd.DataFrame({
    'cohort': ['Week 1', 'Week 2', 'Week 3', 'Week 4'],
    'week_0': [100, 100, 100, 100],
    'week_1': [45, 48, 52, 50],
    'week_4': [30, 32, 35, 33],
    'week_8': [25, 27, 30, 28]
})
cohort_pivot = cohort_data.set_index('cohort')
sns.heatmap(cohort_pivot, annot=True, fmt='.0f', cmap='RdYlGn', ax=axes[0, 1])
axes[0, 1].set_title('Cohort Retention Heatmap')

# 3. Cohort size comparison
cohorts = ['Week 1', 'Week 2', 'Week 3', 'Week 4']
sizes = [5000, 5200, 4800, 5100]
axes[1, 0].bar(cohorts, sizes, color='#2196F3')
axes[1, 0].set_title('Cohort Sizes')
axes[1, 0].set_ylabel('Users')

# 4. Week 1 retention trend
axes[1, 1].plot(cohorts, [45, 48, 52, 50], marker='o', linewidth=2)
axes[1, 1].set_title('Week 1 Retention Trend')
axes[1, 1].set_ylabel('Retention Rate (%)')
axes[1, 1].grid(True, alpha=0.3)

plt.tight_layout()
plt.savefig('cohort_report.png', dpi=300)

---

Report 3: Executive Dashboard

High-level overview for stakeholders with key metrics and trends.

1. Collect Key Metrics

Gather data for:

• Growth metrics: New users, active users, user growth rate
• Engagement metrics: Events per user, DAU/MAU ratio
• Conversion metrics: Key funnel conversion rate
• Retention metrics: Week 1 retention, long-term retention
• Revenue metrics (if applicable): Revenue, ARPU, LTV

2. Generate Dashboard Report

# Mixpanel Analytics Dashboard

**Report Period**: <from> to <to>
**Generated**: <timestamp>

## 🎯 Key Performance Indicators

| Metric | Current Value | Previous Period | Change | Status |
|--------|--------------|-----------------|---------|--------|
| **Active Users** | 12,450 | 11,200 | +11.2% | ✅ |
| **New Signups** | 2,340 | 2,100 | +11.4% | ✅ |
| **Week 1 Retention** | 42% | 38% | +4pp | ✅ |
| **Conversion Rate** | 24% | 22% | +2pp | ✅ |
| **Events/User** | 15.3 | 14.1 | +8.5% | ✅ |

## 📈 Growth Trends

![Growth Chart](growth_trends.png)

### User Growth
- Total users: 125,000 (+15% vs. last period)
- Monthly active users (MAU): 45,000
- Daily active users (DAU): 12,450
- DAU/MAU ratio: 27.7% (healthy engagement)

## 🔄 Conversion Funnel

![Funnel](funnel_summary.png)

- **Sign Up → Activation**: 68% (-2pp vs. last period) ⚠️
- **Activation → First Action**: 45% (+3pp) ✅
- **First Action → Purchase**: 35% (stable) →
- **Overall Conversion**: 24% (+2pp) ✅

**Action Items**: Improve activation step to recover lost ground

## 💪 User Retention

![Retention](retention_summary.png)

- **Day 0**: 62% (+4pp) ✅
- **Week 1**: 42% (+4pp) ✅
- **Month 1**: 28% (+2pp) ✅
- **Stabilized**: 25% (healthy)

**Insight**: Recent product improvements showing positive impact on retention

## 🎨 User Segmentation

| Segment | Users | % of Total | Engagement | Conversion |
|---------|-------|-----------|------------|------------|
| Power Users | 3,500 | 7% | 45 events/user | 65% |
| Regular Users | 18,000 | 36% | 12 events/user | 28% |
| Casual Users | 28,500 | 57% | 3 events/user | 8% |

## 📊 Top Events (Last 30 Days)

1. **Page View**: 450,000 events
2. **Button Click**: 125,000 events
3. **Purchase**: 24,000 events
4. **Sign Up**: 12,000 events
5. **Share**: 8,500 events

## 🚀 Recommendations

### High Priority
1. **Improve Activation Rate**: Currently 68%, target 75%
   - Hypothesis: Onboarding friction
   - Action: A/B test simplified flow

2. **Convert Casual to Regular**: 28,500 users at risk
   - Strategy: Engagement campaign targeting low-activity users
   - Goal: Move 10% to regular tier

### Medium Priority
3. Expand power user features
4. Optimize purchase funnel for mobile

---
*Generated by Mixpanel Data Plugin*

3. Generate Dashboard Visualizations

import matplotlib.pyplot as plt
import pandas as pd
from datetime import datetime, timedelta

fig, axes = plt.subplots(2, 3, figsize=(18, 12))

# 1. User growth trend
dates = pd.date_range(start='2024-01-01', periods=30, freq='D')
users = [10000 + i*500 + (i%7)*200 for i in range(30)]
axes[0, 0].plot(dates, users, linewidth=2, color='#2196F3')
axes[0, 0].set_title('Daily Active Users Trend')
axes[0, 0].grid(True, alpha=0.3)
axes[0, 0].tick_params(axis='x', rotation=45)

# 2. Funnel visualization
# [Similar to funnel report]

# 3. Retention curve
# [Similar to cohort report]

# 4. Segment distribution pie chart
segments = ['Power', 'Regular', 'Casual']
sizes = [3500, 18000, 28500]
axes[1, 0].pie(sizes, labels=segments, autopct='%1.1f%%', startangle=90)
axes[1, 0].set_title('User Segmentation')

# 5. Top events bar chart
events = ['Page View', 'Button Click', 'Purchase', 'Sign Up', 'Share']
counts = [450000, 125000, 24000, 12000, 8500]
axes[1, 1].barh(events, counts, color='#4CAF50')
axes[1, 1].set_title('Top Events (Last 30 Days)')

# 6. KPI summary
kpis = ['Active Users', 'Retention', 'Conversion', 'Engagement']
values = [12450, 42, 24, 15.3]
changes = [11.2, 4, 2, 8.5]
colors = ['g' if c > 0 else 'r' for c in changes]
axes[1, 2].bar(kpis, values, color=colors, alpha=0.7)
axes[1, 2].set_title('Key Metrics')

plt.tight_layout()
plt.savefig('dashboard.png', dpi=300)

---

Report 4: Custom Report

Build a report based on user specifications.

1. Gather Requirements

Ask the user:

• Objective: What question are you trying to answer?
• Metrics: Which metrics matter most?
• Time period: Analysis window
• Audience: Who will read this report?
• Format: Markdown, PDF, or interactive HTML?

2. Build Custom Analysis

Based on requirements, combine:

• Custom SQL queries
• Multiple visualizations
• Comparative analysis
• Segmentation
• Trend analysis

3. Generate Custom Report Structure

Adapt the report structure to match requirements, including:

• Executive summary focused on user's objective
• Relevant metrics and KPIs
• Analysis sections addressing key questions
• Visualizations supporting conclusions
• Actionable recommendations

---

Report Sharing and Export

After generating any report:

1. Save to File

# Create reports directory if needed
mkdir -p reports

# Save report
<report-content> > reports/<report-type>_<date>.md

2. Export Options

Markdown to PDF:

pandoc reports/funnel_analysis.md -o reports/funnel_analysis.pdf

Markdown to HTML:

pandoc reports/cohort_report.md -o reports/cohort_report.html --self-contained

Include visualizations:

pandoc reports/dashboard.md -o reports/dashboard.pdf --include-in-header=<style.css>

3. Distribution

Suggest sharing options:

• Email report file
• Upload to shared drive
• Post to Slack/Teams
• Add to project documentation
• Schedule automated generation

---

Next Steps

After generating report:

1. Review and refine:

   • Check all metrics are accurate
   • Verify visualizations are clear
   • Validate insights and recommendations

2. Share with stakeholders:

   • Identify key recipients
   • Prepare presentation if needed
   • Schedule follow-up discussion

3. Take action:

   • Prioritize recommendations
   • Create tasks for high-priority items
   • Set up monitoring for key metrics

4. Schedule next report:

   • Determine reporting cadence (weekly/monthly/quarterly)
   • Automate report generation if possible
   • Track metrics over time

---

Troubleshooting

"Missing data for report":

• Run /mp-fetch to get necessary data
• Check date range covers analysis period
• Verify required events exist

"Visualizations not generating":

• Check Python/matplotlib installed
• Verify image save path is writable
• Check for data formatting issues

"Report too complex":

• Break into multiple focused reports
• Simplify visualizations
• Focus on top 3-5 insights