Cohort Analyzer
by a5c-ai
Analyzes revenue cohorts, retention curves, LTV/CAC trends over time
Skill Details
Repository Files
1 file in this skill directory
name: cohort-analyzer description: Analyzes revenue cohorts, retention curves, LTV/CAC trends over time allowed-tools:
- Read
- Write
- Glob
- Grep
- Bash
- WebFetch metadata: specialization: venture-capital domain: business skill-id: vc-skill-011
Cohort Analyzer
Overview
The Cohort Analyzer skill provides systematic analysis of customer and revenue cohorts to understand retention patterns, lifetime value trends, and business health over time. It enables deep understanding of unit economics evolution and customer quality.
Capabilities
Revenue Cohort Analysis
- Track revenue by acquisition cohort
- Analyze net revenue retention (NRR) by cohort
- Measure expansion, contraction, and churn
- Identify cohort quality trends over time
Retention Curve Analysis
- Build and visualize retention curves
- Compare retention across cohorts
- Calculate retention benchmarks by segment
- Identify retention inflection points
LTV/CAC Analysis
- Calculate LTV by cohort and segment
- Track CAC trends over time
- Analyze LTV/CAC ratio evolution
- Model payback period by cohort
Segment Analysis
- Segment cohorts by customer type
- Analyze channel-specific cohort quality
- Compare enterprise vs. SMB retention
- Identify highest-value customer segments
Usage
Analyze Revenue Cohorts
Input: Revenue data by customer and month
Process: Build cohort matrix, calculate retention
Output: Cohort analysis, NRR by cohort, visualizations
Build Retention Curves
Input: Customer data with start dates and activity
Process: Calculate retention by period since acquisition
Output: Retention curves, benchmark comparisons
Calculate Unit Economics
Input: Revenue cohorts, CAC data, time horizon
Process: Calculate LTV, LTV/CAC, payback
Output: Unit economics summary, trend analysis
Identify Cohort Trends
Input: Multi-period cohort data
Process: Analyze quality trends, flag concerns
Output: Trend analysis, quality assessment
Key Metrics
| Metric | Calculation | Target Range |
|---|---|---|
| NRR (Net Revenue Retention) | (Start + Expansion - Churn) / Start | 100-130%+ |
| GRR (Gross Revenue Retention) | (Start - Churn) / Start | 85-95%+ |
| LTV/CAC | Lifetime Value / Customer Acquisition Cost | 3x+ |
| Payback Period | Months to recover CAC | 12-18 months |
Integration Points
- Financial Due Diligence: Support revenue quality analysis
- Financial Model Validator: Validate retention assumptions
- Quarterly Portfolio Reporting: Track portfolio company cohorts
- Customer Reference Tracker: Connect qualitative feedback
Visualization Outputs
- Cohort retention heatmaps
- Retention curve comparisons
- LTV/CAC trend charts
- Cohort revenue waterfalls
- Segment comparison charts
Best Practices
- Use monthly cohorts for SaaS, adjust for business model
- Separate new logo vs. expansion revenue
- Analyze both count and revenue retention
- Look for cohort quality degradation as signal
- Segment analysis often reveals hidden patterns
Related Skills
Attack Tree Construction
Build comprehensive attack trees to visualize threat paths. Use when mapping attack scenarios, identifying defense gaps, or communicating security risks to stakeholders.
Grafana Dashboards
Create and manage production Grafana dashboards for real-time visualization of system and application metrics. Use when building monitoring dashboards, visualizing metrics, or creating operational observability interfaces.
Matplotlib
Foundational plotting library. Create line plots, scatter, bar, histograms, heatmaps, 3D, subplots, export PNG/PDF/SVG, for scientific visualization and publication figures.
Scientific Visualization
Create publication figures with matplotlib/seaborn/plotly. Multi-panel layouts, error bars, significance markers, colorblind-safe, export PDF/EPS/TIFF, for journal-ready scientific plots.
Seaborn
Statistical visualization. Scatter, box, violin, heatmaps, pair plots, regression, correlation matrices, KDE, faceted plots, for exploratory analysis and publication figures.
Shap
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model
Pydeseq2
Differential gene expression analysis (Python DESeq2). Identify DE genes from bulk RNA-seq counts, Wald tests, FDR correction, volcano/MA plots, for RNA-seq analysis.
Query Writing
For writing and executing SQL queries - from simple single-table queries to complex multi-table JOINs and aggregations
Pydeseq2
Differential gene expression analysis (Python DESeq2). Identify DE genes from bulk RNA-seq counts, Wald tests, FDR correction, volcano/MA plots, for RNA-seq analysis.
Scientific Visualization
Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell). Orchestrates matplotlib/seaborn/plotly with publication styles. For quick exploration use seaborn or plotly directly.