Saas Metrics Coach

Saas Metrics Coach

SaaS financial health advisor. Use when a user shares revenue or customer numbers, or mentions ARR, MRR, churn, LTV, CAC, NRR, or asks how their SaaS

Category: development Source: alirezarezvani/claude-skills

What Is Saas Metrics Coach?

Saas Metrics Coach is an intelligent SaaS financial health advisor that acts as a senior CFO assistant for SaaS founders, product owners, and finance teams. It is designed to take raw business data — such as revenue, customer numbers, and costs — and transform them into actionable insights about the financial performance and growth health of a SaaS business. The skill supports calculation of key SaaS metrics like ARR (Annual Recurring Revenue), MRR (Monthly Recurring Revenue), churn rates, customer lifetime value (LTV), customer acquisition cost (CAC), net revenue retention (NRR), and more. By comparing these calculated metrics against industry benchmarks, Saas Metrics Coach offers prioritized, plain-English advice to help businesses identify opportunities and address risks.

You can find the source code and further documentation on GitHub.

Why Use Saas Metrics Coach?

SaaS businesses thrive or fail based on their ability to monitor and react to key financial and operational metrics. Manual calculation and benchmarking of metrics like churn, LTV, CAC, and NRR can be error-prone and time-consuming, especially for founders without finance backgrounds. Saas Metrics Coach addresses these challenges by automating the calculation, contextualizing results with industry norms, and providing expert-level recommendations.

Key benefits include:

  • Accuracy: Automatic calculations based on proven SaaS formulas reduce the risk of human error.
  • Benchmarking: Direct comparison with current industry standards to help you understand your competitive position.
  • Actionable Advice: Plain-language recommendations highlight the most pressing issues and opportunities.
  • Adaptability: Works with partial data and makes clear which assumptions are in play, ensuring transparency in the analysis.
  • Time Savings: Quickly transforms raw numbers into strategic insight, freeing up valuable time for other business activities.

How to Get Started

Getting started with Saas Metrics Coach requires providing a set of core business inputs. The skill is designed to interactively request missing data and work with as much information as you can provide.

Step 1: Gather Your Data

Prepare the following information (as much as possible):

  • Revenue: Current MRR (Monthly Recurring Revenue), last month’s MRR, expansion MRR (upsells or upgrades), churned MRR (downgrades or cancellations).
  • Customers: Total active customers, new customers this month, churned customers this month.
  • Costs: Sales and marketing spend, gross margin percentage.

Step 2: Input Your Data

You can input your data directly into the skill’s interface, via an API, or as parameters in a script call. For example, if using the provided Python scripts:

from scripts.metrics_calculator import calculate_metrics

inputs = {
    "current_mrr": 50000,
    "last_month_mrr": 47000,
    "expansion_mrr": 3000,
    "churned_mrr": 1000,
    "active_customers": 1200,
    "new_customers": 80,
    "churned_customers": 20,
    "sales_marketing_spend": 15000,
    "gross_margin_pct": 80
}

metrics = calculate_metrics(inputs)
print(metrics)

Step 3: Review Results and Recommendations

The skill will return a full metrics report, including calculated values and advice, highlighting which numbers are strong or require attention.

Key Features

  • Comprehensive SaaS Metric Calculations: Computes all core metrics, including ARR, MRR growth rate, churn rate, CAC, LTV, LTV:CAC ratio, CAC payback period, and NRR.
  • Benchmarking Engine: Each metric is compared to industry benchmarks (loaded from reference files), making it easy to see where your business stands.
  • Partial Data Support: If you lack some inputs, the coach will tell you what’s missing and proceed with reasonable assumptions, ensuring no analysis is blocked.
  • Quick Ratio and Unit Economics Simulations: Additional scripts, such as quick_ratio_calculator.py and unit_economics_simulator.py, enable deeper analysis when expansion/churn MRR data is available or for forward-looking projections.
  • Plain-English Explanations: The skill summarizes findings and provides prioritized, actionable recommendations, making complex finance concepts accessible.
  • Open Source and Extensible: Licensed under MIT, the skill can be modified and integrated into your own SaaS analytics workflow.

Example: Calculating Churn Rate

def monthly_churn_rate(churned_customers, active_customers_last_month):
    return (churned_customers / active_customers_last_month) * 100

churn_rate = monthly_churn_rate(20, 1200)
print(f"Monthly churn rate: {churn_rate:.2f}%")

Best Practices

  • Provide Complete Data: The more data you provide, the more accurate and nuanced the analysis will be. Always try to include both revenue and customer numbers.
  • Update Regularly: Run the coach monthly or quarterly to track progress and spot trends early.
  • Act on Recommendations: Use the prioritized advice as a starting point for strategic changes or deeper investigation.
  • Integrate with Workflow: Consider automating data extraction from your billing or analytics platforms to feed directly into the skill’s scripts.
  • Review Assumptions: Always check which assumptions the coach has made if you provided partial data, to ensure you agree with the logic.

Important Notes

  • Partial Data Handling: While the skill works with incomplete inputs, outputs may be less precise. Review which data is missing and consider collecting it for better results.
  • Benchmarks Vary: Industry benchmarks are averages and may not reflect your exact SaaS niche or stage. Use them as guidance, not absolute targets.
  • Not a Substitute for Professional Advice: Saas Metrics Coach is a powerful tool for analysis and guidance, but complex financial decisions should still involve qualified finance professionals when necessary.
  • Script Availability: If the provided scripts are unavailable, fallback formulas are used. Results may differ slightly due to implementation details.
  • Open Source License: The skill is MIT licensed; you are free to adapt and contribute improvements as needed. Always check for updates and improvements on the official repository.