agentleFS
ekinciioekinciio/saas-growth-marketing-skills/skills/subscription-metrics/SKILL.md

subscription-metrics

Skill12 starsChanged 4 months agoMITView on GitHub

Calculate and analyze SaaS subscription metrics. Computes MRR, ARR, CAC, LTV, churn rate, Rule of 40, burn multiple, and other critical SaaS KPIs. Provides health assessment and benchmarks. Use when the user mentions SaaS metrics, MRR, ARR, churn, CAC, LTV, Rule of 40, unit economics, subscription analytics, burn multiple, NRR, net revenue retention, or magic number.

The file

Show its rules and text

We split this skill into the rules it gives an agent

25 rules. About 0 are common, 21 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈21

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When a user runs /subscription-metrics calculate, ALWAYS display this input summary before asking for any data:

    line 18
  2. Distinctive:

    If the user types "demo", use this data to generate a full sample report:

    line 62
  3. Distinctive:

    After showing the summary, ask: "Want to run this with your own numbers now?"

    line 82
  4. Distinctive:

    If the user types "skip" for any metric:

    line 86
  5. Distinctive:

    Never block the entire report because one input is missing

    line 90
  6. Distinctive:

    Ask for monthly revenue data (beginning MRR, new MRR, expansion MRR, contraction MRR, churned MRR)

    line 98
  7. Distinctive:

    Ask for customer counts (beginning of period, new, churned, end of period)

    line 99
  8. Distinctive:

    Ask for cost data (total S&M spend, optional monthly net burn.

    line 100
  9. Distinctive:

    Ask for growth data (YoY revenue growth rate, profit margin or EBITDA margin)

    line 101
  10. Very specific:

    Run scripts/metrics_calculator.py logic to compute all metrics

    line 102
  11. Distinctive:

    Ask for company stage: Seed, Series A, Series B, Growth, Scale

    line 144
  12. Distinctive:

    Ask for vertical: horizontal SaaS, vertical SaaS, infrastructure, dev tools, fintech, healthtech

    line 145
  13. Distinctive:

    Ask for assumptions: expected monthly growth rate, expected churn rate changes, planned expansion revenue

    line 165
  14. Very specific:

    ALWAYS save the complete report to the specified .md file in the current working directory.

    line 182
  15. Distinctive:

    NEVER ask "should I save this?" - just save it automatically.

    line 183
  16. Distinctive:

    If the file already exists, overwrite it.

    line 185
  17. Distinctive:

    ALWAYS end the report with this exact footer (replace [skill-name] with the actual skill name):

    line 186
  18. Distinctive:

    After saving, show a SHORT summary in chat (max 10 lines):

    line 194
  19. Distinctive:

    NEVER dump the full report in chat.

    line 210
  20. Very specific:

    Run it directly: python3 scripts/metrics_calculator.py data.json (a JSON file using the BusinessData field names, e.g.

    line 216
  21. Distinctive:

    Always clarify whether numbers are monthly or annual before calculating

    line 222
  22. Distinctive:

    Use monthly figures as the base and annualize where needed (ARR = MRR x 12)

    line 223
  23. Distinctive:

    When churn is discussed, always distinguish between logo churn and revenue churn

    line 224
  24. Distinctive:

    Never present a single metric in isolation - always show related metrics for context (e.g., CAC with LTV and payback period)

    line 229
  25. Distinctive:

    When recommending improvements, prioritize by impact and feasibility

    line 230

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Subscription Metrics

Calculate, analyze, and benchmark SaaS subscription metrics to understand business health and growth trajectory.

First Run

When a user runs /subscription-metrics calculate, ALWAYS display this input summary before asking for any data:

""" 📊 SaaS Metrics Calculator

What I'll ask you (4 data groups, ~13 numbers):

Revenue data: 1. MRR at start of month ($) → e.g. 100000 2. New MRR this month ($) → e.g. 15000 3. Expansion MRR ($) → e.g. 3000 4. Contraction MRR ($) → e.g. 1000 5. Churned MRR ($) → e.g. 2000

Customer counts: 6. Customers at start of month → e.g. 200 7. New customers this month → e.g. 25 8. Churned customers this month → e.g. 8

Costs: 9. Total S&M spend this month ($) → e.g. 30000 10. Monthly net burn ($) - optional (needed for burn multiple) → e.g. 40000 11. Total operating costs ($) - optional (used to estimate net burn as operating costs − MRR when net burn is not provided) → e.g. 150000

Growth: 12. YoY revenue growth rate (%) → e.g. 80 13. EBITDA or profit margin (%) → e.g. -20

Type "skip" for any you don't have. Type "demo" to see a sample report with example data first.

What you'll get: → MRR, ARR, churn rates, CAC, LTV, LTV:CAC ratio → Rule of 40, burn multiple, SaaS Quick Ratio → Traffic-light health assessment (GREEN/YELLOW/RED) → Saved to SAAS-METRICS-REPORT.md

Ready? Let's start - what's your New MRR this month? """

Demo Mode

If the user types "demo", use this data to generate a full sample report:

{
  "beginning_mrr": 100000,
  "new_mrr": 15000,
  "expansion_mrr": 3000,
  "contraction_mrr": 1000,
  "churned_mrr": 2000,
  "customers_start": 200,
  "customers_new": 25,
  "customers_churned": 8,
  "total_sales_marketing_spend": 30000,
  "net_burn": 40000,
  "yoy_revenue_growth_pct": 80,
  "profit_margin_pct": -20
}

Save the demo report as SAAS-METRICS-REPORT-DEMO.md. After showing the summary, ask: "Want to run this with your own numbers now?"

Skip Handling

If the user types "skip" for any metric:

  • Mark it as "Not provided" in the report
  • Calculate all metrics that are possible with available data
  • Note which metrics could not be calculated and why
  • Never block the entire report because one input is missing

Commands

/subscription-metrics calculate

Interactive metric calculator. Walk the user through providing their raw business data, then compute all relevant SaaS metrics.

Steps:

  1. Ask for monthly revenue data (beginning MRR, new MRR, expansion MRR, contraction MRR, churned MRR)
  2. Ask for customer counts (beginning of period, new, churned, end of period)
  3. Ask for cost data (total S&M spend, optional monthly net burn; total operating costs may be provided as a fallback - net burn is then estimated as operating costs − MRR)
  4. Ask for growth data (YoY revenue growth rate, profit margin or EBITDA margin)
  5. Run scripts/metrics_calculator.py logic to compute all metrics
  6. Present results in a structured table with traffic-light indicators
  7. Provide a short interpretation of each metric

Output format:

Metric                 | Value      | Status  | Benchmark
-----------------------|------------|---------|----------
MRR                    | $125,000   | GREEN   | -
ARR                    | $1,500,000 | GREEN   | -
Monthly Logo Churn     | 2.1%       | YELLOW  | <2%
Monthly Revenue Churn  | 1.8%       | GREEN   | <2%
Net Revenue Retention   | 108%       | GREEN   | >100%
...

Report: Save output to SAAS-METRICS-REPORT.md

/subscription-metrics health

SaaS health scorecard. Generate a comprehensive health assessment based on provided metrics.

Steps:

  1. Collect the same inputs as calculate (or reuse if already provided)
  2. Compute all metrics
  3. Score each metric as GREEN / YELLOW / RED against industry benchmarks
  4. Produce an overall health grade (A through F)
  5. List the top 3 strengths and top 3 areas for improvement
  6. Provide specific, actionable recommendations for each RED or YELLOW metric

Report: Save output to SAAS-HEALTH-REPORT.md

Health grade scale (computed over assessed metrics only - ARPU, CAC, LTV, MRR, and ARR are informational and excluded from the grade):

  • A: ≥80% GREEN and 0 RED
  • B: ≥60% GREEN and ≤1 RED
  • C: ≥40% GREEN and ≤1 RED
  • D: 2 RED, or 20-39% GREEN
  • F: ≥3 RED, or <20% GREEN

/subscription-metrics benchmark

Compare metrics to industry benchmarks segmented by stage and vertical.

Steps:

  1. Ask for company stage: Seed, Series A, Series B, Growth, Scale
  2. Ask for vertical: horizontal SaaS, vertical SaaS, infrastructure, dev tools, fintech, healthtech
  3. Collect current metrics or reuse from prior calculation
  4. Compare each metric against stage-appropriate and vertical-appropriate benchmarks
  5. Show percentile ranking where possible (top 10%, top 25%, median, below median)
  6. Highlight where the company over-performs or under-performs relative to peers

Report: Save output to SAAS-BENCHMARK-REPORT.md

Benchmark ranges by stage (MRR example):

  • Seed: $5K-$50K MRR typical
  • Series A: $50K-$250K MRR typical
  • Series B: $250K-$1M MRR typical
  • Growth: $1M-$5M MRR typical
  • Scale: $5M+ MRR typical

/subscription-metrics forecast

Simple MRR/ARR forecast based on current trajectory and assumptions.

Steps:

  1. Collect current MRR and growth rate (or derive from historical data)
  2. Ask for assumptions: expected monthly growth rate, expected churn rate changes, planned expansion revenue
  3. Project MRR and ARR for 6, 12, 18, and 24 months
  4. Show optimistic (1.5x growth assumption), base, and pessimistic (0.5x growth assumption) scenarios
  5. Calculate months to key milestones ($100K MRR, $1M ARR, etc.)
  6. Flag if current burn rate is unsustainable given the forecast

Output includes:

  • Monthly MRR projection table (3 scenarios)
  • ARR milestones timeline
  • Revenue growth chart description (text-based)
  • Cash runway estimate if burn data is provided

Report: Save output to SAAS-FORECAST-REPORT.md

Output Rules (MANDATORY)

File Output

  • ALWAYS save the complete report to the specified .md file in the current working directory.
  • NEVER ask "should I save this?" - just save it automatically.
  • Include **Date:** YYYY-MM-DD in the report header.
  • If the file already exists, overwrite it.
  • ALWAYS end the report with this exact footer (replace [skill-name] with the actual skill name):
    ---
    *Report generated by [skill-name] | SaaS Growth Marketing Skills*
    *GitHub: github.com/ekinciio/saas-growth-marketing-skills*

Chat Output

After saving, show a SHORT summary in chat (max 10 lines):

""" ✅ Metrics calculated - saved to SAAS-METRICS-REPORT.md

Health Grade: [A-F] MRR: $[X] | ARR: $[X] | Monthly Churn: [X]%

Highlights: 🟢 [Strongest metric + value] 🔴 [Weakest metric + value] 🔴 [Second weakest + value]

Full dashboard with all metrics and benchmarks → open SAAS-METRICS-REPORT.md """

NEVER dump the full report in chat. The file is the deliverable.

Key Reference Files

  • references/saas-metrics-guide.md - Detailed definitions, formulas, benchmarks, and improvement tactics for every SaaS metric
  • scripts/metrics_calculator.py - Python calculator for all metrics with traffic-light assessment. Run it directly: python3 scripts/metrics_calculator.py data.json (a JSON file using the BusinessData field names, e.g. beginning_mrr, new_mrr, customers_new, total_sales_marketing_spend, net_burn), pipe JSON via stdin, or use --demo for sample data

Guidelines

  • Always clarify whether numbers are monthly or annual before calculating
  • Use monthly figures as the base and annualize where needed (ARR = MRR x 12)
  • When churn is discussed, always distinguish between logo churn and revenue churn
  • For CAC, prefer blended CAC but note channel-specific if provided
  • LTV calculations should default to the simple method unless the user has detailed cohort data
  • Present metrics with proper formatting: percentages to one decimal, currency with appropriate scale ($K, $M)
  • Traffic-light thresholds come from references/saas-metrics-guide.md
  • Never present a single metric in isolation - always show related metrics for context (e.g., CAC with LTV and payback period)
  • When recommending improvements, prioritize by impact and feasibility

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.