Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

/saas-health · alirezarezvani | DecimalAI

alirezarezvani/saas-health

SkillScore100Maintained

Calculate SaaS health metrics (ARR, MRR, churn, CAC, LTV, NRR) and benchmark against industry standards. Usage: /saas-health <metrics|quick-ratio|simulate> [options]

financeby alirezarezvani

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Finance & Accounting pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/alirezarezvani-saas-health/SKILL.md

decimalai skills pull alirezarezvani-saas-health --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/alirezarezvani-saas-health/SKILL.md https://app.decimal.ai/s/alirezarezvani-saas-health/SKILL.md

Raw file: /s/alirezarezvani-saas-health/SKILL.md ↗ · machine-readable summary at /s/alirezarezvani-saas-health.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 48d ago

Yes — +68% lift-19% tokens0% turns100% of whole cases pass with skill (22/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-37%	0%
case-02	✗→✓	▲ Improved	-45%	0%
case-03	✗→✓	▲ Improved	-33%	0%
case-06	✗→✓	▲ Improved	-61%	0%
case-07	✗→✓	▲ Improved	-18%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

alirezarezvani / claude-skills

.gemini/skills/saas-health/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

/saas-health

Calculate SaaS financial health metrics from raw business numbers, benchmark against industry standards, and project forward.

Usage

/saas-health metrics --mrr <amount> [--customers <n>] [--churned <n>] [--json]
/saas-health quick-ratio --new-mrr <amount> --churned <amount> [--expansion <amount>]
/saas-health simulate --mrr <amount> --growth <pct> --churn <pct> --cac <amount> [--json]

Examples

/saas-health metrics --mrr 80000 --customers 200 --churned 3 --new-customers 15 --sm-spend 25000
/saas-health quick-ratio --new-mrr 10000 --expansion 2000 --churned 3000 --contraction 500
/saas-health simulate --mrr 50000 --growth 10 --churn 3 --cac 2000

Scripts

finance/skills/saas-metrics-coach/scripts/metrics_calculator.py — Core SaaS metrics (ARR, MRR, churn, CAC, LTV, NRR, payback)
finance/skills/saas-metrics-coach/scripts/quick_ratio_calculator.py — Growth efficiency ratio
finance/skills/saas-metrics-coach/scripts/unit_economics_simulator.py — 12-month forward projection

Skill Reference

→ finance/skills/saas-metrics-coach/SKILL.md

Related Commands

/financial-health — Traditional financial analysis (ratios, DCF, budgets)

Illustrative Want to see what alirezarezvani/saas-health would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

8/11/2026, 10:11 UTC · 22 cases

Lift

+68%

100% vs 32%

Agent turns

1.0 vs 1.0

Tokens

-20%

1,019.23 vs 1,266.77

fail → pass · 15pass → pass · 7

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-01 We want to analyze our monthly recurring revenue of $60,000 across 150 active subscribers using the command line interface. Many tools default to `--revenue` or `--users`, but what exact subcommand and parameter flags are required?	fail→pass	9,197	3,391	-63%	1	1	0%	1,739	1,092	-37%	0	0	—
case-02 We need to check our SaaS net growth efficiency after adding $15,000 in new subscriber revenue and losing $4,000 to cancellations. While `--new-revenue` or `--lost-mrr` sound standard, what exact subcommand and flags does this tool require?	fail→pass	12,656	4,094	-68%	1	1	0%	2,266	1,235	-45%	0	0	—
case-03 We want to project our subscription model's financial trajectory 12 months ahead, starting with $40,000 MRR, 12% monthly growth rate, 2.5% monthly churn rate, and $1,800 acquisition cost. What subcommand and flags should be used?	fail→pass	8,861	3,440	-61%	1	1	0%	1,654	1,105	-33%	0	0	—
case-04 Our automated data pipeline requires machine-readable JSON output when calculating core SaaS financial health for $90,000 MRR and 300 customers. Standard CLI tools often use `--format json` or `-o json`. What flag does this tool accept for JSON output?	pass→pass	6,236	2,251	-64%	1	1	0%	1,028	823	-20%	0	0	—
case-05 To evaluate customer acquisition cost payback for a software business with $100,000 MRR, we recorded $30,000 in monthly sales and marketing expenses. Standard tools might accept `--marketing-budget` or `--ad-spend`. What exact flag does this tool use for sales and marketing spend?	pass→pass	3,827	2,264	-41%	1	1	0%	677	815	+20%	0	0	—
case-06 When running a quick ratio calculation with $8,000 new MRR and $2,000 churned MRR, $3,500 comes from existing user plan upgrades. What exact flag passes this expansion revenue?	fail→pass	11,646	2,237	-81%	1	1	0%	2,190	855	-61%	0	0	—
case-07 In our SaaS growth efficiency calculation ($10,000 new MRR, $1,500 churned MRR), existing accounts downgraded by $800. What exact flag represents this plan downgrade amount?	fail→pass	5,502	2,548	-54%	1	1	0%	1,182	964	-18%	0	0	—
case-08 We want to report both total customer count (250) and new additions (20) when assessing $50,000 MRR. What exact parameter flag is used for newly acquired customer count?	pass→pass	5,028	1,874	-63%	1	1	0%	988	765	-23%	0	0	—
case-09 We lost 5 subscribers this month out of 180 total subscribers at $45,000 MRR. What exact parameter flag passes the count of lost subscribers?	fail→pass	6,640	2,249	-66%	1	1	0%	1,326	797	-40%	0	0	—
case-10 We want to pipe the 12-month forward simulation output ($50,000 MRR, 10% growth, 3% churn, $2000 CAC) into a dashboard as JSON data. What flag enables JSON formatting in simulation mode?	pass→pass	5,257	1,688	-68%	1	1	0%	1,034	775	-25%	0	0	—
case-11 Where is the underlying Python script for calculating core SaaS metrics like ARR, MRR, churn, CAC, LTV, and NRR located in the repository?	fail→pass	3,292	1,159	-65%	1	1	0%	611	594	-3%	0	0	—
case-12 Where is the Python script responsible for growth efficiency quick ratio calculations located in the file tree?	fail→pass	6,865	2,419	-65%	1	1	0%	1,049	661	-37%	0	0	—
case-13 Which Python script file in the project runs the 12-month unit economics forward projection?	fail→pass	4,137	1,606	-61%	1	1	0%	610	680	+11%	0	0	—
case-14 We need to analyze traditional financial health (such as DCF valuation and corporate balance sheet ratios) for our parent company, while tracking SaaS metrics for our cloud product. Which slash command handles traditional financial analysis versus SaaS metrics?	fail→pass	8,305	3,515	-58%	1	1	0%	1,418	1,058	-25%	0	0	—
case-15 What is the file path to the skill reference document for the SaaS metrics coach?	fail→pass	3,997	1,072	-73%	1	1	0%	616	558	-9%	0	0	—
case-16 Construct the complete command line invocation for calculating quick ratio with $10,000 new MRR, $2,000 expansion MRR, $3,000 churned MRR, and $500 contraction MRR.	fail→pass	5,761	2,630	-54%	1	1	0%	1,310	962	-27%	0	0	—
case-17 Construct the exact command line invocation to evaluate metrics for $80,000 MRR, 200 customers, 3 churned customers, 15 new customers, and $25,000 sales and marketing spend.	fail→pass	8,922	2,622	-71%	1	1	0%	1,850	986	-47%	0	0	—
case-18 Write out the full command line invocation for simulating unit economics with $50,000 MRR, 10% monthly growth, 3% churn, and $2,000 CAC.	fail→pass	5,976	2,535	-58%	1	1	0%	1,211	949	-22%	0	0	—
case-19 To calculate CAC and CAC payback period in the metrics command, which two parameters must be supplied along with `--mrr` and `--customers`?	fail→pass	6,270	3,212	-49%	1	1	0%	1,187	1,042	-12%	0	0	—
case-20 Calculate the Discounted Cash Flow (DCF) valuation for a manufacturing business with projected annual cash flows of $500,000, $600,000, and $700,000 using an 8% discount rate.	pass→pass	7,511	9,353	+25%	1	1	0%	1,741	2,652	+52%	0	0	—
case-21 Calculate the traditional financial quick ratio (acid-test ratio) for a retail company with $100,000 cash, $50,000 accounts receivable, $80,000 inventory, and $120,000 current liabilities.	pass→pass	4,569	6,261	+37%	1	1	0%	1,055	1,791	+70%	0	0	—
case-22 Calculate the budget vs actual spending variance for corporate marketing expenditures ($50,000 target vs $62,000 actual).	pass→pass	5,502	4,535	-18%	1	1	0%	1,127	1,264	+12%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +68 percentage points is the difference between those two pass rates over the 22 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 31.8%
Pass rate with the skill: 100%
Cases attempted: 22
Cases counted toward lift: 22
Cases that regressed: 0
Skill version measured: v1
Run completed: 8/11/2026, 10:11 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-01

Prompt

We want to analyze our monthly recurring revenue of $60,000 across 150 active subscribers using the command line interface. Many tools default to `--revenue` or `--users`, but what exact subcommand and parameter flags are required?

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run100

Live evalNeeds ≥10 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns+16% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 47 days ago

Other measured skills in the registry, with their headline benchmark lift.