CFO Skill

⚠️ DISCLAIMER

This skill displays data. It is NOT financial, legal, tax, accounting, or investment advice.

Numbers may be stale, miscategorized, or reflect bugs in upstream systems. Frameworks below (LTV:CAC, runway, burn multiple, Rule of 40) are heuristics, not guarantees. Decisions about hiring, fundraising, distributions, taxes, or solvency must be made by you in consultation with a qualified CFO, accountant, lawyer, or tax advisor. The author and contributors accept no liability for decisions made based on this skill's output.

Two ways to use it

Mode 1: CSV templates (works with any stack)

Drop four CSVs into a folder, run one command, get an Excel workbook. Works with any CRM/bank/billing stack, Attio, HubSpot, Salesforce, Pipedrive, Mercury, Brex, Stripe, Chargebee, Ramp, Pleo, whatever.

Templates live in templates/. Realistic example data lives in examples/ so you can try the pipeline before plugging in real data.

python skills/cfo-skill/run.py --source csv --csv-dir ./my-data --output cfo.xlsx

CSV schemas (column headers in templates/):

status values: active, churned, lead (only active counts toward MRR). direction values: in, out. Invoice status values: paid, unpaid, draft.

Mode 2: Live API pull (Attio + Qonto + Stripe + Moss)

Set credentials in your environment, run the puller, get the same Excel workbook from live data.

python skills/cfo-skill/run.py --source api --providers all --output cfo.xlsx

Or pick specific providers, they run in the order you list, and later writers win on customers.csv / invoices.csv:

python skills/cfo-skill/run.py --source api --providers qonto,stripe,moss      # Stripe-billed SaaS
python skills/cfo-skill/run.py --source api --providers qonto,attio,moss        # CRM-driven (no Stripe)
python skills/cfo-skill/run.py --source api --providers qonto,attio,stripe,moss # both, Stripe wins on MRR

Provider-by-provider:

Each puller writes its slice to a temp folder; the same compute layer then generates the Excel workbook. You don't have to use all four. A Stripe + Mercury founder can run --providers stripe and use CSV templates for the bank side. A HubSpot + Brex founder skips API mode entirely and uses CSV for everything.

Required environment variables

Only set the ones for providers you actually use.

Skill is read-only, never request write scopes. Never log or echo a secret.

What the workbook contains

Eight sheets:

1. Summary: headline metrics with heuristic flags (runway, concentration, DSO, burn multiple)
2. Cash Flow: monthly inflows / outflows / net for the trailing 3 months
3. Customers: full customer table from your input data
4. Concentration: top 1 / 5 / 10% of MRR + top-10 customer table
5. AR Aging: unpaid invoices bucketed (current, 1-30, 31-60, 61-90, 90+) + per-invoice detail
6. Spend: by category, by vendor, by department
7. Recurring Vendors: heuristic detection (3+ similar transactions)
8. Disclaimer: full disclaimer in-workbook

Computed metrics

Frameworks used (LTV:CAC, Rule of 40, Magic Number, etc.) live in references/metrics-benchmarks.md. Bootstrapped case studies in references/case-studies.md.

What this skill does NOT do

• ❌ Make recommendations on hiring, raises, distributions, or fundraising
• ❌ Give tax, legal, or accounting advice
• ❌ Project cash flow into the future as a "forecast" you can rely on
• ❌ Determine whether your company is solvent
• ❌ Write to any of the connected systems (read-only by design)

For any of these: "I can show you the numbers. The decision is for you and a qualified advisor."

How Claude should answer a CFO question

1. Restate the question in numerical terms. ("What's our runway?" → "I need cash balance and trailing 3-month net burn.")
2. Identify which provider(s) to query from the table above, or which CSV(s) to read.
3. Run run.py with appropriate flags, or read the CSVs directly via cfo.load_all() + cfo.summarize().
4. Show raw numbers first, then computed metric, then framework.
5. Repeat the disclaimer when the user is making a real decision.
6. Flag data quality issues explicitly (stale data, missing fields, miscategorized expenses).

Attribution

Frameworks, benchmarks, and case studies adapted from EveryInc/charlie-cfo-skill (MIT, © 2026 Every).

Data layer (Stripe + Attio + Qonto + Moss pullers + CSV templates + Excel writer) by 5050Growth.