agentleFS
me-workspaceme-workspace/orchestrator-operational-agent-skills/finance-analyst/SKILL.md

finance-analyst

Skill1 starsChanged 45 days agoMITView on GitHub

Use this skill for any finance/accounting work - "laporan keuangan", "cashflow", "runway", "harga/pricing", "unit economics", "MRR/ARR/churn", budgeting, invoice/AR review, forecasting, or evaluating whether a business/product is profitable. Covers SaaS metrics, cashflow analysis, and pricing models. Do NOT use for tax filing advice or audited financial statements - flag those for a licensed accountant.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never mix currencies silently.

    line 11
  2. Distinctive:

    Use consistent period buckets (calendar month) before comparing.

    line 12

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Finance Analyst

Numbers first, narrative second. Every claim must trace to a source figure; state assumptions explicitly and separately from data.

Ground rules

  • Never mix currencies silently; state currency and period on every figure.
  • Use consistent period buckets (calendar month) before comparing.
  • Distinguish cash (money moved) vs accrual (earned/owed) - say which basis you're on.
  • Round in presentation only, never mid-calculation. Money math: integers in smallest unit or decimal type, never float.

SaaS / subscription metrics (definitions to use verbatim)

  • MRR = sum of active subscriptions' monthly-normalized price. New / expansion / contraction / churned MRR reported separately.
  • Churn (logo) = customers lost ÷ customers at period start. Revenue churn uses MRR. Report both.
  • ARPU = MRR ÷ active customers. LTV ≈ ARPU × gross margin ÷ monthly revenue churn (state this is an approximation).
  • CAC = full sales+marketing spend ÷ new customers. Healthy: LTV/CAC ≥ 3, CAC payback ≤ 12 months.
  • Runway = cash ÷ average monthly net burn (last 3 months, not best month).

Standard deliverable - monthly finance snapshot

# Snapshot <bulan>
Kas akhir: X | Net burn: X | Runway: X bulan
MRR: X (new +a, expansion +b, contraction -c, churn -d) | Growth MoM: x%
Pelanggan aktif: N | Logo churn: x% | ARPU: X
Top 3 pengeluaran: ...
Perhatian: <anomali, pelanggan telat bayar, biaya naik tak wajar>
Asumsi & sumber data: ...

Pricing / unit economics analysis

  1. Compute true unit cost: infra + payment fees + support time + COGS per unit/customer.
  2. Contribution margin per tier; flag any tier with margin < 50% for a software product.
  3. Price recommendation: anchor to value delivered and competitor range, not cost-plus alone. Give 2-3 scenarios with break-even volume each.

Red flags to always surface

Negative gross margin customers · churn trending up 2+ months · one customer > 25% of revenue · AR older than 60 days · spend category growing faster than revenue · runway < 6 months.

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.