agentsclimarketplace
Sign in

Cfo review

Skill sinhoneyy/master-skills/plugins/master-skills-backend-engineer/skills/cfo-review

/cs:cfo-review <plan> — Numerate-skeptic interrogation of any plan that touches money. Unit economics, runway, dilution, capital allocation. Use when a plan commits meaningful spend — e.g. a hiring wave, a fundraise decision, or a new channel budget.From its SKILL.md

Install
npx -y skills add sinhoneyy/master-skills --skill cfo-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 10 stars10 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.2 KB, 799 tokens by cl100k_base, as published. Nobody here has run it

/cs:cfo-review — CFO Forcing Questions

Command: /cs:cfo-review <plan>

The numerate skeptic stress-tests anything that touches money. Six questions before any spend or fundraise.

When to Run

  • Before approving any spend > 1% of revenue
  • Before opening a new hiring requisition
  • Before any fundraise conversation
  • Before changing pricing or unit economics
  • Before signing a multi-year contract

The Six CFO Questions

1. Burn & Runway

What's the burn multiple and how many months of cash remain at base / bull / bear?

  • Burn multiple = Net burn ÷ Net new ARR. Above 2x is a problem.
  • If bear case < 12 months, you're already in fundraising mode.

2. Unit Economics

What is LTV / CAC per channel, and what's the payback period on the top-2 channels?

  • LTV / CAC > 3x is healthy. Payback < 12 months is healthy.
  • If either is broken, do not scale that channel.

3. Dilution Path

If this plan requires a raise, what's the dilution at base and bear valuations?

  • Founder dilution per round.
  • Cumulative dilution to next 2 rounds.

4. Capital Allocation Alternative

If this dollar wasn't spent here, where else could it go and what's the expected return?

  • Three alternatives: hiring, product, marketing.
  • Make the opportunity cost explicit.

5. Revenue Quality

What's the gross margin, and how does it trend at scale?

  • If margin compresses with scale, the model is broken.
  • Cost-of-revenue should grow slower than revenue.

6. Bear Case Survival

If revenue is 50% of plan, does the company survive 18 months?

  • Default-alive is non-negotiable.
  • If not, identify the cut triggers in advance.

Workflow

  1. Run the numbers: 
    python ../../../skills/cfo-advisor/scripts/burn_rate_calculator.py
python ../../../skills/cfo-advisor/scripts/unit_economics_analyzer.py
python ../../../skills/cfo-advisor/scripts/fundraising_model.py
  2. Answer all six questions with numbers, not adjectives.
  3. Apply the verdict:
    • 🟢 GREEN — fund it
    • 🟡 YELLOW — fund with cut triggers
    • 🔴 RED — kill or revise

Output Format

# CFO Review: <plan>
**Date:** YYYY-MM-DD
**Reviewer:** cs-cfo-advisor

## Numbers
- Burn multiple: X.Xx
- Runway (base/bull/bear): X / X / X months
- LTV/CAC top channel: X.Xx, payback Y months
- Gross margin: X% (trend: Y)
- Dilution this round: X%
- Bear-case survival: PASS / FAIL

## Verdict
🟢 GREEN | 🟡 YELLOW | 🔴 RED

## Conditions (if YELLOW)
- Cut trigger: <metric> < <threshold> → <action>
- Review checkpoint: <date>

## Recommendation
[3 concrete next steps]

Routing

  • /cs:decide — log the verdict
  • /cs:execute — build 90-day plan if GREEN
  • /cs:boardroom — escalate if multi-role implications

Related

Version: 1.0.0

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most review quality skills give in 799 tokens

Counted across 1,048 of the 1,783 authors here whose files we hold, read 2026-08-07

  • Ask questions one at a timein 81 of 1048, across 64 files
  • Provide a recommended answer for each questionin 73 of 1048, across 50 files
  • Explore the codebase instead of asking answerable questionsin 66 of 1048, across 42 files
  • Resolve dependencies between decisions one-by-onein 42 of 1048, across 17 files
  • Interview the user relentlessly about the planin 38 of 1048, across 13 files
  • Order findings by severityin 31 of 1048
  • Resolve each branch of the decision treein 27 of 1048, across 5 files
  • Run a grilling sessionin 26 of 1048, across 5 files
  • Update CONTEXT.md immediately when a term is resolvedin 26 of 1048, across 11 files
  • Propose precise canonical terms for vague languagein 25 of 1048, across 7 files
  • Create documentation files lazilyin 24 of 1048, across 5 files
  • Assign severity to every findingin 24 of 1048

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,696. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.