Cmo review

Skill sinhoneyy/master-skills/skills/cmo-review

/cs:cmo-review <plan> — Narrative-first interrogation of positioning, ICP, message house, and channel mix. Use when launching a campaign or repositioning, or when CAC is rising and the one-sentence positioning test fails.From its SKILL.md

Install

npx -y skills add sinhoneyy/master-skills --skill cmo-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

3.1 KB, 783 tokens by cl100k_base, as published. Nobody here has run it

/cs:cmo-review — CMO Forcing Questions

Command: /cs:cmo-review <plan>

The narrative-first strategist pressure-tests positioning before debating tactics.

When to Run

Before launching any new campaign
Before changing positioning, tagline, or category
Before allocating > 10% of marketing budget to a new channel
Before a major PR moment (funding announcement, product launch)
When pipeline contribution is declining

The Six CMO Questions

1. ICP (One Real Person)

Name one real person in your ICP. Company, title, what they do daily, what they hate.

Persona ≠ ICP. ICP is real.
If you can't name one, the ICP isn't sharp enough.

2. JTBD

What job is the customer hiring this product to do, and what's the alternative they use today?

One sentence the customer would say out loud.
"We use spreadsheets" is a valid alternative. So is "we don't."

3. Positioning Statement

One sentence: For [ICP], who needs [job], we are [category] that [differentiator] unlike [alternative].

This is the headline. Everything cascades.
If it doesn't fit in one sentence, it's not positioning yet.

4. Distribution Channel

Where does the customer first hear your name — and is it inbound or outbound at this stage?

Name the channel, intent, and the path to first contact.
PLG, sales-led, content-led, partnership-led — pick a primary.

5. CAC Payback

Per channel: what's CAC, what's payback in months, and is it improving?

If a channel's payback is > 18 months, it isn't a channel — it's a hobby.

6. Defensibility of Brand

If a well-funded competitor copies your messaging tomorrow, what's still yours?

Category position, founder-market fit, customer love, distribution lock — name one.

Workflow

Run the models:

python ../../../skills/cmo-advisor/scripts/marketing_budget_modeler.py
python ../../../skills/cmo-advisor/scripts/growth_model_simulator.py

Answer the six questions in writing.
Apply the verdict:
- 🟢 GREEN — story is sharp, channel mix sound
- 🟡 YELLOW — sharpen positioning before scaling
- 🔴 RED — positioning broken; do not spend

Output Format

# CMO Review: <plan>
**Date:** YYYY-MM-DD

## Positioning
One-sentence statement: <here>

## ICP
- Named persona: <name, title, company>
- JTBD: <one sentence in their words>

## Channel Mix
- Primary: <channel> | CAC $X | Payback Ym
- Secondary: <channel> | CAC $X | Payback Ym

## Verdict
🟢 / 🟡 / 🔴

## Next Steps
[3 concrete actions]

Routing

/cs:cro-review — pipeline contribution check
/cs:cpo-review — product ↔ positioning alignment
/cs:decide — log the verdict

Agent: cs-cmo-advisor
Skill: cmo-advisor
Execution domain: ../../../../marketing-skill/

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 783 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.