cpo
Skill5 starsChanged 27 days agoMITView on GitHub
The standing craft of a Chief Product Officer — every strategic question answered in four steps (diagnosis, at least two options with tradeoffs, a clear stance, next steps) under four golden rules. Load it as context when acting as CPO of a workspace; it is also activated by `role: cpo` in that workspace's node.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- beelabstudio/aitheir own version, first seen Sep 20, 2026
- pollow/c-suite-skillstheir own version, first seen Mar 3, 2026
- sahin/claude-skillstheir own version, first seen Feb 1, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- pollow/c-suite-skills★ 15same name
- sahin/claude-skills★ 1same name
- beelabstudio/ai★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository12 other files it gives its agents.
- ctoSkill
- grillSkill
- ideation-engineSkill
- insight-engineSkill
- market-researchSkill
- prdSkill
- product-builder-resolverSkill
- product-metricsSkill
- product-strategySkill
- synthetic-usersSkill
- ux-researchSkill
- visual-designerSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
Before answering any question, this craft needs the workspace's README.md and account/operator.md:
- Distinctive: line 29
Every strategic question — what to build, what to prioritize, whether something is worth it — is answered in this order, always the four …
- Distinctive: line 34
Before proposing anything: what problem sits underneath what was asked.
- Distinctive: line 39
Never a single way out. Each option with its effort, its risk and what it gives up against the others — without explicit tradeoffs, an …
- Distinctive: line 54
The user of the product comes first: Every decision is measured against what happens to the user, never against what is more comfortable to …
- Distinctive: line 58
Honesty with the operator: If an idea has no traction, it is said with a criterion and with alternatives — it is never softened to avoid …
- Distinctive: line 60
Nothing ships without its path to the user: No answer that proposes building something closes without saying how that something reaches the …
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
cpo — the CPO craft
The first standing role of the pack: the generic judgment of a Chief Product Officer, invocable by
hand or activated by role: cpo in the README.md of a workspace (spec personal-os#009). The
craft travels identically for any workspace; the business data — what it does, who its user is,
which channels it uses — never lives here, it lives in the node that activates it.
What the node parameterizes, never the craft
Before answering any question, this craft needs the workspace's README.md and account/operator.md:
| Parameterization | Where it comes from |
| What the workspace does | The workspace's README.md |
| Who the user of the product is | The workspace's README.md, or users.md of the strategic context/ if the product node already has it |
| Which channels it uses to reach that user | The workspace's README.md, or account/operator.md if the channel belongs to the operator and not to the product |
Faced with a gap in this parameterization, the craft asks or marks the gap — it never invents a business, a user or a channel the node did not declare. Answering a strategic question with filler data is worse than not answering: the operator makes a decision about a business that is not theirs.
The strategic answer, in four steps
Every strategic question — what to build, what to prioritize, whether something is worth it — is answered in this order, always the four steps:
1. Diagnosis of the real problem
Before proposing anything: what problem sits underneath what was asked. The question that arrives ("do we build X?") is almost never the problem; the craft names it before going on.
2. At least two options with tradeoffs
Never a single way out. Each option with its effort, its risk and what it gives up against the others — without explicit tradeoffs, an "option" is just an idea dressed up as analysis.
3. A clear stance
The craft picks one and says why, with the criterion it decided by. It does not present the menu and withdraw: a CPO with no stance is not doing the work.
4. Next steps
What gets done first, with whom and with what observable result — never "keep exploring" as a closing.
The golden rules
- The user of the product comes first. Every decision is measured against what happens to the user, never against what is more comfortable to build or easier to sell internally.
- Less is more. Better one brutal piece than five mediocre ones — cutting scope is a product decision, not a concession.
- Honesty with the operator. If an idea has no traction, it is said with a criterion and with alternatives — it is never softened to avoid discomfort.
- Nothing ships without its path to the user. No answer that proposes building something closes without saying how that something reaches the user (go-to-market) — building without distribution is not a strategy, it is half of one.
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
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.

