
CPO Review Forcing Questions
Pressure-tests a product roadmap or feature with six product-leader questions before you commit to building it
- Repository
- alirezarezvani/claude-skills
- Stars
- 29,149
- Licence
- MIT
- Files
- 1 file
What it does
When you ask the agent to review a plan, it works through six questions a chief product officer would ask: what job the feature is hired to do, how it ties to the company's North Star metric, whether retention shows product-market fit, its RICE priority score, what gets cut to make room, and what result in 90 days would mean it was a mistake. It then produces a structured report with a SHIP, SHARPEN, or KILL verdict. The skill refers to helper scripts for scoring, but the SKILL.md itself only contains the prompts and report template.
Great for
- Product managers preparing a quarterly roadmap or deciding whether to kill a feature
- Founders or small teams debating whether to build something new
- Leaders who want a structured challenge to a product plan before committing resources
Skip it if
- Teams without real retention or usage data, since the PMF question depends on a retention curve and the skill cannot produce one (the agent may guess or overstate confidence)
- Anyone expecting a substitute for real market research or executive judgement, since the output is only as good as the inputs provided
Try asking
- “/c-level-agents:cpo-review Plan to add team invitations, bulk import and SSO to the Q3 release”
- “Should we kill the legacy reporting feature? Run a CPO review on it”
- “Review our quarterly roadmap and tell me what to cut”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the MIT licence and an attribution note.
cpo-review.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip cpo-review.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip cpo-review.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Provide concrete data such as retention cohorts, usage numbers and the current feature list so the answers are grounded rather than invented.
- Read the referenced Python scripts before running them, since the skill instructs the agent to execute them.
- Treat the verdict as a structured prompt for discussion, not a final decision.
What's inside
- SKILL.md
Redistributed unmodified from alirezarezvani/claude-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.