Run adversarial review on a PM artifact via the pm-critic sub-agent. Returns findings graded P0/P1/P2/P3 with a concrete fix suggestion per finding and a machine-readable status block. Use after producing a PRD, meeting recap, OKR set, persona, or any PM artifact you want stress-tested before it ships.
安装
npx skills add product-on-purpose/pm-skills --skill utility-pm-criticnpx skills add product-on-purpose/pm-skills --skill utility-pm-critic -a claude-code -gnpx skills add product-on-purpose/pm-skills --skill utility-pm-critic -a codex -ggemini skills install https://github.com/product-on-purpose/pm-skills.git --path skills/utility-pm-criticgh skill install product-on-purpose/pm-skills utility-pm-criticgit clone --depth 1 https://github.com/product-on-purpose/pm-skills /tmp/product-on-purpose__pm-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/product-on-purpose__pm-skills/skills/utility-pm-critic ~/.claude/skills/utility-pm-critic # Claude Code
cp -R /tmp/product-on-purpose__pm-skills/skills/utility-pm-critic ~/.agents/skills/utility-pm-critic # Codex, Cursor, Gemini CLI, Copilot, OpenCode