Before showing the user any substantive GTM deliverable (positioning, value prop, homepage, launch post, pricing, sales script, the brief, the market research, or the roadmap), stress-test it against the standard as an independent critic, because the agent that wrote it is the worst judge of whether it is good.
安装
npx skills add AIDevGTM/gtm-cofounder --skill review-the-worknpx skills add AIDevGTM/gtm-cofounder --skill review-the-work -a claude-code -gnpx skills add AIDevGTM/gtm-cofounder --skill review-the-work -a codex -ggemini skills install https://github.com/AIDevGTM/gtm-cofounder.git --path skills/17-review-the-workgh skill install AIDevGTM/gtm-cofounder review-the-workgit clone --depth 1 https://github.com/AIDevGTM/gtm-cofounder /tmp/AIDevGTM__gtm-cofounder
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/AIDevGTM__gtm-cofounder/skills/17-review-the-work ~/.claude/skills/review-the-work # Claude Code
cp -R /tmp/AIDevGTM__gtm-cofounder/skills/17-review-the-work ~/.agents/skills/review-the-work # Codex, Cursor, Gemini CLI, Copilot, OpenCode