Use when the user asks to "audit our brand narrative" or "is this message on-canon"; runs separate typed TALE truth, system, or effectiveness profiles and never averages them into one composite. Checks differentiation, canon, landing consistency, and evidence integrity. Not for launch readiness — use launch-readiness-auditor; not for social operations — use social-quality-auditor.
安装
npx skills add aaron-he-zhu/aaron-marketing-skills --skill narrative-quality-auditornpx skills add aaron-he-zhu/aaron-marketing-skills --skill narrative-quality-auditor -a claude-code -gnpx skills add aaron-he-zhu/aaron-marketing-skills --skill narrative-quality-auditor -a codex -ggemini skills install https://github.com/aaron-he-zhu/aaron-marketing-skills.git --path narrative/evaluate/narrative-quality-auditorgh skill install aaron-he-zhu/aaron-marketing-skills narrative-quality-auditorgit clone --depth 1 https://github.com/aaron-he-zhu/aaron-marketing-skills /tmp/aaron-he-zhu__aaron-marketing-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/aaron-he-zhu__aaron-marketing-skills/narrative/evaluate/narrative-quality-auditor ~/.claude/skills/narrative-quality-auditor # Claude Code
cp -R /tmp/aaron-he-zhu__aaron-marketing-skills/narrative/evaluate/narrative-quality-auditor ~/.agents/skills/narrative-quality-auditor # Codex, Cursor, Gemini CLI, Copilot, OpenCode