Compute a business's CAC and ROAS family metrics from real spend and outcome data, then judge whether the spend is healthy against three references - the business's own break-even, its own trailing history, and provenance-labelled external benchmarks - returning healthy, watch, unhealthy, or insufficient evidence.
Install
npx skills add mbfinotti/advertising-skills --skill cac-roas-benchmarknpx skills add mbfinotti/advertising-skills --skill cac-roas-benchmark -a claude-code -gnpx skills add mbfinotti/advertising-skills --skill cac-roas-benchmark -a codex -ggemini skills install https://github.com/mbfinotti/advertising-skills.git --path skills/cac-roas-benchmarkgh skill install mbfinotti/advertising-skills cac-roas-benchmarkgit clone --depth 1 https://github.com/mbfinotti/advertising-skills /tmp/mbfinotti__advertising-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/mbfinotti__advertising-skills/skills/cac-roas-benchmark ~/.claude/skills/cac-roas-benchmark # Claude Code
cp -R /tmp/mbfinotti__advertising-skills/skills/cac-roas-benchmark ~/.agents/skills/cac-roas-benchmark # Codex, Cursor, Gemini CLI, Copilot, OpenCode