video1.0<iframe src="https://www.loom.com/embed/304f7487332d49ca91ab304068c76a38" frameborder="0" width="1728" height="1296" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>12961728Loomhttps://www.loom.com12961728https://cdn.loom.com/sessions/thumbnails/304f7487332d49ca91ab304068c76a38-5c4b593dea052621.gif450.357This Loom shows how to audit Meta ads campaign performance in Claude using Claude Code, skills, and MCPs. It explains that you can chat in simple language to request an analysis of how campaigns have performed since launch this month, without needing to know code, upload screenshots, or export CSVs. In the example, Claude Code runs in the Tor Agency account and returns analysis for three campaigns launched during the first half of this month, including a “flag to watch” testing variant and recommendations to lean into the primary masterclass campaign while diagnosing the direct response campaign first. For the direct response campaign, it provides four step checks, starting with confirming the conversion event is fired.