Compares your Meta ad sets and identifies where audiences overlap significantly, causing your ads to compete against each other in the same auctions. Tells you exactly which ad sets are cannibalizing each other and how much it's costing you in inflated CPMs. Platform: Meta.
npx skills add https://github.com/irinabuht12-oss/marketing-skills --skill audience-overlap-analysis
Compares your Meta ad sets and identifies where audiences overlap significantly, causing your ads to compete against each other in the same auctions. Tells you exactly which ad sets are cannibalizing each other and how much it's costing you in inflated CPMs.
Claude analyzes your ad set targeting parameters — custom audiences, lookalikes, interest stacks, age/gender splits, and geo targeting — and maps the overlap between them. It cross-references this with delivery data to identify where auction overlap is actually driving up costs vs where it's theoretical but not impactful.
You're running 6 prospecting ad sets on Meta, each targeting different interest stacks. Claude identifies that ad sets 2, 4, and 6 have an estimated 60%+ audience overlap because the interest categories share the same underlying user pool. These three ad sets have CPMs 28% higher than the non-overlapping ones. Recommendation: consolidate into one ad set with broader targeting and let Meta's algorithm optimize, or use audience exclusions to create clean segments.
This skill works best with live account data. Connect the free Ryze MCP once and Claude reads your Google Ads, Meta Ads, GA4 and Search Console directly:
https://connector.get-ryze.ai/mcpclaude mcp add ryze --transport http https://connector.get-ryze.ai/mcpSetup guide: https://www.get-ryze.ai/how-to-connect-claude-to-google-meta-ads-mcp
Take irinabuht12-oss/audience-overlap-analysis from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.