creative-fatigue-detection

--- name: creative-fatigue-detection description: Monitors your ads for early signs of fatigue before performance fully collapses. Tracks frequency buildup, CTR decay, CPM increases, and engagement drops across all active creatives and tells you which ones need rotation now vs next week. Platform: Meta. metadata: platform: Meta --- # 4/ Creative Fatigue Detection — Meta ## What it does Monitors your ads for early signs of fatigue before performance fully collapses. Tracks frequency buildup, CTR decay, CPM increases, and engagement drops across all active creatives and tells you which ones need rotation now vs next week. ## How it works Claude looks at daily performance trends for each ad — CTR trajectory, frequency accumulation, cost per result movement, and engagement rate changes. It flags ads showing consistent decline over 3+ days and categorizes them as urgent (replace now), warning (1-2 weeks left), or healthy (still performing). ## Practical example You're running 14 ads across 5 ad sets on Meta. Claude flags 3 ads as urgent — they've lost 40%+ CTR over 8 days with frequency above 3.5. Four more are in warning status with CTR declining 5-10% per day. The remaining 7 are still healthy. Claude also notes that your top performer from last month has shifted from urgent to dead — it's been running 6 weeks and the audience has seen it an average of 5.8 times. ## What you get back - Each ad categorized as urgent, warning, or healthy with supporting data - Days of useful life remaining for warning-status ads - Frequency and CTR trend data for each creative - Recommended rotation schedule based on current trajectory - Which audiences have been overexposed to which creatives ## When to use it - Weekly creative health checks across all active campaigns - Before creative review meetings to prioritize what needs replacing - When CPA starts creeping up and you suspect creative is the cause - After scaling campaigns, because higher budgets burn through creatives faster ## Data access (Ryze MCP) 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: - claude.ai / Claude Desktop: Settings → Connectors → Add custom connector → `https://connector.get-ryze.ai/mcp` - Claude Code: `claude mcp add ryze --transport http https://connector.get-ryze.ai/mcp` - Cursor: Settings → MCP → add the same URL Setup guide: https://www.get-ryze.ai/how-to-connect-claude-to-google-meta-ads-mcp

1. **Gather Data**: Export Meta Ads Manager reports for the last 7-14 days, including frequency, CTR, CPM, and engagement metrics. Use the 'Breakdown by Creative' view to isolate individual assets. 2. **Configure Thresholds**: Adjust the frequency, CTR decay, CPM increase, and engagement thresholds in the prompt based on your campaign goals (e.g., higher thresholds for brand awareness vs. lower for performance). 3. **Run Analysis**: Paste the prompt into your AI tool (e.g., Claude, ChatGPT) and input the campaign name, timeframe, and topic/audience insights. Cross-check the AI's recommendations against your creative library to avoid duplicates. 4. **Prioritize and Act**: Sort flagged creatives by expected impact (e.g., highest volume or steepest decline first). Use Meta's 'Duplicate Ad' feature to quickly generate new variations, then pause the old ones. 5. **Monitor and Iterate**: After 3-5 days, re-run the analysis to confirm fatigue is resolved. Track ROAS recovery in Meta Ads Manager to validate the AI's suggestions. **Tip**: For better results, include audience insights (e.g., 'targeting new customers in the 25-45 age group') to tailor creative suggestions. Use Meta's 'Audience Insights' tool to identify underperforming segments.