anomaly-detection

--- name: anomaly-detection description: Catches unusual performance changes across your accounts — CPC spikes, CVR drops, spend surges, impression collapses, CTR shifts — and flags them with context about what likely changed. The goal is to catch problems in hours instead of discovering them days later during a routine check. Platform: Google and Meta. metadata: platform: Google and Meta --- # 6/ Anomaly Detection — Google + Meta ## What it does Catches unusual performance changes across your accounts — CPC spikes, CVR drops, spend surges, impression collapses, CTR shifts — and flags them with context about what likely changed. The goal is to catch problems in hours instead of discovering them days later during a routine check. ## How it works Claude compares current performance against your recent baseline (typically 7-14 day rolling average) and flags any metric that moves beyond a threshold you set. It then cross-references the anomaly against common causes — budget changes, auction shifts, ad disapprovals, audience exhaustion, landing page issues, or external events. ## Practical example Thursday at 2pm, your branded search CPC jumps 47% compared to the 14-day average. Claude flags it and identifies that a competitor started bidding on your brand terms (impression share dropped from 94% to 71% simultaneously). It also catches that a Meta campaign's CVR dropped 60% — the landing page started returning 404 errors after a site deployment at 1:30pm. ## What you get back - List of anomalies ranked by financial impact (estimated wasted or lost spend) - Each anomaly paired with the most likely cause based on correlated data shifts - Recommended immediate actions for each issue - Severity rating so you know what to fix now vs what can wait - Baseline comparison data so you can see exactly how far off normal the metric is ## When to use it - Daily monitoring across all active accounts - After website deployments or landing page changes - During high-spend periods like Black Friday or product launches - When managing multiple accounts and you can't manually check everything daily ## 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

[{"step":"Gather your data. Export performance reports from [PLATFORM: Google Ads/Meta Ads Manager] for the [DATE_RANGE] you want to analyze. Include metrics like CPC, CVR, spend, impressions, and CTR. Save the data as a CSV or connect your account via API if your tool supports it.","tip":"Use Google Data Studio or Meta Ads Manager's built-in reporting to pull the last 7 days of data. Ensure your time zone settings match to avoid discrepancies in anomaly timing."},{"step":"Customize the prompt. Replace [ACCOUNT_NAME], [DATE_RANGE], [PLATFORMS], [METRICS], and [THRESHOLD] with your specific details. Adjust the [TIME_WINDOW] if you want to focus on a shorter or longer period.","tip":"For Meta Ads, include both Instagram and Facebook placements in your data export. For Google Ads, ensure you’re pulling data for Search, Display, and Video campaigns separately if you want granular insights."},{"step":"Run the analysis. Paste the customized prompt into your AI tool (e.g., ChatGPT, Claude) and generate the report. If using an API-connected tool, upload your data file and run the analysis directly.","tip":"For large accounts, break the analysis into smaller chunks (e.g., by campaign type or platform) to avoid overwhelming the AI with too much data at once."},{"step":"Review and act. Use the AI-generated report to prioritize anomalies based on their potential revenue impact. Implement the recommended actions and monitor the changes in real-time.","tip":"Set up alerts in your ad platform (e.g., Google Ads' 'Change History' alerts or Meta's 'Anomaly Detection' alerts) to catch similar issues automatically in the future."},{"step":"Document and iterate. Save the report for your records and note which anomalies were resolved successfully. Use this data to refine your thresholds or improve your anomaly detection strategy over time.","tip":"Track false positives (e.g., anomalies that weren’t actionable) to adjust your [THRESHOLD] or [TIME_WINDOW] in future analyses."}]