anomaly-detection
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
Install
npx skills add https://github.com/irinabuht12-oss/marketing-skills/tree/main/skills/anomaly-detection
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install irinabuht12-oss-marketing-skills@llmmart
git clone https://github.com/irinabuht12-oss/marketing-skills.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole irinabuht12-oss/marketing-skills collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
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
Files (marketing-skills)
-
SKILL.md 2.6 KB
--- 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
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.