Alert Manager
Sets up proactive monitoring alerts for ranking, traffic, technical, backlink, competitor, and GEO changes.
Quick Start
Set up SEO monitoring alerts for [domain]Create ranking drop alerts for my top 20 keywordsSkill Contract
Expected output: an alert configuration summary plus the standard handoff summary for memory/monitoring/.
- Reads: baselines, critical keywords/metrics to watch, normal volatility, delivery preferences, and any user-provided or tool data.
- Writes: a user-facing monitoring deliverable and reusable summary.
- Promotes: significant anomalies, durable thresholds, follow-up actions, and pending decisions to
memory/open-loops.md. - Done when: each chosen alert category has a named trigger condition, threshold, and priority; a Critical/High/Medium/Low response plan and delivery routing are defined; and thresholds are tuned to the metric's stated normal volatility.
- Primary next skill: performance-reporter when alert output needs a reporting cadence.
Handoff Summary
Emit the standard shape from skill-contract.md §Handoff Summary Format.
Data Sources
All integrations optional (see CONNECTORS.md). With tools, monitor real-time feeds from ~~SEO tool, ~~search console, and ~~web crawler. Without tools, ask for baselines, critical keywords, preferences, and historical data.
Decision Gates
Stop and ask the user when:
- No baseline or normal-volatility reference exists for the metrics to be watched — thresholds would be arbitrary. Offer: (1) supply recent baseline data, (2) use the Quick Reference defaults below and label them Estimated, (3) cancel.
Continue silently (never stop for):
- Which delivery channel to use — default to the channel already in context (or email) and note it.
- A category the user did not mention — leave it unconfigured; do not add alerts they did not request.
Instructions
When a user requests alert setup:
- Define Alert Categories — choose from rankings, traffic, technical, backlinks, competitors, GEO / AI, and brand alerts.
- Configure Alert Rules by Category — define trigger condition, threshold, alert name, and priority for each relevant rule; tie each threshold to a stated baseline and label that baseline Measured / User-provided / Estimated.
- Define Alert Response Plans — map Critical / High / Medium / Low to response time and next actions.
- Set Up Alert Delivery — configure channels, routing, cooldowns, maintenance windows, and escalation paths.
- Create Alert Summary — output category counts, the critical playbook, and a weekly review checklist as the deliverable.
Label every metric Measured (tool/export), User-provided, or Estimated (model inference); never present an estimate as measured; if a required metric is unavailable, mark it N/A — do not invent it.
Reference: See Alert Configuration Templates for the full category tables, thresholds, and response-plan templates.
Example
Sample outcome: a keyword alert matrix with Critical vs High thresholds, a response plan for drops, and notification routing to email + Slack.
Tips for Success
Start simple, tune thresholds to normal volatility, avoid alert fatigue, and review the system regularly.
Alert Threshold Quick Reference
| Metric | Warning | Critical | Frequency |
|---|---|---|---|
| Organic traffic | -15% WoW | -30% WoW | Daily |
| Keyword positions | >3 position drop | >5 position drop | Daily |
| Pages indexed | -5% change | -20% change | Weekly |
| Crawl errors | >10 new/day | >50 new/day | Daily |
| Core Web Vitals | "Needs Improvement" | "Poor" | Weekly |
| Backlinks lost | >5% in 1 week | >15% in 1 week | Weekly |
| AI citation loss | Any key query | >20% queries | Weekly |
| Security issues | Any detected | Any detected | Daily |
Reference: See Alert Threshold Guide for threshold setting, fatigue prevention, escalation paths, and response playbooks.
Save Results
Ask "Save these results?" If yes, write to memory/monitoring/ — see Skill Contract §Save Results Template.
Reference Materials
- Alert Threshold Guide — Thresholds, fatigue prevention, and escalation templates
Next Best Skill
Reporting cadence requested → performance-reporter. Standalone setup → Terminal. Visited-set rule applies per skill-contract.md.
