
Alert Manager
- 4.7k installs
- 115 repo stars
- Updated July 13, 2026
- aaron-he-zhu/seo-geo-claude-skills
alert-manager configures threshold notifications for future SEO ranking, traffic, technical, backlink, competitor, and GEO visibility changes.
About
alert-manager (v9.9.10) is a Claude Code SEO skill that sets up proactive monitoring alerts for ranking, traffic, technical, backlink, competitor, and GEO or AI visibility changes. Invoke it when users ask to set SEO alerts, traffic alerts, competitor alerts, watch keywords, or receive notifications such as 排名掉了提醒我. It is not for one-time measurement or reporting; defer those to rank-tracker or performance-reporter. The skill contract reads baselines, critical keywords, normal volatility, and delivery preferences, then writes an alert configuration summary plus a handoff for memory/monitoring/. Workflows choose alert categories, define per-category trigger conditions and thresholds labeled Measured, User-provided, or Estimated, map Critical through Low response plans, and configure delivery routing with cooldowns and escalation paths. Decision gates stop when no baseline exists, offering supplied data, Quick Reference defaults labeled Estimated, or cancel. Quick Reference tables document organic traffic drops, keyword position drops, crawl errors, Core Web Vitals, backlink loss, AI citation loss, and security issue thresholds. Done when each category has named triggers, tuned thre.
- Configures proactive alerts for rankings, traffic, technical issues, backlinks, competitors, GEO, and brand changes.
- Explicitly not for one-time measurement; rank-tracker and performance-reporter handle tracking and reporting.
- Labels every metric baseline Measured, User-provided, or Estimated and never presents estimates as measured.
- Quick Reference thresholds cover traffic WoW drops, keyword position drops, crawl errors, CWV, and AI citation loss.
- Outputs alert configuration summary plus memory/monitoring/ handoff with Critical through Low response plans.
Alert Manager by the numbers
- 4,735 all-time installs (skills.sh)
- +5 installs in the week ending Jul 28, 2026 (Skillselion tracking)
- Ranked #148 of 1,881 Marketing & SEO skills by installs in the Skillselion catalog
- Security screen: MEDIUM risk (skills.sh audit)
- Data as of Jul 28, 2026 (Skillselion catalog sync)
alert-manager capabilities & compatibility
- Capabilities
- define alert categories for rankings, traffic, t · configure trigger conditions and thresholds tied · map critical, high, medium, and low response pla · set delivery channels, cooldowns, and escalation · apply quick reference defaults for common seo me · write monitoring handoff summaries to memory/mon
- Use cases
- seo · marketing · orchestration
- Runs
- Runs locally
- Pricing
- Free
What alert-manager says it does
Sets up proactive monitoring alerts for ranking, traffic, technical, backlink, competitor, and GEO changes.
npx skills add https://github.com/aaron-he-zhu/seo-geo-claude-skills --skill alert-managerAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 4.7k |
|---|---|
| repo stars | ★ 115 |
| Security audit | 2 / 3 scanners passed |
| Last updated | July 13, 2026 |
| Repository | aaron-he-zhu/seo-geo-claude-skills ↗ |
What it does
Configure threshold alerts for future SEO ranking, traffic, technical, backlink, competitor, and GEO visibility changes.
Who is it for?
Setting up ranking drop alerts, traffic anomaly notifications, competitor watch rules, and GEO citation loss monitoring with tuned baselines.
Skip if: One-time SEO measurement, raw rank tracking snapshots, or executive performance reports; use rank-tracker or performance-reporter instead.
When should I use this skill?
User asks to set SEO alerts, traffic alerts, competitor alerts, alert me if rankings drop, watch keywords, or 排名掉了提醒我.
What you get
A named alert matrix with tuned thresholds, priority levels, response playbooks, delivery routing, and a reusable memory/monitoring/ summary.
- Alert threshold configuration table
- SEO response plan templates
By the numbers
- Skill version 9.9.10 documented in frontmatter.
- Quick Reference table defines eight metric types with Warning and Critical thresholds.
Files
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:
1. Define Alert Categories — choose from rankings, traffic, technical, backlinks, competitors, GEO / AI, and brand alerts. 2. 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. 3. Define Alert Response Plans — map Critical / High / Medium / Low to response time and next actions. 4. Set Up Alert Delivery — configure channels, routing, cooldowns, maintenance windows, and escalation paths. 5. 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.
Alert Configuration Templates
Compact alert thresholds and response plans for SEO/GEO monitoring.
1. Alert Thresholds
| Area | Alert | Condition | Priority |
|---|---|---|---|
| Rankings | Critical drop | Top 3 keyword drops 5+ positions | Critical |
| Rankings | Top 10 loss | Top 10 keyword drops out of top 10 | High |
| Rankings | Moderate drop | Any keyword drops 10+ positions | Medium |
| Rankings | Competitor overtake | Competitor passes you for key term | Medium |
| Rankings | Positive movement | New Top 3, page 1 entry, 10+ position climb | Positive |
| SERP features | Snippet lost / won | Featured snippet ownership changes | High / Positive |
| SERP features | AI Overview change | Appears or disappears | Medium |
| Traffic | Traffic crash | Day-over-day decline >=50% | Critical |
| Traffic | Significant drop | Week-over-week decline >=30% | High |
| Traffic | Moderate decline | Month-over-month decline >=20% | Medium |
| Traffic | Trend warning | 3 consecutive weeks decline | Medium |
| Conversions | Conversion drop | Organic conversions down 30%+ | Critical |
| Conversions | CVR decline | Conversion rate drops 20%+ | High |
| Technical | Site down | HTTP 5xx errors | Critical |
| Technical | SSL expiry | Certificate expires in 14 days | Critical |
| Technical | Robots.txt block | Important pages blocked | Critical |
| Technical | Index drop | Important pages drop from index | Critical |
| Technical | Crawl/index/CWV/mobile issue | Error spike 50%+, 10% index drop, CWV poor, mobile errors | High |
| Technical | New 404 pages | 404 errors on important pages | Medium |
| Technical | Redirect chains | 3+ redirect hops | Medium |
| Security | Manual action / malware | GSC warning or flagged issue | Critical |
| Backlinks | High-value link lost | DA 70+ link removed | High |
| Backlinks | High-value link gained | New DA 70+ link | Positive |
| Backlinks | Multiple lost links | 10+ links lost in a day | Medium |
| Backlinks | Toxic / negative SEO | Spam pattern or toxic score +20% | High |
| Competitors | Competitor content/backlink move | New content/update or high-DA link | Info |
| GEO | Citation lost/won | AI citation ownership changes | Medium / Positive |
| GEO | Citation rate drop | AI citation rate drops 20%+ | High |
| Brand | Negative mention / rating drop | Sentiment or rating deterioration | High |
| Brand | Unlinked mention | Brand mention without link | Opportunity |
2. Page-Level Traffic Rules
| Page Type | Alert Condition | Priority |
|---|---|---|
| Homepage | 20%+ decline | Critical |
| Top 10 pages | 30%+ decline | High |
| Conversion pages | 25%+ decline | High |
| Blog posts | 40%+ decline | Medium |
3. Response Plans
| Priority | Response Time | Immediate Actions |
|---|---|---|
| Critical | Within 1 hour | Confirm data, check server/GSC/indexing, assign owner, start incident log |
| High | Same day | Diagnose cause, compare competitors/SERP, create recovery plan |
| Medium | Within 48 hours | Investigate trend, batch with related alerts, schedule fix |
| Low / Info | Weekly review | Document, tag trend, no interruption |
| Positive | Weekly review | Record win and identify repeatable driver |
| Alert Type | First Checks |
|---|---|
| Site down | Server, DNS, CDN, deploy status |
| Traffic crash | Algorithm update, GSC errors, analytics tag, competitors |
| Manual action | GSC message, affected URLs, remediation path |
| Critical rank drop | Indexing, SERP change, page changes, competitor movement |
| Backlink loss | Source page status, relationship owner, outreach path |
| CWV failure | Template, script, image, hosting, field data |
4. Notification Setup
| Priority | Channels | Frequency | Escalation |
|---|---|---|---|
| Critical | Email + SMS + Slack | Immediate | No response in 1hr -> Director |
| High | Email + Slack | Immediate | No response in 4hr -> Manager |
| Medium | Email + Slack | Daily digest | No response in 24hr -> Lead |
| Low / Positive | Weekly digest | None |
| Role | Critical | High | Medium | Low |
|---|---|---|---|---|
| SEO Manager | Yes | Yes | Yes | Yes |
| Dev Team | Yes | Tech only | No | No |
| Marketing Lead | Yes | Yes | No | No |
| Executive | Yes | No | No | No |
5. Suppression Rules
- Suppress duplicate alerts for 24 hours.
- Suppress known maintenance windows.
- Batch low-priority alerts into digests.
- Require source timestamp and metric source on every alert.
- Mark unresolved alerts with owner, status, and next check time.
Alert Threshold Guide
Severity Levels
Standard Deviation method: Info (1 SD), Warning (1.5 SD), Critical (2 SD), Emergency (3 SD) from baseline mean.
Thresholds by Metric Category
Traffic
| Metric | Warning | Critical | Emergency |
|---|---|---|---|
| Organic sessions (WoW) | -15% | -30% | -50% |
| Organic sessions (DoD) | -25% weekday | -40% | Site appears down |
| Non-brand sessions (WoW) | -20% | -35% | -50% |
| Organic conversions (WoW) | -20% | -40% | -60% |
| Top 10 page traffic (WoW) | -25% | -40% | -60% |
Rankings
| Metric | Warning | Critical |
|---|---|---|
| Tier 1 keyword position | Drop >= 3 | Drop >= 5 |
| Tier 2 keyword position | Drop >= 5 | Drop >= 10 |
| Tier 3 keyword position | Drop >= 10 | Off page 3 |
| Average position (all) | +2.0 worsening | +5.0 worsening |
| Keywords in top 10 | -10% count | -20% count |
| Brand keyword | Any drop from #1 | Below #3 |
| Featured snippet | Any loss | 3+ losses |
Technical
| Metric | Warning | Critical | Emergency |
|---|---|---|---|
| New 4xx errors | >5/day | >20/day | >100/day |
| New 5xx errors | >1/day | >5/day | >20/day |
| Crawl rate change | -30% baseline | -60% baseline | Near-zero |
| Index coverage drop | -5% | -15% | -30% |
| Server response time | >500ms | >1000ms | >2000ms |
| LCP (mobile) | Needs Improvement | Poor | >6s |
| CLS | >0.1 | >0.25 | >0.5 |
| INP | >200ms | >500ms | >1000ms |
Backlinks
| Metric | Warning | Critical |
|---|---|---|
| Referring domains lost (weekly) | >5% total | >15% total |
| High-authority link lost (DR 60+) | Any loss | 3+ in one week |
| Toxic link spike | >10/week | >50/week |
| Exact match anchor % | Reaches 20% | Reaches 30% |
GEO / AI Visibility
| Metric | Warning | Critical |
|---|---|---|
| AI citation rate | Drops 10+ pp | Below 10% |
| Key query citation lost | Any Tier 1 | 3+ Tier 1 queries |
| Citation position | Worsens by 2+ | Dropped entirely |
Alert Routing
| Priority | Channel | Escalation |
|---|---|---|
| P0 Emergency | SMS + Phone + Slack #emergencies | PagerDuty on-call |
| P1 Urgent | Slack #alerts + Email | SMS if unacknowledged in 4h |
| P2 Important | Email + Slack #daily | Auto-escalate to P1 after 1 week |
| P3 Monitor | Weekly digest | Auto-escalate to P2 after 1 month |
Suppression Rules
| Rule | Configuration |
|---|---|
| Duplicate cooldown | No re-alert same metric for 24h |
| Maintenance window | Suppress non-security alerts |
| Weekend adjustment | Increase traffic thresholds +20% |
| Recovery auto-close | Close if metric normalizes within 48h |
| Batch related | Group multiple ranking drops into one alert |
Threshold Tuning
| Signal | Action |
|---|---|
| >30% false positives | Widen thresholds by 0.5 SD |
| Missed real problem | Tighten the specific threshold |
| Seasonal change | Adjust baselines for known patterns |
| Major site change | Re-establish baseline (2-4 week observation) |
| After algorithm update | Stabilize 2-4 weeks, then recalibrate |
Site Maturity Guidelines
| Stage | Approach |
|---|---|
| New (0-6mo) | Wide thresholds, few alerts |
| Growing (6-18mo) | Moderate thresholds, expand coverage |
| Established (18mo+) | Tight thresholds, comprehensive |
| Post-migration | Reset to wide, re-tighten over 4-8 weeks |
Related skills
How it compares
Use alert-manager for threshold templates when you already track rankings and need consistent escalation rules rather than a full rank-reporting workflow.
FAQ
When should I use alert-manager versus rank-tracker?
Use alert-manager to configure future threshold notifications; use rank-tracker for one-time or ongoing position measurement and reporting.
What happens if no baseline exists for a metric?
Stop and ask the user to supply baseline data, accept Quick Reference defaults labeled Estimated, or cancel rather than invent thresholds.
Which alert categories are supported?
Rankings, traffic, technical, backlinks, competitors, GEO or AI, and brand alerts with per-category trigger conditions and priorities.
Is Alert Manager safe to install?
skills.sh reports 2 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.