Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.anomalyarmor.ai/llms.txt

Use this file to discover all available pages before exploring further.

The /armor:coverage skill analyzes what’s being monitored and identifies gaps in your data observability coverage.

​
Usage

/armor:coverage
Or ask naturally:
  • “What am I monitoring?”
  • “What tables have no alerts?”
  • “Show me monitoring gaps”
  • “Which tables need freshness checks?”

​
Coverage Categories

  • Freshness: Tables with/without freshness schedules
  • Schema: Tables with/without schema baselines
  • Metrics: Tables with/without data quality metrics
  • Alerts: Tables with/without alert rules

​
Example Usage

​
Coverage Overview

You: What's my monitoring coverage?

Claude: Monitoring Coverage Summary:

Total Assets: 45

Coverage by Type:
- Freshness: 38 (84%)
- Schema: 42 (93%)
- Metrics: 35 (78%)
- Alerts: 28 (62%)

By Environment:
- Production: 100% covered
- Staging: 75% covered
- Raw/Landing: 50% covered

Overall Score: B+ (Good, but room for improvement)

​
Find Unmonitored Tables

You: What tables have no monitoring?

Claude: Found 7 unmonitored tables:

Raw Layer:
- raw.events_backup
- raw.legacy_data

Staging:
- staging.temp_orders
- staging.test_data

Archive:
- archive.orders_2023
- archive.customers_2023

Sandbox:
- sandbox.dev_analysis

Recommendation:
1. Add freshness monitoring to raw.events_backup (production data)
2. Review if archive tables need monitoring
3. Consider excluding sandbox from coverage metrics

​
Prioritize Gaps

You: What critical tables need monitoring?

Claude: Critical Tables Missing Monitoring:

HIGH PRIORITY (Production):
1. raw.events_backup
   - No freshness monitoring
   - No quality metrics
   - Recommendation: Add immediately

2. gold.financial_summary
   - Has freshness, missing quality checks
   - Recommendation: Add row count + null checks

MEDIUM PRIORITY:
3. staging.customer_enriched
   - Missing schema baseline
   - Recommendation: Create baseline

Coverage improvement: +12% by addressing these 3 tables

​
Common Questions

​
What counts as a ‘good’ coverage score?

Production tables should be at 100%. Staging in the 70-90% range is typical. Raw/landing and archive tables often don’t need full coverage, so anything above 50% there is usually fine. The overall letter grade weights production tables most heavily.

​
How do I exclude sandbox or archive tables from my coverage score?

Tag them with a governance tag (like sandbox or archive) using /armor:tags. The coverage skill respects exclusion tags so your score reflects only the tables you actually care about.

Monitor

Set up monitoring

Quality

Add quality checks

Status

Health overview