Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →github/aws-cloudwatch-investigation
Reusable investigation patterns for AWS CloudWatch: Logs Insights query templates, alarm-to-deployment correlation, blast-radius narrowing decision tree, and PromQL-style metric query patterns for structured incident triage.
Passed 19 of 21 test cases with the skill, and 11 of 21 without it.
and 13 more in the full report
9 fixed11 passed either way1 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
What specific conditions must be satisfied for a deployment event to receive a STRONG correlation rating against a CloudWatch alarm?
| Checked | Without skill | With skill |
|---|---|---|
| Requires actor identity to match a CI/CD role | Missed | Passed |
| Requires confirming alarm status in prior deployment cycle | Missed | Passed |
The instructions your model reads when the skill loads.
Reusable patterns for investigating production incidents using CloudWatch Logs, Metrics, and Alarms. These patterns are designed to be composed together during incident triage.
Find the top errors in a time window, grouped by error type:
fields @timestamp, @message, @logStream
| filter @message like /(?i)(error|exception|fatal|critical)/
| stats count(*) as errorCount by bin(5m), @logStream
| sort errorCount desc
| limit 20
Identify which operations are driving latency spikes:
fields @timestamp, @duration, operation
| filter ispresent(@duration)
| stats avg(@duration) as avgMs,
pct(@duration, 50) as p50Ms,
pct(@duration, 95) as p95Ms,
pct(@duration, 99) as p99Ms,
count(*) as invocations
by operation
| sort p99Ms desc
| limit 15
Quantify cold start impact during an incident:
test cases passed, vs 11 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.