signoz-investigating-alerts
Alert Investigate
Diagnose why a SigNoz alert fired. The skill correlates the alert's own
signal with neighbor signals around the fire window, and surfaces a
ranked list of likely causes with supporting evidence. It is the
companion to signoz-explaining-alerts — explain decodes the rule
statically; investigate diagnoses a specific incident.
Prerequisites
This skill calls SigNoz MCP server tools heavily (signoz:signoz_get_alert,
signoz:signoz_get_alert_history, signoz:signoz_execute_builder_query,
signoz:signoz_query_metrics, signoz:signoz_search_traces, signoz:signoz_search_logs,
signoz:signoz_get_trace_details, etc.). Before running the workflow,
confirm the signoz:signoz_* tools are available. If they are not, the
SigNoz MCP server is not installed or configured — stop and direct
the user to set it up: https://signoz.io/docs/ai/signoz-mcp-server/.
The investigation depends on correlating multiple MCP queries; without
the server there is no way to ground the analysis.
More from signoz/agent-skills
signoz-docs
Use this skill first whenever the user asks about SigNoz instrumentation, OpenTelemetry setup, querying, dashboards, alerts, troubleshooting, self-hosted deployment, API endpoints, auth headers, or where to find anything in SigNoz docs.
116signoz-clickhouse-query
>-
100signoz-searching-docs
>
39signoz-writing-clickhouse-queries
>-
39signoz-generating-queries
>
35signoz-modifying-dashboards
>
34