Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From claude-devops
Investigate service health in Datadog by running run-investigation.sh with the service name, environment, and time window.
npx claudepluginhub kjenney/claude-devopsHow this skill is triggered — by the user, by Claude, or both
Slash command
/claude-devops:datadog-troubleshootingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
The `/datadog-query` command and `datadog-investigator` agent run the automated investigation orchestrator:
Investigates production issues by querying Datadog logs, metrics, and APM traces, then correlating findings with codebase. Useful for debugging errors, latency spikes, alerts in deployed services.
Queries Datadog logs, metrics, APM traces, RUM events, incidents, and monitors for production debugging and performance analysis. Activates on Datadog, APM traces, or RUM mentions.
Share bugs, ideas, or general feedback.
The /datadog-query command and datadog-investigator agent run the automated investigation orchestrator:
bash skills/datadog-troubleshooting/run-investigation.sh "<service-name>" "<environment>" "[time-window-minutes]"
Set Datadog credentials:
export DD_API_KEY="<your-api-key>"
export DD_APP_KEY="<your-app-key>"
Run /datadog-query command
Agent asks for service name, environment, and time window (defaults to 60 minutes)
Agent executes the investigation script
Wait for results
DD_API_KEY from Datadog → Organization Settings → API KeysDD_APP_KEY from Datadog → Organization Settings → Application KeysDD_SITE optional (defaults to datadoghq.com, use datadoghq.eu for EU)examples/investigate-service.sh - Queries monitors, logs, metrics, and APM traces for a service