When your payment service goes down at 2 AM and you're fumbling through Slack history for that kubectl command, you need structured runbooks that work under pressure. This generates comprehensive incident response procedures with specific bash commands, escalation matrices, and communication templates. It covers service outages, database issues, traffic spikes, and partial failures with actual troubleshooting steps like checking pod status, rolling back deployments, and killing slow queries. The templates include verification commands, rollback procedures, and severity-based escalation paths. Essential for teams moving from "figure it out as we go" to standardized incident response that works when your brain is running on caffeine and adrenaline.
npx skills add https://github.com/wshobson/agents --skill incident-runbook-templates