.claude/skills/status/SKILL.md
Check Kaizen system health across all nodes and services
npx skillsauth add Dirty13itch/kaizen statusInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Run comprehensive health check. Report on each section:
Cluster: kubectl get nodes -o wide && kubectl get pods -A
GPUs: kubectl exec into GPU pods and run nvidia-smi or check node labels
Inference: curl -s http://10.10.10.12:30000/health and port 30001
Storage: df -h /mnt/disk9/models on VAULT, check NFS PV status
Monitoring: Check Prometheus/Grafana pods in kaizen-monitoring namespace
Format as a status dashboard. Flag anything not healthy.
testing
Pre-commit validation suite for manifests, scripts, and configs
testing
Run the full integration test suite
testing
Resume from last checkpoint — show progress, cluster state, next actions
devops
Emergency rollback for Kaizen deployments