Dirty13itch
13 verified skills
cluster-audit
Full cluster state audit. Use when asked for cluster status, health check, or infrastructure audit. Produces comprehensive report of all nodes, pods, services, PVCs, GPUs, and issues.
testing
deploy
Deploy Kaizen components with safety checks and validation
testing
gpu-status
Check GPU allocation and utilization across all nodes. Use when asked about GPUs, VRAM, or model capacity.
testing
kaizen-dev
Development workflow for Kaizen - branching, commits, testing
development
memory-test
Run E2E memory pipeline test — embed text, store in Qdrant, search and retrieve. Use to validate the memory system is working.
testing
session-resume
Resume from last checkpoint — show progress, cluster state, next actions
testing
status
Check Kaizen system health across all nodes and services
testing
test
Run the full integration test suite
testing
rollback
Emergency rollback for Kaizen deployments
devops
deploy-model
Deploy or redeploy an inference model on the cluster. Use when asked to deploy, update, or restart a model.
devops
.claude/skills/kaizen-infrastructure
--- name: kaizen-infrastructure description: Kaizen infrastructure management. Use when working on Kubernetes manifests, Talos configuration, Flux GitOps, or cluster operations. Triggers on: k8s, kubernetes, flux, talos, cluster, node, deployment, helm, kustomize. allowed-tools: Read, Write, Bash, Grep, Glob --- # Kaizen Infrastructure Skill ## When to Use - Creating or modifying Kubernetes manifests - Configuring Talos Linux nodes - Setting up Flux GitOps resources - Deploying applications to
tools
overnight
Launch autonomous overnight build session with Ralph Wiggum
development
validate
Pre-commit validation suite for manifests, scripts, and configs
testing