ai-development-scaffold/.claude/skills/infrastructure/docker-kubernetes/SKILL.md

name, description

name	description
docker-kubernetes	Docker containerization and Kubernetes orchestration patterns. Use when building containers, writing Dockerfiles, or deploying to Kubernetes.

Docker & Kubernetes Skill

Dockerfile Best Practices

Multi-Stage Build (Python)

# Build stage
FROM python:3.12-slim as builder

WORKDIR /app

# Install build dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential \
    && rm -rf /var/lib/apt/lists/*

# Install Python dependencies
COPY pyproject.toml uv.lock ./
RUN pip install uv && uv sync --frozen --no-dev

# Production stage
FROM python:3.12-slim as production

WORKDIR /app

# Create non-root user
RUN groupadd -r appuser && useradd -r -g appuser appuser

# Copy only necessary files from builder
COPY --from=builder /app/.venv /app/.venv
COPY src/ ./src/

# Set environment
ENV PATH="/app/.venv/bin:$PATH"
ENV PYTHONUNBUFFERED=1
ENV PYTHONDONTWRITEBYTECODE=1

# Switch to non-root user
USER appuser

EXPOSE 8000

HEALTHCHECK --interval=30s --timeout=3s --start-period=5s --retries=3 \
    CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')"

CMD ["uvicorn", "src.main:app", "--host", "0.0.0.0", "--port", "8000"]

Multi-Stage Build (Node.js)

# Build stage
FROM node:22-alpine as builder

WORKDIR /app

# Install dependencies first (layer caching)
COPY package*.json ./
RUN npm ci

# Build application
COPY . .
RUN npm run build

# Production stage
FROM node:22-alpine as production

WORKDIR /app

# Create non-root user
RUN addgroup -S appuser && adduser -S appuser -G appuser

# Copy only production dependencies and built files
COPY --from=builder /app/package*.json ./
RUN npm ci --only=production && npm cache clean --force

COPY --from=builder /app/dist ./dist

USER appuser

EXPOSE 3000

HEALTHCHECK --interval=30s --timeout=3s --start-period=5s --retries=3 \
    CMD wget --no-verbose --tries=1 --spider http://localhost:3000/health || exit 1

CMD ["node", "dist/main.js"]

Multi-Stage Build (Rust)

# Build stage
FROM rust:1.75-slim as builder

WORKDIR /app

# Create a dummy project for dependency caching
RUN cargo new --bin app
WORKDIR /app/app

# Copy manifests and build dependencies
COPY Cargo.toml Cargo.lock ./
RUN cargo build --release && rm -rf src

# Copy source and build
COPY src ./src
RUN touch src/main.rs && cargo build --release

# Production stage
FROM debian:bookworm-slim as production

# Install runtime dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
    ca-certificates \
    && rm -rf /var/lib/apt/lists/*

# Create non-root user
RUN groupadd -r appuser && useradd -r -g appuser appuser

COPY --from=builder /app/app/target/release/app /usr/local/bin/app

USER appuser

EXPOSE 8080

HEALTHCHECK --interval=30s --timeout=3s --start-period=5s --retries=3 \
    CMD ["/usr/local/bin/app", "health"]

CMD ["/usr/local/bin/app"]

Docker Compose

Development Setup

# docker-compose.yml
services:
  app:
    build:
      context: .
      target: development
    ports:
      - "8000:8000"
    volumes:
      - .:/app
      - /app/.venv  # Exclude venv from mount
    environment:
      - DATABASE_URL=postgresql://user:pass@db:5432/myapp
      - REDIS_URL=redis://redis:6379/0
      - DEBUG=true
    depends_on:
      db:
        condition: service_healthy
      redis:
        condition: service_started

  db:
    image: postgres:16-alpine
    environment:
      POSTGRES_USER: user
      POSTGRES_PASSWORD: pass
      POSTGRES_DB: myapp
    volumes:
      - postgres_data:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U user -d myapp"]
      interval: 5s
      timeout: 5s
      retries: 5

  redis:
    image: redis:7-alpine
    volumes:
      - redis_data:/data

volumes:
  postgres_data:
  redis_data:

Production Setup

# docker-compose.prod.yml
services:
  app:
    image: ${REGISTRY}/myapp:${VERSION}
    deploy:
      replicas: 3
      resources:
        limits:
          cpus: '0.5'
          memory: 512M
        reservations:
          cpus: '0.25'
          memory: 256M
      restart_policy:
        condition: on-failure
        delay: 5s
        max_attempts: 3
    environment:
      - DATABASE_URL_FILE=/run/secrets/db_url
    secrets:
      - db_url
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s

secrets:
  db_url:
    external: true

Kubernetes Manifests

Deployment

# k8s/deployment.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
  name: myapp
  labels:
    app: myapp
spec:
  replicas: 3
  selector:
    matchLabels:
      app: myapp
  template:
    metadata:
      labels:
        app: myapp
    spec:
      securityContext:
        runAsNonRoot: true
        runAsUser: 1000
        fsGroup: 1000
      containers:
        - name: myapp
          image: myregistry/myapp:v1.0.0
          ports:
            - containerPort: 8000
          resources:
            requests:
              cpu: "100m"
              memory: "128Mi"
            limits:
              cpu: "500m"
              memory: "512Mi"
          env:
            - name: DATABASE_URL
              valueFrom:
                secretKeyRef:
                  name: myapp-secrets
                  key: database-url
          livenessProbe:
            httpGet:
              path: /health
              port: 8000
            initialDelaySeconds: 10
            periodSeconds: 10
          readinessProbe:
            httpGet:
              path: /ready
              port: 8000
            initialDelaySeconds: 5
            periodSeconds: 5
          securityContext:
            allowPrivilegeEscalation: false
            readOnlyRootFilesystem: true
            capabilities:
              drop:
                - ALL

Service

# k8s/service.yaml
apiVersion: v1
kind: Service
metadata:
  name: myapp
spec:
  selector:
    app: myapp
  ports:
    - port: 80
      targetPort: 8000
  type: ClusterIP
---
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
  name: myapp
  annotations:
    kubernetes.io/ingress.class: nginx
    cert-manager.io/cluster-issuer: letsencrypt-prod
spec:
  tls:
    - hosts:
        - myapp.example.com
      secretName: myapp-tls
  rules:
    - host: myapp.example.com
      http:
        paths:
          - path: /
            pathType: Prefix
            backend:
              service:
                name: myapp
                port:
                  number: 80

ConfigMap and Secrets

# k8s/config.yaml
apiVersion: v1
kind: ConfigMap
metadata:
  name: myapp-config
data:
  LOG_LEVEL: "info"
  CACHE_TTL: "3600"
---
apiVersion: v1
kind: Secret
metadata:
  name: myapp-secrets
type: Opaque
stringData:
  database-url: postgresql://user:pass@db:5432/myapp  # Use sealed-secrets in production

Horizontal Pod Autoscaler

# k8s/hpa.yaml
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: myapp
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: myapp
  minReplicas: 2
  maxReplicas: 10
  metrics:
    - type: Resource
      resource:
        name: cpu
        target:
          type: Utilization
          averageUtilization: 70
    - type: Resource
      resource:
        name: memory
        target:
          type: Utilization
          averageUtilization: 80

Helm Chart Structure

myapp-chart/
├── Chart.yaml
├── values.yaml
├── values-prod.yaml
├── templates/
│   ├── _helpers.tpl
│   ├── deployment.yaml
│   ├── service.yaml
│   ├── ingress.yaml
│   ├── configmap.yaml
│   ├── secret.yaml
│   └── hpa.yaml
└── charts/

values.yaml

replicaCount: 2

image:
  repository: myregistry/myapp
  tag: latest
  pullPolicy: IfNotPresent

service:
  type: ClusterIP
  port: 80

ingress:
  enabled: true
  host: myapp.example.com
  tls: true

resources:
  requests:
    cpu: 100m
    memory: 128Mi
  limits:
    cpu: 500m
    memory: 512Mi

autoscaling:
  enabled: true
  minReplicas: 2
  maxReplicas: 10
  targetCPUUtilization: 70

Commands

# Docker
docker build -t myapp:latest .
docker build --target development -t myapp:dev .
docker run -p 8000:8000 myapp:latest
docker compose up -d
docker compose logs -f app
docker compose down -v

# Kubernetes
kubectl apply -f k8s/
kubectl get pods -l app=myapp
kubectl logs -f deployment/myapp
kubectl rollout status deployment/myapp
kubectl rollout undo deployment/myapp
kubectl port-forward svc/myapp 8000:80

# Helm
helm install myapp ./myapp-chart
helm upgrade myapp ./myapp-chart -f values-prod.yaml
helm rollback myapp 1
helm uninstall myapp

Security Checklist

• Run as non-root user
• Use multi-stage builds (minimal final image)
• Pin base image versions
• Scan images for vulnerabilities (Trivy, Snyk)
• No secrets in images or environment variables
• Read-only root filesystem where possible
• Drop all capabilities, add only needed ones
• Set resource limits
• Use network policies
• Enable Pod Security Standards