Docker Development

Docker Development

Smaller images. Faster builds. Secure containers. No guesswork.

Opinionated Docker workflow that turns bloated Dockerfiles into production-grade containers. Covers optimization, multi-stage builds, compose orchestration, and security hardening.

Not a Docker tutorial — a set of concrete decisions about how to build containers that don't waste time, space, or attack surface.

Slash Commands

When This Skill Activates

Recognize these patterns from the user:

• "Optimize this Dockerfile"
• "My Docker build is slow"
• "Create a docker-compose for this project"
• "Is this Dockerfile secure?"
• "Reduce my Docker image size"
• "Set up multi-stage builds"
• "Docker best practices for [language/framework]"
• Any request involving: Dockerfile, docker-compose, container, image size, build cache, Docker security

If the user has a Dockerfile or wants to containerize something → this skill applies.

Workflow

/docker:optimize — Dockerfile Optimization

1. Analyze current state

   • Read the Dockerfile
   • Identify base image and its size
   • Count layers (each RUN/COPY/ADD = 1 layer)
   • Check for common anti-patterns

2. Apply optimization checklist

   BASE IMAGE
   ├── Use specific tags, never :latest in production
   ├── Prefer slim/alpine variants (debian-slim > ubuntu > debian)
   ├── Pin digest for reproducibility in CI: image@sha256:...
   └── Match base to runtime needs (don't use python:3.12 for a compiled binary)
   
   LAYER OPTIMIZATION
   ├── Combine related RUN commands with && \
   ├── Order layers: least-changing first (deps before source code)
   ├── Clean package manager cache in the same RUN layer
   ├── Use .dockerignore to exclude unnecessary files
   └── Separate build deps from runtime deps
   
   BUILD CACHE
   ├── COPY dependency files before source code (package.json, requirements.txt, go.mod)
   ├── Install deps in a separate layer from code copy
   ├── Use BuildKit cache mounts: --mount=type=cache,target=/root/.cache
   └── Avoid COPY . . before dependency installation
   
   MULTI-STAGE BUILDS
   ├── Stage 1: build (full SDK, build tools, dev deps)
   ├── Stage 2: runtime (minimal base, only production artifacts)
   ├── COPY --from=builder only what's needed
   └── Final image should have NO build tools, NO source code, NO dev deps

3. Generate optimized Dockerfile

   • Apply all relevant optimizations
   • Add inline comments explaining each decision
   • Report estimated size reduction

4. Validate

   python3 scripts/dockerfile_analyzer.py Dockerfile

/docker:compose — Docker Compose Configuration

1. Identify services

   • Application (web, API, worker)
   • Database (postgres, mysql, redis, mongo)
   • Cache (redis, memcached)
   • Queue (rabbitmq, kafka)
   • Reverse proxy (nginx, traefik, caddy)

2. Apply compose best practices

   SERVICES
   ├── Use depends_on with condition: service_healthy
   ├── Add healthchecks for every service
   ├── Set resource limits (mem_limit, cpus)
   ├── Use named volumes for persistent data
   └── Pin image versions
   
   NETWORKING
   ├── Create explicit networks (don't rely on default)
   ├── Separate frontend and backend networks
   ├── Only expose ports that need external access
   └── Use internal: true for backend-only networks
   
   ENVIRONMENT
   ├── Use env_file for secrets, not inline environment
   ├── Never commit .env files (add to .gitignore)
   ├── Use variable substitution: ${VAR:-default}
   └── Document all required env vars
   
   DEVELOPMENT vs PRODUCTION
   ├── Use compose profiles or override files
   ├── Dev: bind mounts for hot reload, debug ports exposed
   ├── Prod: named volumes, no debug ports, restart: unless-stopped
   └── docker-compose.override.yml for dev-only config

3. Generate compose file

   • Output docker-compose.yml with healthchecks, networks, volumes
   • Generate .env.example with all required variables documented
   • Add dev/prod profile annotations