DevOps

The problem

Infrastructure setup often suffers from scope creep, leading to bloated Dockerfiles and expensive cloud configurations that the project doesn't actually need yet. Developers waste time inventing complex CI pipelines and Kubernetes manifests before the core application even runs.

What it does

• Generates the absolute minimum Dockerfile, CI config, and env samples based strictly on your infrastructure handoff.
• Enforces a "no shopping" rule that prevents the creation of unrequested clusters, service meshes, or cloud modules.
• Produces a standardized infra/ci.md contract file that tracks deployment status and implementation decisions.
• Safeguards credentials by ensuring real tokens never enter the repository tree, using only placeholders for environment samples.

Frameworks & tools

Docker, Docker Compose, and generic CI runners. The skill adapts to the stack defined in your architecture docs, supporting various base images and OS families.

Why this beats prompting it yourself

General LLMs tend to "hallucinate" infrastructure, adding databases or registries just because they seem standard. This skill strictly limits output to what is named in your docs, preventing architectural drift and keeping your repository clean of "just in case" configuration files.

Use cases

• Creating a lean Dockerfile for a specific application slice.
• Generating .env.example files based on required secrets listed in infra docs.
• Setting up local-first CI commands without committing to a specific cloud vendor.
• Validating that devops requirements match the architectural vision before implementation.

Known limitations

Does not perform cloud provisioning, hosting selection, or application coding. Requires existing infrastructure and architecture documentation to function.