Skip to content

DevOps Engineer

Writes Dockerfiles, CI/CD pipelines, Kubernetes and Terraform configs, and incident runbooks

Stars
12,176
Licence
MIT
Files
10 files

What it does

This skill gives an AI coding agent the playbook of a senior DevOps engineer. When you ask for help with building, testing, packaging, or deploying software, the agent follows structured steps (assess, design, implement, validate, deploy with approval, monitor) and loads reference notes on GitHub Actions, GitLab CI, Docker, Kubernetes, Terraform, deployment strategies, platform engineering, release automation, and incident response. It produces pipeline files, Dockerfiles, infrastructure templates, and rollback procedures, and it is instructed to ask for explicit approval before any production deployment.

Great for

  • Developers setting up CI/CD pipelines for a web or API project
  • Teams containerizing an app or writing Kubernetes manifests and Terraform templates
  • On-call engineers who want a structured incident response or runbook draft

Skip it if

  • Running production deployments unattended: the skill requires human approval, and the agent can still make mistakes in generated configs that must be reviewed before use
  • Non-technical users without access to a repository, cloud account, or terminal, since the outputs need to be run and checked by someone who understands them
  • Teams needing a verified security audit: the skill recommends container scanning but does not itself perform a security review

Try asking

  • “Create a GitHub Actions workflow that builds, tests, scans, and pushes a Docker image for my Python app”
  • “Write a multi-stage Dockerfile for my Node service with a health check”
  • “Draft a Kubernetes deployment with resource limits and a rollback procedure for production”
  • “Write a runbook for responding to a database outage, with a postmortem template”
Step-by-step guide: how to use DevOps EngineerInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 10 original files, the MIT licence and an attribution note.

    devops-engineer.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip devops-engineer.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip devops-engineer.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Review every generated pipeline, Dockerfile, and Terraform plan yourself before running them against real environments
  • Keep secrets in a secret manager, not in code or CI variables, and check the agent did not hardcode any
  • Ask the agent to name the exact rollback command and verification step before any deployment, and confirm it matches your platform

What's inside

  • references/deployment-strategies.md
  • references/docker-patterns.md
  • references/github-actions.md
  • references/gitlab-ci.md
  • references/incident-response.md
  • references/kubernetes.md
  • references/platform-engineering.md
  • references/release-automation.md
  • references/terraform-iac.md
  • SKILL.md

Redistributed unmodified from Jeffallan/claude-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.