dirien

Getting Started With DevOps AI Skills — DevOps skill for Claude Code

DevOps community

Getting Started with DevOps AI Skills — a Pulumi workshop: build, share, and run Agent Skills with Microsoft APM.

How to install Getting Started With DevOps AI Skills

This entry records only its repository, not the path inside it, so there is no exact command to give. Open dirien/getting-started-with-devops-ai-skills and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Getting Started With DevOps AI Skills does

Getting Started with DevOps AI Skills — a Pulumi workshop: build, share, and run Agent Skills with Microsoft APM. Slides, chapters, skills, LSP+hooks, and a Claude/Codex/Pulumi devcontainer.

Alternatives in DevOps

  • Claudable — Claudable is an open-source web builder that leverages local CLI agents, such as Claude Code, Codex, Gemini CL 4k ★
  • Claudekit DevOps Tools — DevOps automation tools 1.9k ★
  • DevOps Basics Pack — Foundational DevOps skills and practices 1.6k ★

README

Getting Started with DevOps AI Skills

A hands-on workshop on building, sharing, and running **Agent Skills** for DevOps and platform engineering — using [Pulumi](https://www.pulumi.com/) as the running example and [Microsoft APM](https://microsoft.github.io/apm/) to manage the agent primitives.

**Presenters:** Engin Diri (Senior Solutions Architect) & Adam Gordon Bell (Community Engineer) · Pulumi **Format:** Workshop (≈ 60 min) · slides + follow-along chapters

[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/dirien/getting-started-with-devops-ai-skills)


What you'll learn

AI coding agents (Claude Code, Copilot, Cursor, Pulumi Neo …) are good out of the box, but they don't know *your* runbooks, *your* golden paths, or *your* infrastructure conventions. **Agent Skills** are the missing piece: small, composable folders of instructions + scripts that teach an agent how your team actually ships software.

By the end you will be able to:

  • Discover and evaluate existing skills before writing your own
  • Connect skills to your agent and use them inside real DevOps workflows
  • Read the anatomy of a skill (SKILL.md, frontmatter, bundled resources)
  • Build skills from scratch — simple and complex/multi-file
  • Follow design principles that make skills reliable and discoverable
  • Maintain skills: keep them current, version them, and remove them cleanly
  • Turn an everyday DevOps workflow into a reusable skill

This workshop reframes the LinkedIn Learning course *"Give Your Agent Skills"* for a **DevOps / platform-engineering** audience, and grounds every lesson in real infrastructure-as-code tasks.

Who it's for

Platform engineers, SREs, and DevOps engineers who already use (or want to use) an AI coding agent and want it to follow their team's standards instead of guessing.

Run it in a Codespace (zero setup)

The fastest way to follow along: open the repo in a **GitHub Code