AI Runway AKS Setup
Walk an existing AKS cluster to a running AI model: cluster verification, controller install, GPU assessment, provider setup, first deployment
- What
- Walk an existing AKS cluster to a running AI model: cluster verification, controller install, GPU assessment, provider setup, first deployment
- Cost
- Free
- Needs
- an Azure subscription (billable — GPU node pools cost several dollars/hour), an existing AKS cluster, `kubectl`, `make`, and `az` CLI access. Companion `azure-kubernetes` skill needed if no cluster exists yet.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — an Azure ops skill that takes you from a bare AKS cluster to a running AI model through AI Runway, in six sequenced steps: cluster verification, controller installation, GPU assessment (it flags dtype/attention constraints like bfloat16 on T4/V100), inference provider setup (KAITO, Dynamo, or KubeRay), first model deployment, and a summary with smoke test. It asks for your confirmation before every install, supports `skip-to-step N` to resume a half-finished setup, and ships an error-handling matrix with remediation commands. By @microsoft, listed here with credit to its creator. Honest caveats: the SKILL.md carries an explicit cost warning — GPU node pools are billable (A100-class nodes run several dollars per hour) and you need a real Azure subscription; it assumes an AKS cluster already exists and hands off to the companion `azure-kubernetes` skill when it doesn't; it uses `kubectl`/`make` directly, no MCP tools. Skill Harbor never reviews the code, review it yourself before use.
Version:
Install
Prerequisites: an Azure subscription (billable — GPU node pools cost several dollars/hour), an existing AKS cluster, `kubectl`, `make`, and `az` CLI access. Companion `azure-kubernetes` skill needed if no cluster exists yet. Install "AI Runway AKS Setup" for me. It walks an existing AKS cluster from verification through controller install, GPU assessment, and inference provider setup to a running AI model deployment. Repository: https://github.com/microsoft/azure-skills/blob/main/.github/plugins/azure-skills/skills/airunway-aks-setup/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "microsoft-azure-airunway-aks-setup". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. confirm my Azure login and GPU cost approval). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.