airunway-aks-setup
Skill1.6k starsChanged 19 days agoMITView on GitHub
Set up AI Runway on AKS — from bare cluster to running model. Covers cluster verification, controller install, GPU assessment, provider setup, and first deployment. WHEN: \"setup AI Runway\", \"onboard AKS cluster\", \"install AI Runway\", \"airunway setup\", \"deploy model to AKS\", \"GPU inference on AKS\", \"KAITO setup on AKS\", \"run LLM on AKS\", \"vLLM on AKS\", \"set up model serving on AKS\", \"AI Runway controller\".
5 other projects use a version of this, 3 of them edited.
Trending
More talk lately.about the whole repository
Most recently taken up by
- desktop-commander/skillsedited, first seen Oct 17, 2026
- microsoft/GitHub-Copilot-for-Azureedited, first seen Oct 13, 2026
- microsoft/skillsword for word, first seen Oct 13, 2026
- microsoft/agent-skillsword for word, first seen Oct 8, 2026
- jorgeasaurus/agent-skillsedited, first seen May 11, 2026
Who's talking about microsoft/azure-skills
- microsoft/apm“Fold marketplace authoring config into apm.yml as the single APM surface”GitHub · Apr 29, 2026 · 2 reactions
- salaboy/skills-oci“Support for Skill Collections”GitHub · Jul 3, 2026 · 1 reactions
- Azure/azure-dev“Add `azd tool install/upgrade azure-skills` with per-host selection”GitHub · Jun 18, 2026 · 1 reactions
- microsoft/apm“feat(pack): unify 'apm pack' to produce bundle and marketplace.json (closes #722)”GitHub · Apr 29, 2026 · 1 reactions
- microsoft/GitHub-Copilot-for-Azure“Update CHANGELOG.md when syncing plugin content”GitHub · Apr 16, 2026 · 1 reactions
The biggest 5 of 50 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 50
Talked about on GitHub (50 times).
On GitHub · 50
- Apr 29, 2026Fold marketplace authoring config into apm.yml as the single APM surface — microsoft/apm2 reactions
- Jul 3, 2026Support for Skill Collections — salaboy/skills-oci1 reaction
- Jun 18, 2026Add `azd tool install/upgrade azure-skills` with per-host selection — Azure/azure-dev1 reaction · 1 comment
- Apr 29, 2026feat(pack): unify 'apm pack' to produce bundle and marketplace.json (closes #722) — microsoft/apm1 reaction · 1 comment
- Apr 16, 2026Update CHANGELOG.md when syncing plugin content — microsoft/GitHub-Copilot-for-Azure1 reaction · 2 comments
45 more on GitHub
- Nov 14, 2026agent-skills.github.microsoft.azure-skills: 1.2.123 → 1.2.124 — sudosubin/agents.nix0 reactions
- Nov 13, 2026claude-code-marketplaces.github.microsoft.azure-skills: 1.2.123 → 1.2.124 — sudosubin/agents.nix0 reactions
- Nov 13, 2026claude-code-plugins.github.microsoft.azure-skills: 1.2.123 → 1.2.124 — sudosubin/agents.nix0 reactions
- Nov 13, 2026agent-plugins.github.microsoft.azure-skills: 1.2.123 → 1.2.124 — sudosubin/agents.nix0 reactions
- Nov 13, 2026copilot-plugins.github.microsoft.azure-skills: 1.2.123 → 1.2.124 — sudosubin/agents.nix0 reactions
- Nov 13, 2026[Skill Bug]: prereq native-module unknown guidance conflicts with Boolean schema — microsoft/GitHub-Copilot-for-Azure0 reactions · 1 comment
- Nov 13, 2026agent-skills.github.microsoft.azure-skills: 1.2.122 → 1.2.123 — sudosubin/agents.nix0 reactions
- Nov 12, 2026claude-code-marketplaces.github.microsoft.azure-skills: 1.2.122 → 1.2.123 — sudosubin/agents.nix0 reactions
- Nov 12, 2026claude-code-plugins.github.microsoft.azure-skills: 1.2.122 → 1.2.123 — sudosubin/agents.nix0 reactions
- Nov 12, 2026agent-plugins.github.microsoft.azure-skills: 1.2.122 → 1.2.123 — sudosubin/agents.nix0 reactions
- Nov 12, 2026copilot-plugins.github.microsoft.azure-skills: 1.2.122 → 1.2.123 — sudosubin/agents.nix0 reactions
- Nov 10, 2026copilot-plugins.github.microsoft.azure-skills: 1.2.120 → 1.2.122 — sudosubin/agents.nix0 reactions
- Nov 10, 2026agent-skills.github.microsoft.azure-skills: 1.2.120 → 1.2.122 — sudosubin/agents.nix0 reactions
- Nov 10, 2026claude-code-marketplaces.github.microsoft.azure-skills: 1.2.120 → 1.2.122 — sudosubin/agents.nix0 reactions
- Nov 10, 2026claude-code-plugins.github.microsoft.azure-skills: 1.2.120 → 1.2.122 — sudosubin/agents.nix0 reactions
- Nov 10, 2026agent-plugins.github.microsoft.azure-skills: 1.2.120 → 1.2.122 — sudosubin/agents.nix0 reactions
- Nov 10, 2026copilot-plugins.github.microsoft.azure-skills: 1.2.118 → 1.2.120 — sudosubin/agents.nix0 reactions
- Nov 10, 2026claude-code-marketplaces.github.microsoft.azure-skills: 1.2.118 → 1.2.120 — sudosubin/agents.nix0 reactions
- Nov 10, 2026agent-skills.github.microsoft.azure-skills: 1.2.118 → 1.2.120 — sudosubin/agents.nix0 reactions
- Nov 10, 2026claude-code-plugins.github.microsoft.azure-skills: 1.2.118 → 1.2.120 — sudosubin/agents.nix0 reactions
- Nov 10, 2026agent-plugins.github.microsoft.azure-skills: 1.2.118 → 1.2.120 — sudosubin/agents.nix0 reactions
- Nov 9, 2026claude-code-marketplaces.github.microsoft.azure-skills: 1.2.115 → 1.2.118 — sudosubin/agents.nix0 reactions
- Nov 9, 2026chore: sync azure plugin name and version to apm.yml — microsoft/GitHub-Copilot-for-Azure0 reactions
- Nov 9, 2026copilot-plugins.github.microsoft.azure-skills: 1.2.115 → 1.2.118 — sudosubin/agents.nix0 reactions
- Nov 9, 2026agent-skills.github.microsoft.azure-skills: 1.2.115 → 1.2.118 — sudosubin/agents.nix0 reactions
- Nov 9, 2026claude-code-plugins.github.microsoft.azure-skills: 1.2.115 → 1.2.118 — sudosubin/agents.nix0 reactions
- Nov 9, 2026agent-plugins.github.microsoft.azure-skills: 1.2.115 → 1.2.118 — sudosubin/agents.nix0 reactions
- Nov 7, 2026claude-code-marketplaces.github.microsoft.azure-skills: 1.2.114 → 1.2.115 — sudosubin/agents.nix0 reactions
- Nov 6, 2026agent-skills.github.microsoft.azure-skills: 1.2.114 → 1.2.115 — sudosubin/agents.nix0 reactions
- Nov 6, 2026claude-code-plugins.github.microsoft.azure-skills: 1.2.114 → 1.2.115 — sudosubin/agents.nix0 reactions
- Nov 6, 2026agent-plugins.github.microsoft.azure-skills: 1.2.114 → 1.2.115 — sudosubin/agents.nix0 reactions
- Nov 6, 2026copilot-plugins.github.microsoft.azure-skills: 1.2.114 → 1.2.115 — sudosubin/agents.nix0 reactions
- Nov 6, 2026agent-skills.github.microsoft.azure-skills: 1.2.113 → 1.2.114 — sudosubin/agents.nix0 reactions
- Nov 5, 2026claude-code-plugins.github.microsoft.azure-skills: 1.2.113 → 1.2.114 — sudosubin/agents.nix0 reactions
- Nov 5, 2026agent-plugins.github.microsoft.azure-skills: 1.2.113 → 1.2.114 — sudosubin/agents.nix0 reactions
- Nov 5, 2026copilot-plugins.github.microsoft.azure-skills: 1.2.113 → 1.2.114 — sudosubin/agents.nix0 reactions
- Nov 5, 2026claude-code-marketplaces.github.microsoft.azure-skills: 1.2.113 → 1.2.114 — sudosubin/agents.nix0 reactions
- Nov 5, 2026agent-plugins.github.microsoft.azure-skills: init at 1.2.113 — sudosubin/agents.nix0 reactions
- Nov 4, 2026agent-skills.github.microsoft.azure-skills: 1.2.111 → 1.2.113 — sudosubin/agents.nix0 reactions
- Nov 4, 2026claude-code-plugins.github.microsoft.azure-skills: 1.2.111 → 1.2.113 — sudosubin/agents.nix0 reactions
- Nov 4, 2026agent-skills.github.microsoft.azure-skills: 1.2.110 → 1.2.111 — sudosubin/agents.nix0 reactions
- Nov 2, 2026agent-skills.github.microsoft.azure-skills: 1.2.109 → 1.2.110 — sudosubin/agents.nix0 reactions
- Nov 2, 2026chore: bump external skill pins — jthiruveedula/agentkit0 reactions
- Oct 30, 2026agent-skills.github.microsoft.azure-skills: 1.2.108 → 1.2.109 — sudosubin/agents.nix0 reactions
- Oct 29, 2026agent-skills.github.microsoft.azure-skills: 1.2.106 → 1.2.108 — sudosubin/agents.nix0 reactions
Other versions5 projects use a version of this.
Word for word · 2
- microsoft/skills★ 3.2k100% same
- microsoft/agent-skills★ 3.2k100% same
Edited · 3
- microsoft/GitHub-Copilot-for-Azure★ 26499% same
- jorgeasaurus/agent-skills★ 1497% same
- desktop-commander/skills★ 497% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository88 other files it gives its agents.
- aks-cost-optimizationSkill
- aks-gpu-inferenceSkill
- aks-known-issuesSkill
- aks-network-captureSkill
- aks-troubleshootingSkill
- azure-search-navSkill
- azure-advisor-actionabilitySkill
- azure-advisor-cost-optimizationSkill
- azure-advisorSkill
- cost-analysisSkill
- cost-estimationSkill
- cost-governanceSkill
- cost-optimizationSkill
- azure-kusto-graphSkill
- azure-kusto-irql-graphSkill
- azure-kusto-irqlSkill
- azure-local-multi-rackSkill
- azure-localSkill
- appinsights-instrumentationSkill
- azure-aigatewaySkill
- azure-aiSkill
- azure-app-onboard-prereqSkill
- azure-app-onboardSkill
- azure-cloud-migrateSkill
- azure-complianceSkill
- azure-computeSkill
- azure-deploySkill
- azure-diagnosticsSkill
- azure-enterprise-infra-plannerSkill
- azure-kubernetes-app-deploySkill
- azure-kubernetes-automatic-readinessSkill
- azure-kubernetesSkill
- azure-kustoSkill
- azure-messagingSkill
- azure-prepareSkill
- azure-quotasSkill
- azure-reliabilitySkill
- azure-resource-lookupSkill
- azure-resource-visualizerSkill
- azure-storageSkill
- azure-upgradeSkill
- azure-validateSkill
- discover-azure-skillsSkill
- entra-agent-idSkill
- entra-app-registrationSkill
- finetuningSkill
- capacitySkill
- customizeSkill
- presetSkill
- deploy-modelSkill
- microsoft-foundrySkill
- python-appservice-deploySkill
- foundry-iqSkill
- airunway-aks-setupSkill
- appinsights-instrumentationSkill
- azure-aigatewaySkill
- azure-aiSkill
- azure-app-onboard-prereqSkill
- azure-app-onboardSkill
- azure-cloud-migrateSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
5 rules. 3 are common, 1 is distinctive, and 1 is very specific to this project.
3
Common
Most of the 3 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Common: line 32
Use this skill when the user wants to:
- Distinctive: line 42
Keep initial GPU node-pool, provider, controller, and model setup in this skill.
- Common: line 55
Ask for user confirmation before any install or deployment action
- Common: line 56
If a step is already complete, report status and skip to the next step
- Very specific: line 57
If the user provides skip-to-step N, start at step N.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
AI Runway AKS Setup
This skill walks users from a bare Kubernetes cluster to a running AI model deployment. Follow each step in sequence unless the user provides skip-to-step N to resume from a specific phase.
Cost awareness: GPU node pools incur significant compute charges (A100-80GB can cost $3–5+/hr). Confirm the user understands cost implications before provisioning GPU resources.
Prerequisites
This skill assumes an AKS cluster already exists. If the user does not have a cluster, hand off to the azure-kubernetes skill first to provision one (with a GPU node pool unless CPU-only inference is acceptable), then return here.
Quick Reference
| Property | Value |
| Best for | End-to-end AI Runway onboarding on AKS |
| CLI tools | kubectl, make, curl |
| MCP tools | None |
| Related skills | azure-kubernetes (cluster setup), azure-diagnostics (baseline troubleshooting), optional aks-gpu-inference (existing GPU/inference Day-2 incidents only) |
When to Use This Skill
Use this skill when the user wants to:
- Set up AI Runway on an existing AKS cluster from scratch
- Install the AI Runway controller and CRDs
- Assess GPU hardware compatibility for model deployment
- Choose and install an inference provider (KAITO, Dynamo, KubeRay)
- Deploy their first AI model to AKS via AI Runway
- Resume a partially-complete AI Runway setup from a specific step
GPU setup versus Day-2 incidents
Keep initial GPU node-pool, provider, controller, and model setup in this skill. For an incident affecting an existing GPU or inference deployment, load optional-gpu-day2.md before deciding whether to offer the focused optional add-on.
MCP Tools
This skill uses no MCP tools. All cluster operations are performed directly via kubectl and make.
Rules
- Execute steps in sequence — load the reference for each step as you reach it
- Report cluster state at each step: ✓ healthy, ✗ missing/failed
- Ask for user confirmation before any install or deployment action
- If a step is already complete, report status and skip to the next step
- If the user provides
skip-to-step N, start at step N; assume prior steps are complete
Steps
| # | Step | Reference |
| 1 | Cluster Verification — context check, node inventory, GPU detection | step-1-verify.md |
| 2 | Controller Installation — CRD + controller deployment | step-2-controller.md |
| 3 | GPU Assessment — detect GPU models, flag dtype/attention constraints | step-3-gpu.md |
| 4 | Provider Setup — recommend and install inference provider | step-4-provider.md |
| 5 | First Deployment — pick a model, deploy, verify Ready | step-5-deploy.md |
| 6 | Summary — recap, smoke test, next steps | step-6-summary.md |
Error Handling
| Error / Symptom | Likely Cause | Remediation |
| No kubeconfig context | Not connected to a cluster | Run az aks get-credentials or equivalent |
| Controller in CrashLoopBackOff | Config or RBAC issue | kubectl logs -n airunway-system -l control-plane=controller-manager --previous |
| Provider not ready | Image pull or RBAC issue | kubectl logs <pod-name> -n <namespace> for the provider pod |
| ModelDeployment stuck in Pending | GPU scheduling failure or provider not ready | kubectl describe modeldeployment <name> -n <namespace> events |
bfloat16 errors at inference | T4 or V100 lacks bfloat16 support | Add --dtype float16 to serving args |
For full error handling and rollback procedures, see troubleshooting.md.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

