Name: airunway-aks-setup
Rating: 73.6 (1 reviews)
Author: microsoft

airunway-aks-setup

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".

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

The canonical home for this skill is airunway-aks-setup in microsoft/GitHub-Copilot-for-Azure

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-orchestrated overview skill: a clean step table, explicit validation/confirmation gates, and concrete error-handling commands, with detail correctly delegated to one-level-deep references. The only slack is minor redundancy between the Quick Reference table and the MCP Tools section.

Suggestions

Remove the standalone '## MCP Tools' section (or fold it into the Quick Reference table) — it restates 'MCP tools | None' already shown in the table.

Consider inlining one or two of the most critical executable commands (e.g., the controller install make target) into the Steps table so the body is self-sufficient for the first action without needing to open a reference.

Add a brief validation command to the Steps table row for Step 1 (e.g., the kubectl context/node check) so the entry checkpoint is visible without opening the reference.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no explanations of AKS/kubectl), but the standalone 'MCP Tools' section restates the 'MCP tools \| None' row already in the Quick Reference table — a minor instance of over-explanation that could be trimmed.	4 / 5
Actionability	The Error Handling table gives concrete, executable commands ('kubectl logs -n airunway-system ...', '--dtype float16') and the Rules are specific, but the main per-step executable guidance lives in the referenced step files rather than the body itself — mostly executable with minor gaps.	4 / 5
Workflow Clarity	A clear six-step sequence table is paired with explicit validation checkpoints (Rule 2's ✓/✗ status reporting at each step, Rule 3's confirmation gate before installs/deploys) and an error-handling table providing feedback loops for recovery, matching the anchor for clear sequence with explicit validation and feedback.	5 / 5
Progressive Disclosure	The body is a clear overview with a well-signaled steps table pointing to one-level-deep references under references/steps/ (all six step files and troubleshooting.md verified to exist), with detail appropriately split out and easy to navigate.	5 / 5
	Total	18 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-structured description that concisely states the end-to-end purpose and pairs it with a rich set of natural trigger phrases. It is third-person/infinitive in voice and avoids vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'cluster verification, controller install, GPU assessment, provider setup, and first deployment' — giving comprehensive coverage of the setup workflow, matching the anchor for multiple specific concrete actions.	5 / 5
Completeness	It explicitly answers both 'what' ('Set up AI Runway on AKS — from bare cluster to running model') and 'when' (concrete WHEN trigger phrases), matching the anchor for clearly and explicitly answering both with concrete triggers.	5 / 5
Trigger Term Quality	The WHEN clause provides eleven natural trigger phrases including synonyms and tool names a user would actually say ('setup AI Runway', 'KAITO setup on AKS', 'vLLM on AKS', 'run LLM on AKS'), matching the comprehensive-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	'AI Runway on AKS' carves a clear niche with distinct, product-specific triggers (KAITO, vLLM, AI Runway controller), giving minimal conflict risk with adjacent skills like azure-kubernetes.	5 / 5
	Total	20 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 6 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 6 deeper-than-1-level	Warning

	Total	13 / 16 Passed

Repository: microsoft/azure-skills
Path: .github/plugins/azure-skills/skills/airunway-aks-setup/SKILL.md
Commit: 9d46511

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.