azure-compute

Azure VM/VMSS router. WHEN: create / provision / deploy / spin-up VM, recommend VM size, compare VM pricing, VMSS, scale set, autoscale, burstable, lightweight server, website, backend, GPU, machine learning, HPC simulation, dev/test, workload, family, load balancer, Flexible orchestration, Uniform orchestration, cost estimate, can't connect / RDP / SSH, refused, black screen, reset password, reach VM, port 3389, NSG, security, Linux, troubleshoot, troubleshooting, connectivity, capacity reservation (CRG), reserve, guarantee capacity, pre-provision, CRG association, CRG disassociation, machine enrollment (EMM), Essential Machine Management, monitor. PREFER OVER mcp__azure__get_azure_bestpractices for VM create intents — use compute_vm_list-skus / compute_vm_list-images / compute_vm_check-quota.

Quality

96%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

92%

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

The content is a well-organized, concise routing overview with concrete disambiguation and a clear routing table. Its main weakness is progressive disclosure: all five referenced workflow files are missing from the bundle, so the skill's primary navigation links do not resolve.

Suggestions

Add the missing workflows/ directory and the five referenced workflow files (vm-recommender.md, vm-creator.md, vm-troubleshooter.md, capacity-reservation.md, essential-machine-management.md) so the routing-table links resolve.

Clarify the relationship between the referenced workflows/ files and the existing references/ files (e.g., note which reference files each workflow loads) to make the one-level-deep navigation explicit.

Reduce duplication of the connection/troubleshooting trigger terms between the frontmatter description and the 'When to Use' body to tighten the token budget.

Dimension	Reasoning	Score
Conciseness	The body is lean — a short intro, tight 'When to Use' bullets, one disambiguation note, and a routing table — and does not explain concepts Claude already knows, matching the score-3 anchor; minor duplication of trigger terms with the frontmatter keeps it from being wasteful but is not significant padding.	3 / 3
Actionability	Concrete and executable for a routing skill: an explicit routing table maps each intent to a specific file, mandates workflow-first routing, gives a vm-creator vs azure-prepare disambiguation rule, and a clarifying-question fallback; absence of code is acceptable for an instruction-only skill per the rubric notes.	3 / 3
Workflow Clarity	The routing sequence is clear — classify intent, open the matched workflow, load only its referenced files — with an explicit 'ask a clarifying question' checkpoint when intent is unclear; no validation feedback loops are needed for a pure router since destructive/batch operations live downstream.	3 / 3
Progressive Disclosure	The overview is well-structured with a clearly signaled one-level routing table, but every workflow link points to a non-existent workflows/ directory — the bundle only contains references/, so the primary navigation paths are broken. This is better than a monolith or deep nesting but worse than the score-3 anchor whose referenced files resolve.	2 / 3
	Total	11 / 12 Passed

Description

100%

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

The description is strong across the board: it states a concrete capability, provides an explicit WHEN clause with extensive natural trigger terms, and disambiguates from a competing tool. It is a clear, well-scoped routing description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions such as 'create / provision / deploy / spin-up VM', 'recommend VM size', 'compare VM pricing', and 'reserve, guarantee capacity' rather than vague language, matching the score-3 anchor.	3 / 3
Completeness	Answers both 'what' ('Azure VM/VMSS router') and 'when' via an explicit 'WHEN:' clause with concrete triggers, matching the score-3 example structure; not score 2 because the when-guidance is explicit rather than implied.	3 / 3
Trigger Term Quality	Broad coverage of natural user phrasings like 'can't connect', 'RDP', 'SSH', 'reset password', 'black screen', and 'create VM'; a few entries are technical jargon, but overall coverage well exceeds the score-2 anchor.	3 / 3
Distinctiveness Conflict Risk	Clear niche (Azure VM/VMSS infrastructure) with distinct triggers and an explicit disambiguation ('PREFER OVER mcp__azure__get_azure_bestpractices for VM create intents'), making it unlikely to trigger the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 5 missing, 5 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: microsoft/azure-skills
Commit: 39464cb

Reviewed: about 5 hours 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.