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, 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

78%

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

Fix and improve this skill with Tessl

tessl review fix ./.github/plugins/azure-skills/skills/azure-compute/SKILL.md

Quality

Content

72%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.

The body is an efficiently written router with clear intent and a well-formed routing table, but it cannot actually execute its own workflow: the workflow files it mandates do not exist in the bundle, and destructive/batch operations lack validation checkpoints.

Suggestions

Include the referenced workflow files (workflows/vm-recommender.md, vm-creator.md, capacity-reservation.md, essential-machine-management.md) in the bundle so the mandatory routing targets resolve.

Add explicit validation/verification checkpoints (e.g. quota check before create, confirm CRG association succeeded) to the create and capacity-reservation workflows to lift the workflow_clarity cap.

Reconcile the 'never route directly to references/*' rule with the bundle, which currently only ships references/ — either ship the workflow wrappers or clarify that references/ files are the workflow entry points.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: no concept explanations, just a purpose line, when-to-use bullets, a disambiguation note, and a routing table, with every token earning its place.	5 / 5
Actionability	Concrete routing table with named workflow files, use-when conditions, and specific tool names (compute_vm_list-skus / images / check-quota) gives mostly executable guidance; minor gaps because actual commands live in the (absent) workflow files rather than inline.	4 / 5
Workflow Clarity	A clear workflow-first sequence (classify → open workflow → load refs → clarify if unclear) is present, but the destructive/batch operations (VM create, CRG associate/disassociate) lack explicit validation or feedback-loop checkpoints, which caps workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	The overview is well-structured and signals one-level-deep references via a clean table, but every linked path (workflows/vm-recommender.md, vm-creator.md, capacity-reservation.md, essential-machine-management.md) does not exist in the bundle — only references/*.md files are present — so navigation is broken despite the good intent.	3 / 5
	Total	15 / 20 Passed

Description

83%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.

The description is a strong, trigger-rich router pitch that clearly states what it does and when to use it, with explicit conflict-avoidance guidance. It is slightly verbose from synonym stacking and could be tightened for token efficiency.

Suggestions

Trim redundant synonym clusters (e.g. 'create / provision / deploy / spin-up') to the most common natural phrasing to reduce padding without losing triggers.

Briefly note the azure-prepare disambiguation boundary directly in the description so conflict risk with the app-deployment sibling skill is resolved without relying on the body.

Dimension	Reasoning	Score
Specificity	Names the Azure VM/VMSS domain and many concrete actions (recommend/compare/price, create/provision/deploy, reserve/guarantee capacity, machine enrollment/monitor), matching the 'several specific actions; minor gaps' anchor rather than 5 due to some redundant synonym padding.	4 / 5
Completeness	Explicitly answers both 'what' ('Azure VM/VMSS router') and 'when' (a concrete 'WHEN:' clause listing trigger phrases), matching the anchor that requires both with concrete triggers.	5 / 5
Trigger Term Quality	Broad natural keyword coverage (VM, scale set, autoscale, burstable, website, GPU, HPC, dev/test, cost estimate) plus tool names, but the list is keyword-stuffed and a few natural user phrasings are missing, placing it just above the 'good coverage' anchor and below 5.	4 / 5
Distinctiveness Conflict Risk	Clear Azure-compute niche with an explicit disambiguation cue ('PREFER OVER mcp__azure__get_azure_bestpractices'), giving minimal conflict risk; not a 5 because related-skill overlap (e.g. azure-prepare) is only resolved in the body, not the description.	4 / 5
	Total	17 / 20 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: 4 missing, 4 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: microsoft/azure-skills
Path: .github/plugins/azure-skills/skills/azure-compute/SKILL.md
Commit: 16dc8c5

Reviewed: about 12 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.