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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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

The body is a tight, well-organized routing skill with a clear decision tree and routing rule, but its progressive-disclosure structure is undermined by five broken workflow-file links and four unreferenced reference files. Actionability suffers because the cited workflow files cannot be read.

Suggestions

Either include the five referenced `workflows/*.md` files in the bundle or replace the dead links with links to the existing `references/` files (e.g. `references/vm-families.md`, `references/vmss-guide.md`).

Add a navigation line linking the real reference files (vm-families, vmss-guide, vm-quotas, retail-prices-api) so the on-demand lookup the routing rule describes actually has a target.

Confirm the workflow file paths match the bundle layout exactly (the body uses `workflows/<name>/<name>.md` but no `workflows/` directory exists).

Dimension	Reasoning	Score
Conciseness	The body is lean: a routing overview, a compact decision tree, and a one-line routing rule, with no explanation of concepts Claude already knows, matching the 'lean and efficient; every token earns its place' anchor.	3 / 3
Actionability	Routing guidance is concrete (named workflow files, an explicit disambiguation rule), but the five referenced `workflows/*.md` files do not exist in the bundle, so the core 'read the workflow file' action cannot actually be executed — incomplete rather than fully copy-paste ready.	2 / 3
Workflow Clarity	The routing decision tree sequences intents clearly and the routing rule ('read the matched workflow file before any reference file') gives an explicit order; no destructive/batch operations are involved, so the missing-validation cap at 2 does not apply.	3 / 3
Progressive Disclosure	The overview is well-structured as a one-level-deep pointer to separate workflow files, but those referenced paths are broken (the files are absent) and the four real `references/*.md` files are never linked from the body, so navigation does not actually resolve.	2 / 3
	Total	10 / 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 highly specific, covers natural trigger terms comprehensively, answers both what and when explicitly, and carves out a clear non-conflicting niche. It is third-person and free of vague fluff, though the keyword list is long.

Dimension	Reasoning	Score
Specificity	Names the domain (Azure VM/VMSS) and lists many concrete actions such as 'recommend VM size', 'compare VM pricing', 'create / provision / deploy', 'reset password', and 'CRG association / disassociation', matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly states both what ('Azure VM/VMSS router') and when (an explicit 'WHEN:' clause enumerating triggers), matching the 'clearly answers both what AND when' anchor; the missing-trigger cap at 2 does not apply.	3 / 3
Trigger Term Quality	Strong natural-term coverage a user would actually say — 'can't connect', 'RDP / SSH', 'port refused', 'black screen', 'website', 'backend', 'dev/test' — matching the 'good coverage of natural terms' anchor.	3 / 3
Distinctiveness Conflict Risk	Clear niche (bare VM/VMSS infrastructure) with distinct triggers and explicit disambiguation ('PREFER OVER mcp__azure__get_azure_bestpractices'), making wrong-skill triggering unlikely.	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: 2cd48ca

Reviewed: about 8 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.