azure-compute
Azure VM and VMSS router for recommendations, pricing, autoscale, orchestration, and connectivity troubleshooting. WHEN: Azure VM, VMSS, scale set, recommend, compare, server, website, burstable, lightweight, VM family, workload, GPU, learning, simulation, dev/test, backend, autoscale, load balancer, Flexible orchestration, Uniform orchestration, cost estimate, connect, refused, Linux, black screen, reset password, reach VM, port 3389, NSG, troubleshoot.
86
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid skill description with excellent trigger term coverage and clear completeness via the explicit WHEN clause. Its main weaknesses are that the capability descriptions are somewhat high-level (category names rather than specific actions) and the 'router' framing plus some generic terms could create overlap with other Azure-related skills. The extensive keyword list is a strength for discoverability but the core capability statement could be more specific about what concrete actions the skill performs.
Suggestions
Replace high-level category names like 'recommendations' and 'connectivity troubleshooting' with more specific actions, e.g., 'Recommends optimal VM families based on workload type, estimates costs, configures VMSS autoscale rules, and diagnoses VM connectivity issues.'
Clarify the 'router' role—if this skill delegates to sub-skills, state that explicitly so Claude understands this is a dispatch skill rather than a direct executor.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Azure VM and VMSS) and lists several action areas (recommendations, pricing, autoscale, orchestration, connectivity troubleshooting), but these are category-level rather than concrete specific actions like 'compare VM families' or 'configure autoscale rules'. | 2 / 3 |
Completeness | The description clearly answers both 'what' (Azure VM/VMSS router for recommendations, pricing, autoscale, orchestration, and connectivity troubleshooting) and 'when' with an explicit 'WHEN:' clause containing extensive trigger terms. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say, including specific terms like 'burstable', 'GPU', 'port 3389', 'NSG', 'black screen', 'reset password', 'load balancer', 'scale set', and various workload types. These are highly natural and cover many common user query variations. | 3 / 3 |
Distinctiveness Conflict Risk | While the Azure VM/VMSS focus is fairly specific, the description is labeled as a 'router' which suggests it's a meta-skill, and some terms like 'recommend', 'compare', 'cost estimate', 'troubleshoot' are quite generic and could overlap with other Azure or cloud infrastructure skills. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured routing skill that efficiently dispatches Azure VM requests to appropriate downstream workflows. Its strengths are excellent organization, clear decision logic with a disambiguation fallback, and proper progressive disclosure to workflow and reference files. The only minor weakness is that as a pure router, it contains no executable code or commands itself, though this is appropriate for its purpose.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It avoids explaining what VMs or VMSS are, assumes Claude's competence, and every section serves a clear routing purpose without unnecessary padding. | 3 / 3 |
Actionability | The routing logic is concrete with clear signal-to-workflow mappings and a decision tree, but the skill itself contains no executable code or commands—it's purely a routing/dispatch skill. The guidance is specific enough to act on but relies entirely on downstream workflow files for actual instructions. | 2 / 3 |
Workflow Clarity | For a routing skill, the workflow is unambiguous: a clear decision tree with three branches (recommend, troubleshoot, unclear) plus a signal-mapping table. The 'unclear' branch includes a specific disambiguation question, which serves as a validation checkpoint for intent classification. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure. The SKILL.md serves as a concise overview/router with well-signaled one-level-deep references to workflow files and reference documents. Navigation is clear via both the decision tree and the summary table. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- microsoft/github-copilot-for-azure
- Commit
a46a937
- Reviewed
Table of Contents
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.