azure-compute
Azure VM and VMSS router for recommendations, pricing, autoscale, orchestration, connectivity troubleshooting, and capacity reservations. 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, capacity reservation, CRG, reserve VMs, guarantee capacity, pre-provision capacity, CRG association, CRG disassociation.
88
85%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is a strong skill description that clearly defines its scope (Azure VM and VMSS operations), lists specific capabilities, and provides an extensive explicit 'WHEN' clause with natural trigger terms. The description is well-structured with a concise 'what' statement followed by comprehensive trigger keywords covering recommendations, troubleshooting, autoscaling, and capacity reservations. Minor improvement could be made by slightly organizing the trigger terms into logical groupings for readability, but functionally it is excellent.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists multiple specific concrete actions: recommendations, pricing, autoscale, orchestration, connectivity troubleshooting, and capacity reservations. These are distinct, well-defined capabilities within the Azure VM/VMSS domain. | 3 / 3 |
Completeness | Clearly answers both 'what' (Azure VM and VMSS router for recommendations, pricing, autoscale, orchestration, connectivity troubleshooting, and capacity reservations) and 'when' with an explicit 'WHEN:' clause containing extensive trigger terms. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say, including common variations like 'scale set', 'VMSS', 'burstable', 'GPU', 'black screen', 'reset password', 'port 3389', 'NSG', 'connect', 'refused', 'CRG'. These are highly natural keywords spanning multiple user intent patterns. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche focused on Azure VM and VMSS specifically. The trigger terms are domain-specific (port 3389, NSG, CRG, VMSS, Flexible/Uniform orchestration) and unlikely to conflict with non-Azure or non-VM skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
70%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 clearly directs users to the appropriate workflow based on intent. Its main weakness is redundancy — the routing logic is expressed in three overlapping formats (ASCII tree, signal table, workflows table), which wastes tokens. The skill lacks any executable content itself, functioning purely as a dispatcher, which limits its standalone actionability.
Suggestions
Consolidate the routing information into a single representation (e.g., just the signal table with the fallback note) instead of repeating it three times in different formats.
Trim the 'When to Use This Skill' section since it largely duplicates the YAML frontmatter description and the signal table keywords.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but has some redundancy — the routing logic is expressed three times (ASCII tree, signal table, and workflows table) conveying overlapping information. The 'When to Use This Skill' section is somewhat verbose with trigger keywords that overlap with the YAML description. | 2 / 3 |
Actionability | The skill provides clear routing logic with specific file paths, but it is purely a router — it contains no executable code, commands, or concrete examples. The actionability depends entirely on the referenced workflow files, which are not provided. The routing instructions themselves are concrete enough to follow. | 2 / 3 |
Workflow Clarity | For a routing skill, the workflow is clear and unambiguous: identify user intent → match to workflow → read workflow file before references. The fallback for unclear intent is explicitly defined ('Ask: Are you looking for...'). The routing rule about reading the workflow file first is a useful checkpoint. | 3 / 3 |
Progressive Disclosure | The skill is well-structured as a top-level router with clear one-level-deep references to workflow files and their associated reference files. Navigation is easy with the workflows table showing purpose and references for each path. Content is appropriately split across files. | 3 / 3 |
Total | 10 / 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
771a666
- 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.