azure-compute
Azure VM and VMSS router for recommendations, pricing, autoscale, orchestration, connectivity troubleshooting, capacity reservations, and Essential Machine Management. 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, essential machine management, EMM, machine enrollment.
68
83%
Does it follow best practices?
Impact
—
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 description has strong trigger term coverage and good completeness with an explicit WHEN clause, making it easy for Claude to know when to select it. However, the 'what' portion reads more like a list of topic categories than concrete actions, and the extremely broad scope within Azure VM/VMSS could create overlap with more specialized skills. The description would benefit from slightly more specific action verbs and tighter scoping of generic terms.
Suggestions
Replace category labels with concrete action verbs (e.g., instead of 'recommendations' say 'Recommends VM families based on workload requirements'; instead of 'connectivity troubleshooting' say 'Diagnoses VM connectivity issues including NSG rules and port access')
Consider narrowing or qualifying generic trigger terms like 'server', 'website', 'backend', and 'Linux' to reduce conflict risk with other infrastructure-related skills (e.g., 'Azure Linux VM' instead of just 'Linux')
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Azure VM and VMSS) and lists several action areas (recommendations, pricing, autoscale, orchestration, connectivity troubleshooting, capacity reservations, EMM), but these are category labels rather than concrete specific actions like 'extract text' or 'fill forms'. It tells you the topics but not exactly what it does with them. | 2 / 3 |
Completeness | The description clearly answers both 'what does this do' (Azure VM/VMSS routing for recommendations, pricing, autoscale, etc.) and 'when should Claude use it' with an explicit 'WHEN:' clause containing extensive trigger terms. Both components are present and explicit. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say, including both technical terms (NSG, port 3389, CRG, VMSS) and natural language phrases (black screen, reset password, reach VM, connect refused, recommend, compare, lightweight, burstable). The breadth of keyword variations is strong. | 3 / 3 |
Distinctiveness Conflict Risk | While the Azure VM/VMSS focus is fairly specific, the description is extremely broad within that domain—covering recommendations, pricing, autoscale, troubleshooting, capacity reservations, and machine management. Some terms like 'server', 'website', 'backend', 'load balancer', 'Linux' are generic enough to potentially conflict with other Azure or 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 clearly maps user intents to specific workflow files with good progressive disclosure. Its main weakness is redundancy — the routing logic is expressed three times (ASCII tree, signal table, workflows table) which inflates token usage without adding clarity. The actionability and workflow clarity are strong for a routing-type skill.
Suggestions
Consolidate the routing information into a single representation (e.g., just the signal table with the fallback note) instead of repeating it across the ASCII tree, signal table, and workflows table to improve token efficiency.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient as a routing document, but there is redundancy between the ASCII tree, the signal table, and the workflows table — all three convey largely the same routing information. The 'When to Use This Skill' section is also somewhat verbose with overlapping trigger descriptions. | 2 / 3 |
Actionability | For a routing skill, this is highly actionable: it provides clear signal-to-workflow mappings, specific file paths to follow, and an explicit fallback question for ambiguous intent. The routing rule about reading the workflow file first is a concrete, specific instruction. | 3 / 3 |
Workflow Clarity | The routing workflow is unambiguous with a clear decision tree, a signal-matching table, and an explicit fallback for unclear intent. The routing rule ('Always read the matched workflow file before accessing any reference files') provides a clear sequencing instruction. For a routing skill (not a destructive/batch operation), this is sufficient. | 3 / 3 |
Progressive Disclosure | The skill is an excellent example of progressive disclosure: it serves as a concise overview/router that points to one-level-deep workflow files, each with their own reference files clearly listed. Navigation is well-signaled with both inline links and a 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/azure-skills
- Commit
d02fd24
- 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.