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 is strong in trigger term coverage and completeness, with an explicit WHEN clause containing extensive natural keywords. Its main weakness is that the 'what' portion reads more like a list of topic categories than specific concrete actions, and the very broad scope could create overlap with other Azure-related skills. The description is functional and would likely perform well in skill selection despite these minor issues.
Suggestions
Replace category labels with more specific action verbs, e.g., 'Recommends optimal VM sizes, estimates costs, configures autoscale rules, troubleshoots connectivity issues' instead of 'recommendations, pricing, autoscale, connectivity troubleshooting'.
Consider narrowing scope or adding boundary statements to reduce conflict risk with other Azure skills, e.g., 'Does not cover Azure App Service, AKS, or non-VM networking issues'.
| 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 explicitly answers both 'what does this do' (Azure VM and VMSS router for recommendations, pricing, autoscale, etc.) and 'when should Claude use it' with a clear 'WHEN:' clause listing 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 (VMSS, NSG, CRG, port 3389) and natural language terms (recommend, compare, server, website, burstable, black screen, reset password, connect, refused, troubleshoot). The breadth of keyword variations is strong. | 3 / 3 |
Distinctiveness Conflict Risk | While the Azure VM/VMSS focus is fairly specific, the breadth of topics (pricing, autoscale, connectivity troubleshooting, load balancer) could overlap with other Azure-specific skills covering networking, pricing, or load balancing. The term 'router' suggests this dispatches to sub-skills, which helps, but the wide scope increases potential overlap. | 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. Its main weakness is mild redundancy between the ASCII routing tree and the signal-matching table, which convey overlapping information. Overall, it's concise enough, highly actionable for its purpose, and demonstrates excellent progressive disclosure.
Suggestions
Consider consolidating the ASCII routing tree and the signal table into a single representation to reduce redundancy and save tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but has some redundancy — the routing tree and the signal table convey largely the same information. The 'When to Use This Skill' section is somewhat verbose with overlapping trigger phrases. However, it avoids explaining concepts Claude already knows. | 2 / 3 |
Actionability | The routing logic is concrete and unambiguous: given a user intent, Claude knows exactly which workflow file to read and follow. The fallback for unclear intent provides a specific clarifying question. The routing rule about reading the workflow file first is a clear, actionable instruction. | 3 / 3 |
Workflow Clarity | For a routing skill, the workflow is clear and well-sequenced: identify intent → match to workflow → read workflow file before references. The fallback for ambiguous intent is explicit. This is a single-step routing task, and the single action is unambiguous with clear decision criteria. | 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 a summary table mapping workflows to their references. | 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
dd731da
- 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.