azure-compute
Recommend Azure VM sizes, VM Scale Sets (VMSS), and configurations based on workload requirements, performance needs, and budget constraints. No Azure account required — uses public documentation and the Azure Retail Prices API. WHEN: recommend VM size, which VM should I use, choose Azure VM, VM for web/database/ML/batch/HPC, GPU VM, compare VM sizes, cheapest VM, best VM for workload, VM pricing, cost estimate, burstable/compute/memory/storage optimized VM, confidential computing, VM trade-offs, VM families, VMSS, scale set recommendation, autoscale VMs, load balanced VMs, VMSS vs VM, scale out, horizontal scaling, flexible orchestration.
Install with Tessl CLI
npx tessl i github:microsoft/github-copilot-for-azure --skill azure-compute93
Does it follow best practices?
Evaluation — 89%
↑ 1.32xAgent success when using this skill
Validation for skill structure
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 an excellent skill description that hits all the key criteria. It provides specific capabilities (VM sizing, VMSS, configurations), clarifies constraints (no Azure account needed), and includes a comprehensive explicit 'WHEN:' clause with extensive natural trigger terms covering various user scenarios from cost optimization to workload-specific recommendations.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Recommend Azure VM sizes, VM Scale Sets (VMSS), and configurations based on workload requirements, performance needs, and budget constraints.' Also specifies data sources used (public documentation and Azure Retail Prices API). | 3 / 3 |
Completeness | Clearly answers both what (recommend Azure VM sizes, VMSS, and configurations based on requirements) and when (explicit 'WHEN:' clause with comprehensive trigger scenarios covering use cases, comparisons, pricing, and scaling needs). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say, including variations like 'recommend VM size', 'which VM should I use', 'cheapest VM', 'GPU VM', 'VM for web/database/ML/batch/HPC', 'VMSS vs VM', 'horizontal scaling', and workload-specific terms like 'burstable/compute/memory/storage optimized VM'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear Azure VM-specific niche. The combination of 'Azure VM', 'VMSS', 'VM families', and Azure-specific terminology makes it unlikely to conflict with other cloud provider skills or general infrastructure skills. | 3 / 3 |
Total | 12 / 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, actionable skill with clear workflows and good progressive disclosure through reference files. The main weakness is moderate verbosity—some content is duplicated (decision tree + table) and basic Azure concepts are over-explained. The explicit verification steps and fallback handling demonstrate strong workflow design.
Suggestions
Consolidate the VM vs VMSS decision tree and the signal/recommendation table—they convey overlapping information and one could be removed
Remove explanatory phrases like 'Built-in autoscale; no custom automation needed' in the table—Claude understands VMSS capabilities
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundant content—the decision tree and table in Step 2 overlap significantly, and some explanations (like what VMSS is) could be trimmed since Claude knows Azure basics. | 2 / 3 |
Actionability | Provides concrete, executable guidance with specific web_fetch commands, exact URL patterns, API query references, and clear output table format. The workflow steps are specific and actionable. | 3 / 3 |
Workflow Clarity | Clear 6-step sequence with explicit validation checkpoints (REQUIRED fetch steps, fallback warnings if fetch fails), decision trees, and error handling table. Includes feedback loops for verification. | 3 / 3 |
Progressive Disclosure | Well-structured overview with clear one-level-deep references to VM Family Guide, Retail Prices API Guide, and VMSS Guide. Content is appropriately split between main skill and reference files. | 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.
- 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.