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.
94
92%
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 recommendations), specifies the tools it uses (public docs and Azure Retail Prices API), and provides an extensive explicit trigger list covering many natural user phrasings. The description is well-structured with a clear separation between capability description and trigger terms, making it highly effective for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: recommend VM sizes, VM Scale Sets, configurations based on workload requirements, performance needs, and budget constraints. Also specifies it uses public documentation and the Azure Retail Prices API. | 3 / 3 |
Completeness | Clearly answers both 'what' (recommend Azure VM sizes, VMSS, and configurations based on workload/performance/budget) and 'when' with an explicit 'WHEN:' clause listing extensive trigger scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'recommend VM size', 'which VM should I use', 'cheapest VM', 'GPU VM', 'VM pricing', 'cost estimate', 'VMSS vs VM', 'scale out', 'horizontal scaling', plus workload-specific terms like 'web/database/ML/batch/HPC'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — narrowly scoped to Azure VM sizing and VMSS recommendations specifically, with clear domain-specific triggers like 'Azure VM', 'VM families', 'VMSS', 'flexible orchestration' that are unlikely to conflict with other 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-crafted skill with excellent workflow clarity, strong actionability through specific URLs and decision trees, and good progressive disclosure via reference files. The main weakness is moderate verbosity — the 'When to Use' section is redundant with the description, the references are listed twice, and some explanatory text could be trimmed. Overall it's a high-quality skill that effectively guides Claude through a complex multi-step recommendation process.
Suggestions
Remove or consolidate the duplicate references sections (References and Reference Index) into a single table
Remove the 'When to Use This Skill' section since it duplicates the YAML description triggers and Claude can infer applicability from the workflow itself
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some redundancy — the 'When to Use This Skill' section largely duplicates the trigger phrases from the description, the References section is listed twice (once as 'References' and again as 'Reference Index'), and some tables contain information Claude could infer. The 'When to Use This Skill' section and the introductory paragraph restate the same information. | 2 / 3 |
Actionability | The skill provides concrete, executable guidance throughout: specific API URLs for web_fetch, exact URL patterns for documentation lookup, a clear decision tree for VM vs VMSS, specific API query patterns referenced via the retail prices guide, and a well-defined output table format. The fallback behavior when web_fetch fails is explicitly specified. | 3 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced with explicit validation checkpoints — notably the REQUIRED verification steps using web_fetch after initial reference file filtering, fallback warnings when verification fails, and a clear decision tree for VM vs VMSS. Error handling is covered in a dedicated table with specific recovery actions. | 3 / 3 |
Progressive Disclosure | Content is well-structured with a clear overview in SKILL.md and three one-level-deep reference files (vm-families.md, retail-prices-api.md, vmss-guide.md). The Reference Index table with 'When to Load' guidance enables on-demand loading. References are clearly signaled throughout the workflow steps. | 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
- jonathan-vella/azure-agentic-infraops
- Commit
ec7b8ff
- 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.