azure-compute
**ANALYSIS SKILL** — Recommend Azure VM sizes and VMSS for workload, performance, and budget. Uses public docs and the Azure Retail Prices API. WHEN: "recommend VM size", "choose Azure VM", "GPU VM", "compare VM sizes", "VMSS vs VM", "autoscale VMs". DO NOT USE FOR: provisioning VMs (azure-prepare), VM pricing for budgets (azure-pricing MCP).
70
85%
Does it follow best practices?
Impact
—
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 an excellent skill description that hits all the marks. It provides specific capabilities, rich natural trigger terms, explicit when/when-not guidance, and clear boundaries against related skills. The 'DO NOT USE FOR' clause is a particularly strong differentiator that reduces conflict risk.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists concrete actions: recommend VM sizes, recommend VMSS, compare VM sizes, and specifies tools used (public docs, Azure Retail Prices API). Also distinguishes from related but different tasks (provisioning, pricing for budgets). | 3 / 3 |
Completeness | Clearly answers 'what' (recommend Azure VM sizes and VMSS for workload/performance/budget using public docs and API) and 'when' (explicit WHEN clause with trigger phrases). Also includes a 'DO NOT USE FOR' clause that further clarifies boundaries. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'recommend VM size', 'choose Azure VM', 'GPU VM', 'compare VM sizes', 'VMSS vs VM', 'autoscale VMs'. These are realistic phrases a user would type when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit boundary-setting via the 'DO NOT USE FOR' clause, naming specific other skills (azure-prepare, azure-pricing MCP) to avoid conflicts. The niche of VM size recommendation is clearly carved out from provisioning and budget pricing. | 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 skill with excellent progressive disclosure and workflow clarity. Its main weakness is that the SKILL.md itself lacks concrete, executable examples (API queries, web_fetch calls, sample output formats) — all actionable detail is deferred to reference files that weren't provided for evaluation. There's also moderate redundancy between the References section and Reference Index table, and the 'When to Use' list could be trimmed.
Suggestions
Add at least one concrete, executable example inline — e.g., a sample Retail Prices API curl/web_fetch call with expected output format — so the skill is partially actionable without loading references.
Consolidate the 'References' section and 'Reference Index' table into a single table to eliminate duplication and save tokens.
Trim the 'When to Use This Skill' list to 3-4 items since the detailed triggers are already in the description/frontmatter.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but has some redundancy — the 'When to Use This Skill' section repeats what the description already covers, the References section and Reference Index table duplicate the same information, and some rules restate what's in the steps. Could be tightened by ~30%. | 2 / 3 |
Actionability | Provides a clear workflow summary and error handling table, but the actual executable details (API query patterns, web_fetch URLs, decision tables) are all deferred to reference files. The SKILL.md itself contains no concrete code, API calls, or copy-paste-ready examples — it's a well-structured overview but not directly actionable on its own. | 2 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced with a logical progression from requirements gathering through recommendation to next steps. Validation is addressed via the 'always verify against live docs via web_fetch' checkpoint, and error handling covers key failure scenarios with specific recovery actions including a feedback loop for broadening API filters. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure — the SKILL.md provides a concise overview with clearly signaled one-level-deep references to four specific files, each mapped to a specific step. The Reference Index table with 'When to Load' guidance is particularly well done, and the explicit instruction to load on demand prevents unnecessary context consumption. | 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
- jonathan-vella/azure-agentic-infraops
- Commit
05d7617
- 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.