azure-defaults
Azure infrastructure defaults: regions, tags, naming (CAF), AVM-first policy, security baseline, unique suffix patterns. USE FOR: any agent generating or planning Azure resources. DO NOT USE FOR: artifact template structures (use azure-artifacts), pricing lookups (read references/pricing-guidance.md on demand).
89
86%
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 concisely communicates specific Azure infrastructure capabilities, includes clear trigger conditions with both positive and negative use cases, and uses natural domain terminology. The explicit 'USE FOR' and 'DO NOT USE FOR' clauses are excellent for disambiguation. The description uses appropriate third-person/imperative voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete capabilities: regions, tags, naming (CAF), AVM-first policy, security baseline, unique suffix patterns. These are concrete, domain-specific actions/concepts rather than vague language. | 3 / 3 |
Completeness | Clearly answers both what (Azure infrastructure defaults covering regions, tags, naming, AVM-first policy, security baseline, suffix patterns) and when ('USE FOR: any agent generating or planning Azure resources'). Also includes explicit negative triggers ('DO NOT USE FOR') which further clarifies scope. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Azure infrastructure', 'regions', 'tags', 'naming', 'CAF', 'AVM', 'security baseline', 'Azure resources'. These are terms an engineer would naturally use when planning Azure deployments. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit boundary-setting via 'DO NOT USE FOR' clauses that differentiate it from the azure-artifacts skill and pricing guidance. The focus on infrastructure defaults/conventions creates a clear niche distinct from template structures or pricing. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%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 Azure defaults reference skill that excels at progressive disclosure and actionability, providing concrete values, patterns, and code snippets in compact table format. Its main weaknesses are some content redundancy (tag casing warning and deprecated services guidance repeated) and a workflow that reads more as a checklist than a sequenced process with error recovery. The skill effectively serves as a quick-lookup reference for Azure resource generation.
Suggestions
Remove the duplicate tag casing warning and deprecated services guidance from the Gotchas section since they already appear in Quick Reference — or consolidate Gotchas into a single location.
Add a brief error-recovery step to the Validation Checklist (e.g., 'If any check fails, fix the issue and re-run validation before proceeding to deployment').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of tables, but has some redundancy — the tag casing warning appears twice (in Required Tags section and again in Gotchas), and the deprecated services guidance is also repeated. The 'Template-First Output Rules' section feels like it belongs in a separate artifact/template skill rather than Azure defaults. | 2 / 3 |
Actionability | Provides concrete, copy-paste-ready patterns: exact Bicep code for unique suffix, specific naming patterns with abbreviations and max lengths, exact tag names with casing rules, specific region values, and precise security settings. The tables serve as directly actionable lookup references. | 3 / 3 |
Workflow Clarity | The validation checklist at the end provides checkpoints, and the AVM-first rule gives clear sequencing (check AVM → use AVM → never write raw). However, there's no explicit workflow sequence tying these pieces together — it's more of a reference document than a step-by-step process. The checklist lacks a feedback loop (what to do if validation fails). | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear Reference Index table that specifies exactly when to load each reference file. The main skill contains concise summaries with explicit pointers to deeper content (e.g., 'read references/security-baseline-full.md'). All references are one level deep and clearly signaled. | 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
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.