azure-defaults
**UTILITY SKILL** — Azure infrastructure defaults: regions, tags, naming (CAF), AVM-first policy, security baseline, unique suffix patterns. WHEN: "Azure naming convention", "CAF naming", "resource tags", "AVM module", "security baseline", "region default". 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).
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 follows best practices across all dimensions. It uses third person voice, provides specific capabilities, includes explicit trigger terms in a WHEN clause, and even includes a DO NOT USE FOR section to prevent conflicts with related skills. The description is concise yet comprehensive, making it easy for Claude to select appropriately from a large skill set.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete capabilities: regions, tags, naming (CAF), AVM-first policy, security baseline, unique suffix patterns. These are distinct, actionable areas rather than vague abstractions. | 3 / 3 |
Completeness | Clearly answers both 'what' (Azure infrastructure defaults covering regions, tags, naming, AVM policy, security baseline) and 'when' (explicit WHEN clause with trigger terms, USE FOR clause, and even a DO NOT USE FOR clause to reduce false matches). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'Azure naming convention', 'CAF naming', 'resource tags', 'AVM module', 'security baseline', 'region default'. These are terms Azure practitioners naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche (Azure infrastructure defaults/conventions). The DO NOT USE FOR clause explicitly disambiguates from related skills like azure-artifacts and pricing guidance, significantly reducing conflict risk. | 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 Azure defaults skill with strong progressive disclosure and workflow clarity. Its main weakness is moderate redundancy across sections (rules restated in multiple places) and limited executable code examples — most actionable guidance is deferred to reference files. The skill excels as a navigational hub but could be more directly actionable for common operations.
Suggestions
Add 1-2 more executable code snippets in Quick Reference (e.g., a complete Bicep/Terraform tag block applying all 4 required tags, or a security baseline storage account config) to improve actionability.
Consolidate the AVM-first rule and tag casing warning — each appears in 2-3 places; state once definitively in Rules and reference that section elsewhere to reduce token usage.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good use of tables and concise summaries, but some sections (VNet Planning Baseline, Cost Monitoring Baseline) are dense prose blocks that could be tightened. The repeated restatement of rules already covered in Quick Reference (e.g., AVM-first appears in Quick Reference, AVM section, Rules, and Steps) adds redundancy. | 2 / 3 |
Actionability | Provides concrete naming patterns, tag requirements, and one executable Bicep snippet (uniqueSuffix), but most guidance is declarative rather than executable. The AVM section says 'ALWAYS check AVM availability first' without showing how, and security baseline values are listed without showing how to apply them in code. Key actions defer to reference files. | 2 / 3 |
Workflow Clarity | The Steps section provides a clear 8-step sequence with explicit validation at step 8 (lint/validate commands), cross-check governance at step 2, and conditional gates (VNet planning at step 6). The workflow includes feedback loops via governance overrides and the VNet interactive confirmation requirement. The Output Rules checklist adds a pre-save verification step. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear Quick Reference for immediate use, well-organized sections, and a comprehensive Reference Index table with explicit 'When to Load' guidance. References are one level deep and clearly signaled throughout the document with inline links to specific reference files. | 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.