azure-cost-optimization
**ANALYSIS SKILL** — Identify cost savings across Azure subscriptions via cost + utilization analysis. WHEN: "optimize Azure costs", "reduce Azure spending", "find cost savings", "rightsize VMs", "find orphaned resources", "optimize Redis costs". DO NOT USE FOR: deploying (azure-deploy), general diagnostics (azure-diagnostics), security issues (azure-compliance).
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 feature for reducing conflict risk in a multi-skill environment.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: 'Identify cost savings across Azure subscriptions via cost + utilization analysis' and includes specific examples like 'rightsize VMs', 'find orphaned resources', 'optimize Redis costs'. | 3 / 3 |
Completeness | Clearly answers both 'what' (identify cost savings via cost + utilization analysis) and 'when' (explicit WHEN clause with trigger phrases). Also includes a 'DO NOT USE FOR' section that further clarifies boundaries, which is excellent for disambiguation. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'optimize Azure costs', 'reduce Azure spending', 'find cost savings', 'rightsize VMs', 'find orphaned resources', 'optimize Redis costs' — these are all phrases a user would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit boundary-setting via the 'DO NOT USE FOR' clause that names competing skills (azure-deploy, azure-diagnostics, azure-compliance), making it very unlikely to conflict with other Azure-related skills. | 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 that excels at progressive disclosure and workflow clarity, with clear sequencing, safety constraints, and a well-organized reference architecture. Its main weakness is that the SKILL.md itself lacks concrete executable examples — all actionable content is deferred to reference files that weren't provided for evaluation. There is also moderate redundancy around Redis-specific scoping that could be consolidated.
Suggestions
Add at least one concrete executable command example in the SKILL.md itself (e.g., the prerequisite validation commands or a sample cost query) so the skill is partially actionable without loading references.
Consolidate Redis-specific mentions — the branching rule, the Rules bullet, and the Instructions table row all say the same thing; a single clear callout would suffice.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but has some redundancy — Redis-specific scope is mentioned in multiple places (Rules, Instructions table, branching rule callout, Reference Index), and the 'When to Use This Skill' section largely duplicates what the YAML description already conveys. Some tightening is possible. | 2 / 3 |
Actionability | The skill provides a clear workflow table and references to detailed steps, but the SKILL.md itself contains no executable commands or concrete code examples — all actionable content is deferred to reference files. The instructions section is essentially a table of pointers rather than concrete guidance. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced with numbered steps, a branching rule for Redis-specific analysis, explicit prerequisite validation (Step 0), and a read-only-first safety constraint before any remediation. The classification system (Safe/Review/Risky) and audit trail requirements serve as validation checkpoints. The separation of assessment from remediation is a clear feedback loop for destructive operations. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear overview in SKILL.md, a well-organized reference index table with explicit 'When to Load' guidance, and one-level-deep references to specific workflow steps, tools, and domain-specific guides. The 'Load these on demand — do NOT read all at once' instruction is particularly good. | 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.