azure-cost-optimization

Identify and quantify cost savings across Azure subscriptions by analyzing actual costs, utilization metrics, and generating actionable optimization recommendations. USE FOR: optimize Azure costs, reduce Azure spending, reduce Azure expenses, analyze Azure costs, find cost savings, generate cost optimization report, find orphaned resources, rightsize VMs, cost analysis, reduce waste, Azure spending analysis, find unused resources, optimize Redis costs. DO NOT USE FOR: deploying resources (use azure-deploy), general Azure diagnostics (use azure-diagnostics), security issues (use azure-security)

Quality

78%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.github/skills/azure-cost-optimization/SKILL.md

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 covers all key dimensions thoroughly. It provides specific concrete actions, comprehensive natural trigger terms, explicit 'USE FOR' and 'DO NOT USE FOR' clauses, and clear differentiation from related Azure skills. The description is well-structured and would enable Claude to reliably select this skill for cost optimization tasks while avoiding false triggers.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'analyzing actual costs', 'utilization metrics', 'generating actionable optimization recommendations', 'find orphaned resources', 'rightsize VMs', 'optimize Redis costs'. These are concrete, specific capabilities.	3 / 3
Completeness	Clearly answers both 'what' (identify and quantify cost savings by analyzing costs, utilization metrics, generating recommendations) and 'when' (explicit USE FOR clause with extensive trigger scenarios, plus DO NOT USE FOR to prevent misuse).	3 / 3
Trigger Term Quality	Excellent coverage of natural terms users would say: 'optimize Azure costs', 'reduce Azure spending', 'find cost savings', 'find orphaned resources', 'rightsize VMs', 'find unused resources', 'reduce waste'. These are highly natural phrases a user would actually type.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with a clear niche (Azure cost optimization) and explicitly differentiates from related skills via DO NOT USE FOR clauses referencing azure-deploy, azure-diagnostics, and azure-security, minimizing conflict risk.	3 / 3
	Total	12 / 12 Passed

Implementation

57%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill demonstrates strong progressive disclosure and organization, effectively splitting content across reference files with clear navigation. However, it suffers from delegating too much critical workflow content (Steps 4-9) to external files without any inline summary, leaving the main document incomplete for understanding the full process. The Redis-specific conditional sections add verbosity that could be more concisely handled with a simple reference pointer.

Suggestions

Add a brief one-line summary for each of Steps 4-9 in the main document before pointing to the reference file, so the full workflow is understandable without loading the reference (e.g., 'Step 4: Execute cost queries using Cost Management API', 'Step 5: Validate pricing against Azure pricing calculator').

Add explicit validation checkpoints in the workflow, such as verifying azqr output before proceeding to resource discovery, or confirming cost query results before generating recommendations.

Condense Steps 1.5 and 1.6 into a single brief conditional note (e.g., 'For Redis-specific analysis, see [Azure Redis Cost Optimization](./references/azure-redis.md) instead of continuing with Step 2') rather than dedicating two full steps to the conditional branch.

Dimension	Reasoning	Score
Conciseness	The skill has some unnecessary verbosity, particularly in the Redis-specific sections (Steps 1.5 and 1.6) which are quite detailed for a conditional branch. The 'When to Use This Skill' section repeats information likely already in the YAML frontmatter. However, the reference index and progressive disclosure approach help keep the main document from being overly bloated.	2 / 3
Actionability	The skill provides some concrete commands (az CLI, MCP tool calls) but Steps 4-9 are entirely delegated to a reference file with no inline summary of what they entail. The MCP tool call examples use JavaScript-like pseudocode syntax that isn't clearly executable. Key details like how to interpret azqr results or what specific cost queries to run are missing from the main document.	2 / 3
Workflow Clarity	The steps are numbered and sequenced, but Steps 4-9 are completely opaque — delegated to a reference file without even a brief summary of what each step does. There are no explicit validation checkpoints or feedback loops for error recovery. For a multi-step workflow involving cost analysis and potentially destructive recommendations, the lack of validation steps in the main document is a gap.	2 / 3
Progressive Disclosure	The skill excels at progressive disclosure with a clear reference index table, well-signaled one-level-deep references, conditional loading instructions ('Load these on demand — do NOT read all at once'), and appropriate splitting of detailed content into reference files. Navigation is clear with both inline links and the summary table.	3 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

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: 7 days ago

Table of Contents

Discovery Implementation Validation

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.