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)
Install with Tessl CLI
npx tessl i github:microsoft/github-copilot-for-azure --skill azure-cost-optimization94
Does it follow best practices?
Evaluation — 94%
↑ 1.88xAgent success when using this skill
Validation for skill structure
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 exemplary skill description that excels across all dimensions. It provides specific concrete actions, comprehensive natural trigger terms, explicit guidance on both when to use and when NOT to use the skill, and clear differentiation from related Azure skills. The 'DO NOT USE FOR' section is particularly valuable for preventing skill selection conflicts.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'analyzing actual costs', 'utilization metrics', 'generating actionable optimization recommendations', 'find orphaned resources', 'rightsize VMs'. These are concrete, measurable activities. | 3 / 3 |
Completeness | Clearly answers both what (identify and quantify cost savings, analyze costs/utilization, generate recommendations) AND when (explicit 'USE FOR:' clause with comprehensive trigger scenarios). Also includes helpful 'DO NOT USE FOR:' guidance. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'optimize Azure costs', 'reduce Azure spending', 'find cost savings', 'find unused resources', 'reduce waste', 'cost analysis'. These match how users naturally phrase cost optimization requests. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear Azure cost-specific niche. The explicit 'DO NOT USE FOR:' section proactively prevents conflicts with azure-deploy, azure-diagnostics, and azure-security skills, making selection unambiguous. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%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, highly actionable skill for Azure cost optimization with clear workflows and good progressive disclosure. The main weakness is moderate verbosity - some explanatory notes and repeated guidance could be trimmed. The skill excels at providing executable commands, proper validation checkpoints, and clear output specifications.
Suggestions
Consolidate the 'Important Notes' and 'Common Pitfalls' sections - some content overlaps with inline guidance already provided in the steps
Remove explanatory phrases like 'immediate cost savings' after 'orphaned resources' - Claude understands these concepts
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary explanations (e.g., explaining what orphaned resources are, verbose notes sections). Some sections like the report structure template could be more concise, and there's repetition between steps and notes. | 2 / 3 |
Actionability | Provides fully executable PowerShell commands, complete JSON templates for cost queries, specific MCP tool calls, and copy-paste ready code blocks. Commands include actual parameter placeholders and clear instructions for execution. | 3 / 3 |
Workflow Clarity | Clear 9-step sequential workflow with explicit validation checkpoints (Step 0 prerequisites, Step 8 audit trail). Includes conditional branching for Redis-specific analysis, feedback loops for cost query validation, and explicit cleanup step at the end. | 3 / 3 |
Progressive Disclosure | Well-structured with clear overview and appropriately signaled one-level-deep references (azure-redis.md, azure-quick-review.md, azure-resource-graph.md, SDK references). Report templates are linked separately, and content is appropriately split between main skill and reference documents. | 3 / 3 |
Total | 11 / 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.
Table of Contents
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.