az-cost-optimize
Analyze Azure resources used in the app (IaC files and/or resources in a target rg) and optimize costs - creating GitHub issues for identified optimizations.
72
56%
Does it follow best practices?
Impact
79%
2.02xAverage score across 6 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/az-cost-optimize/SKILL.mdQuality
Discovery
57%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description identifies a clear and distinctive niche (Azure cost optimization with GitHub issue creation) but falls short on completeness by lacking an explicit 'Use when...' trigger clause. Trigger terms cover the core domain but miss common user language variations for cloud cost management and specific IaC tool names.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about reducing Azure costs, optimizing cloud spending, or reviewing Azure resource usage.'
Include common trigger term variations such as 'cloud spending', 'reduce costs', 'Terraform', 'Bicep', 'ARM templates', and 'Azure billing' to improve keyword coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Azure resources, cost optimization) and some actions (analyze, optimize costs, create GitHub issues), but lacks detail on specific analysis techniques or types of optimizations performed. | 2 / 3 |
Completeness | Describes what it does (analyze Azure resources and optimize costs, create GitHub issues) but lacks an explicit 'Use when...' clause specifying when Claude should select this skill. The 'when' is only implied. | 2 / 3 |
Trigger Term Quality | Includes relevant terms like 'Azure resources', 'IaC files', 'cost', 'optimize', 'GitHub issues', and 'rg' (resource group), but misses common user variations like 'cloud spending', 'reduce costs', 'Terraform', 'Bicep', 'ARM templates', or 'budget'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of Azure resource analysis, cost optimization, and GitHub issue creation is a very specific niche that is unlikely to conflict with other skills. The scope is clearly defined around Azure cost optimization workflows. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with a well-structured multi-step workflow, concrete tool invocations, and proper validation checkpoints including user confirmation. However, it is severely over-engineered in terms of token efficiency—full issue body templates, KQL queries, optimization pattern catalogs, and mermaid diagram templates are all inlined when they could be referenced externally or generated by Claude from brief instructions. The monolithic structure significantly hurts both conciseness and progressive disclosure.
Suggestions
Extract the GitHub issue body templates (Steps 6 and 7) into separate reference files (e.g., ISSUE_TEMPLATE.md, EPIC_TEMPLATE.md) and reference them from the main skill with one-line links.
Remove the optimization patterns catalog in Step 4 (Compute/Database/Storage/Infrastructure) — Claude already knows Azure cost optimization patterns. Replace with a brief instruction like 'Apply standard Azure cost optimization patterns for each discovered resource type.'
Move the KQL queries into a separate QUERIES.md reference file, keeping only a brief mention that predefined queries are available.
Reduce the user confirmation display template to a brief description of what to show rather than a full ASCII mockup — Claude can format summaries without a detailed template.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~250+ lines with significant redundancy. Templates are shown in full with placeholder text that Claude could generate itself. The optimization patterns section explains basic Azure concepts (e.g., 'Right-size based on CPU/memory usage') that Claude already knows. The emoji-heavy formatting and repeated template structures add substantial token overhead without proportional value. | 1 / 3 |
Actionability | The skill provides specific, executable commands throughout: concrete Azure MCP tool invocations with parameters, KQL queries for monitoring, Azure CLI fallback commands, and detailed issue templates with exact title formats and body structures. The priority scoring formula is concrete and calculable. | 3 / 3 |
Workflow Clarity | The 7-step workflow is clearly sequenced with explicit validation checkpoints: Step 4 includes 'Validate Recommendations', Step 5 requires user confirmation before proceeding, Step 6 issue templates include validation checklists, and the error handling section covers failure modes. The feedback loop of cost validation before issue creation is well-defined. | 3 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of text with no references to external files. The detailed issue templates, KQL queries, optimization patterns, and mermaid diagram templates could all be split into separate reference files. Everything is inlined, making the skill extremely long and difficult to navigate. | 1 / 3 |
Total | 8 / 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
- github/awesome-copilot
- Commit
63d08d5
- 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.