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 communicates a clear niche (Azure cost optimization with GitHub issue creation) and is reasonably specific about its domain, giving it good distinctiveness. However, it lacks an explicit 'Use when...' clause and could benefit from more natural trigger terms that users would actually say when seeking cost optimization help. The description is functional but not fully optimized for skill selection.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to reduce Azure cloud costs, analyze resource spending, or review infrastructure-as-code for cost savings.'
Include more natural trigger term variations such as 'cloud costs', 'Azure spending', 'Terraform', 'Bicep', 'ARM templates', 'cost reduction', 'resource group optimization', and 'Azure billing'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Azure resources, cost optimization) and some actions (analyze, optimize costs, create GitHub issues), but doesn't list multiple concrete specific actions beyond the high-level workflow. Terms like 'IaC files' and 'resources in a target rg' add some specificity but remain somewhat vague about what analysis entails. | 2 / 3 |
Completeness | The 'what' is reasonably covered (analyze Azure resources, optimize costs, create GitHub issues), but there is no explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied by the description of what it does, which caps this at 2 per the rubric guidelines. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Azure resources', 'IaC files', 'optimize costs', 'GitHub issues', and 'rg' (resource group), but misses common user variations like 'cloud costs', 'spending', 'Terraform', 'Bicep', 'ARM templates', 'cost reduction', or 'Azure billing'. A user might say 'reduce my Azure bill' and this might not trigger. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of Azure resource analysis, cost optimization, and GitHub issue creation is a fairly distinct niche. It's unlikely to conflict with other skills given the specific Azure + cost + GitHub issues intersection. | 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 excellent workflow clarity, providing specific tools, commands, and templates for each step along with proper validation gates. However, it is severely over-engineered in length—the extensive inline templates, KQL queries, and optimization pattern catalogs bloat the token budget significantly. The lack of any progressive disclosure or supporting files means Claude must load this entire document every time, wasting context window on template boilerplate.
Suggestions
Extract the GitHub issue body templates (Steps 6 and 7) into separate reference files like ISSUE_TEMPLATES.md and EPIC_TEMPLATE.md, referencing them from the main skill
Move the KQL query examples and optimization patterns catalog into a separate PATTERNS.md or QUERIES.md file to reduce the main skill's token footprint
Remove explanatory text that Claude already knows—e.g., the Prerequisites section explaining what 'Azure MCP server configured' means, and the verbose descriptions of what each step does before the actual instructions
Condense the priority score formula and optimization categories into a compact table or bullet list rather than expanded sections with examples
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~250+ lines. It over-explains concepts Claude already knows (what IaC is, what cost optimization means, how to use Azure CLI), includes extensive template boilerplate that could be summarized, and repeats patterns across steps. The issue body templates alone consume massive token budget and could be condensed to key structural elements. | 1 / 3 |
Actionability | The skill provides specific, executable Azure CLI commands, concrete MCP tool invocations with parameter examples, real KQL queries, and detailed issue templates with exact formatting. Every step has concrete tools and commands to execute rather than vague descriptions. | 3 / 3 |
Workflow Clarity | The 7-step workflow is clearly sequenced with logical dependencies (discover → collect metrics → analyze → confirm → create issues). It includes explicit validation checkpoints (Step 4's 'Validate Recommendations', Step 5's user confirmation gate before creating issues), error handling section, and feedback loops for cost validation. | 3 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of text with no references to supporting files. The lengthy issue body templates, KQL queries, and optimization patterns could all be split into separate reference files. With no bundle files provided, everything is crammed into a single massive document with no navigation structure beyond sequential steps. | 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
2e7c43b
- 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.