Name: az-cost-optimize
Rating: 74 (1 reviews)
Author: github

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.

2.02x

Quality

61%

Does it follow best practices?

Impact

79%

2.02x

Average score across 6 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/az-cost-optimize/SKILL.md

Quality

Content

63%Weight 40%Scale 1-5

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

The skill body is a thorough, mostly-executable workflow with concrete commands, KQL, formulas, and a confirmation checkpoint before batch issue creation. Its weaknesses are verbosity from inline boilerplate templates and the absence of any progressive disclosure via separate reference files.

Suggestions

Move the large GitHub issue/EPIC body templates (Steps 6-7) into reference files (e.g. references/issue-template.md) and link to them, reducing inline token cost.

Tighten prose by removing explanatory filler Claude already knows (e.g. restating what lifecycle policies or auto-scaling are) and keep only the optimization rules and commands.

Add an explicit validation feedback loop after issue creation (verify created issue numbers, link them into the EPIC checklist) to strengthen the batch-operation recovery path.

Dimension	Reasoning	Score
Conciseness	The content is mostly efficient with concrete commands and KQL examples, but the large inline GitHub-issue body templates (Steps 6-7) are padded boilerplate that bloats the token budget without adding novel guidance Claude doesn't already know.	3 / 5
Actionability	Provides concrete, mostly-executable guidance including specific Azure MCP/CLI commands, KQL queries, a priority-score formula, and labeled issue templates, with only minor gaps (e.g. placeholder variables and 'az billing' hand-waving).	4 / 5
Workflow Clarity	A clear 7-step sequence with a user-confirmation checkpoint (Step 5) and explicit validation (Step 4 'Validate Recommendations', Step 3 cost validation); it is a batch/destructive operation (creating many issues) and does include confirmation, though error-recovery feedback loops are only lightly specified.	4 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ absent) and the body inlines large templates and query blocks that could live in separate files; structure via headers is present but content is not split or externally referenced.	3 / 5
	Total	14 / 20 Passed

Description

58%Weight 40%Scale 1-5

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 clearly states what the skill does (analyze and optimize Azure resource costs, create GitHub issues) but omits any explicit 'Use when...' trigger guidance, capping completeness. Trigger-term coverage is decent but misses natural synonyms users would say.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when the user wants to reduce their Azure bill, optimize cloud spend, or find cost savings in Azure resources.'

Broaden trigger terms with user-natural synonyms such as 'reduce Azure bill', 'cloud spend', 'cost savings', and 'IaC files (.bicep, .tf)'.

Make the concrete actions more specific by listing optimization types (e.g. right-size SKUs, switch to serverless, lifecycle storage tiers) rather than the generic 'optimize costs'.

Dimension	Reasoning	Score
Specificity	Names the domain (Azure resources, IaC files) and several concrete actions ('analyze', 'optimize costs', 'creating GitHub issues'), but the actions are fairly high-level and don't enumerate the optimization kinds.	4 / 5
Completeness	The 'what' is clear (analyze and optimize Azure resource costs, create GitHub issues), but there is no explicit 'when/Use when' trigger clause, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Contains relevant keywords like 'Azure resources', 'IaC files', 'cost', 'optimize', and 'GitHub issues', but lacks common natural user phrasings like 'reduce Azure bill', 'cost savings', or synonyms users would actually say.	3 / 5
Distinctiveness Conflict Risk	The niche (Azure cost optimization with GitHub issue creation) is fairly distinct and unlikely to conflict with most other skills, with only minor overlap risk against generic cost or issue-creation skills.	4 / 5
	Total	14 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: github/awesome-copilot
Path: skills/az-cost-optimize/SKILL.md
Commit: 797cf9f

Reviewed: 2 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.