Name: az-cost-optimize
Rating: 78.5 (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

—

Does it follow best practices?

Impact

79%

2.02x

Average score across 6 eval scenarios

Securityby

Passed

No known issues

Quality

Content

77%

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

The body is a highly actionable, well-sequenced workflow with concrete commands, queries, templates, and validation checkpoints. Its weaknesses are length/verbosity in the emoji-heavy templates and a monolithic structure with no progressive disclosure via reference files.

Suggestions

Move the long individual-issue and EPIC body templates into reference files (e.g. references/issue-template.md) and link to them from SKILL.md.

Trim the emoji decoration and redundant summary blocks in the templates to reduce token load.

Condense the KQL query block to the minimal essential queries and point to a reference for extended examples.

Dimension	Reasoning	Score
Conciseness	Avoids explaining concepts Claude already knows and uses concrete commands, but the ~300-line body with lengthy emoji-heavy issue templates could be tightened; not a 3 because not every token earns its place.	2 / 3
Actionability	Provides fully executable commands (azmcp-*, az CLI), concrete KQL queries, a priority-score formula, and copy-paste-ready issue body templates; not a 2 because guidance is complete rather than pseudocode.	3 / 3
Workflow Clarity	Clear 7-step sequence with explicit validation steps ('VALIDATE CURRENT COSTS', 'Validate Recommendations') and a user-confirmation gate before the batch GitHub-issue creation, plus an error-handling section; not capped at 2 because validation is present for the batch operation.	3 / 3
Progressive Disclosure	Well-organized into labeled sections but monolithic — all large issue/EPIC templates and queries are inline with no separate reference files, and the body exceeds the under-50-line simple-skill threshold; not a 3 because content that should be split out is inline.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 is specific and distinctive, naming concrete analyze/optimize/issue-creation actions in a clear niche. Its main weakness is the missing explicit 'Use when' trigger guidance and reliance on jargon like 'IaC files' and 'rg'.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user wants to reduce Azure costs or optimize Azure resource spend.'

Replace jargon ('IaC files', 'rg') with natural phrasing or spell them out ('Infrastructure-as-Code files', 'resource group').

Include common trigger variations such as 'reduce spending', 'save money', or 'Azure billing'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Analyze Azure resources', 'optimize costs', 'creating GitHub issues for identified optimizations' — matching the multi-action anchor; not the level below which only names a domain and some actions.	3 / 3
Completeness	Clearly answers 'what' but provides no 'when'/'Use when' clause, and the rubric caps completeness at 2 when explicit trigger guidance is missing; not a 1 because the 'what' is strong.	2 / 3
Trigger Term Quality	Contains relevant natural terms ('Azure resources', 'optimize costs', 'GitHub issues') but leans on jargon ('IaC files', 'rg') and omits common variations like 'reduce spending' or 'save money'; not a 3 because coverage of natural user phrasing is incomplete.	2 / 3
Distinctiveness Conflict Risk	The niche of Azure cost optimization coupled with GitHub issue creation is specific and unlikely to trigger for unrelated skills; not a 2 because it does not merely overlap a broad category.	3 / 3
	Total	10 / 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: github/awesome-copilot
Commit: 49d020f

Reviewed: 4 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.