azure-cost-optimization

Identify Azure cost savings from usage and spending data. USE FOR: optimize Azure costs, reduce Azure spending/expenses, analyze Azure costs, find cost savings, generate cost optimization report, identify orphaned resources to delete, rightsize VMs, reduce waste, optimize Redis costs, optimize storage costs, AKS cost analysis add-on, namespace cost, cost spike, anomaly, budget alert, AKS cost visibility. DO NOT USE FOR: deploying resources (use azure-deploy), general Azure diagnostics (use azure-diagnostics), security issues (use azure-security)

Quality

75%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.github/plugins/azure-skills/skills/azure-cost-optimization/SKILL.md

Quality

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 excellent skill description that covers all key dimensions well. It provides specific concrete actions, extensive natural trigger terms, clear 'what' and 'when' guidance, and explicit boundary-setting with related skills via DO NOT USE FOR clauses. The description is comprehensive without being padded with fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: identify orphaned resources, rightsize VMs, optimize Redis costs, optimize storage costs, AKS cost analysis, namespace cost analysis, cost spike/anomaly detection, budget alerts. Goes well beyond vague language.	3 / 3
Completeness	Clearly answers both 'what' (identify Azure cost savings from usage and spending data) and 'when' (explicit 'USE FOR' clause with extensive trigger scenarios). Also includes helpful 'DO NOT USE FOR' guidance with alternative skill recommendations.	3 / 3
Trigger Term Quality	Excellent coverage of natural terms users would say: 'optimize Azure costs', 'reduce Azure spending', 'find cost savings', 'orphaned resources', 'rightsize VMs', 'reduce waste', 'cost spike', 'anomaly', 'budget alert', 'AKS cost visibility'. These are highly natural phrases a user would use.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with a clear niche (Azure cost optimization) and explicitly differentiates itself from related skills via 'DO NOT USE FOR' clauses pointing to azure-deploy, azure-diagnostics, and azure-security. This greatly reduces conflict risk.	3 / 3
	Total	12 / 12 Passed

Implementation

50%

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

This skill is highly actionable with concrete, executable commands and clear tool usage throughout, which is its strongest quality. However, it suffers significantly from verbosity — the full report template, JSON query bodies, and extensive notes sections should be extracted into reference files. The workflow has good sequential structure but the conditional Redis/AKS branching (Steps 1.5-1.8) creates confusing flow, and validation checkpoints between critical steps are missing.

Suggestions

Extract the full report template (Step 7) and cost query JSON (Step 4) into separate template/reference files to dramatically reduce the main skill's token footprint.

Consolidate Steps 1.5-1.8 (Redis/AKS conditional branches) into a single 'Specialized Analysis' section with a simple decision table, rather than interleaving scope-selection steps that break the main workflow flow.

Add explicit validation checkpoints after Step 4 (verify cost query returned data) and after Step 7 (verify report file was created), especially since file creation is involved.

Remove explanatory notes that Claude already knows (e.g., what ISO 8601 format is, how to calculate 30 days ago, what UTF-8 encoding is) to improve conciseness.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~300+ lines. It includes excessive inline detail that could be in reference files (full JSON query templates, full report templates, extensive portal link formats, lengthy notes sections). Many sections explain things Claude already knows (how to calculate dates, what ISO 8601 format is, what PowerShell commands do). The report template alone is massive and should be a separate reference file.	1 / 3
Actionability	The skill provides fully executable commands, concrete code examples (PowerShell, JavaScript MCP calls, JSON query bodies), specific API endpoints, and copy-paste ready templates. Every step has concrete, actionable guidance with real tool invocations and specific parameters.	3 / 3
Workflow Clarity	Steps are clearly numbered and sequenced (0-9), but there are no explicit validation checkpoints between critical steps. The conditional branching (Steps 1.5-1.8 for Redis/AKS) creates confusing flow with unclear re-entry points. There's no validation after the cost query (Step 4) to verify data was returned correctly before proceeding to report generation. The 'choose analysis scope' steps (1.6, 1.8) interrupt the main flow awkwardly.	2 / 3
Progressive Disclosure	The skill does reference external files well (azure-redis.md, azure-quick-review.md, azure-resource-graph.md, azure-aks-*.md), but the main SKILL.md contains far too much inline content that should be in reference files — the full cost query JSON template, the entire report template structure, the complete metrics collection commands, and the audit trail JSON schema. The references are well-signaled but the main file is bloated with content that belongs in templates/references.	2 / 3
	Total	8 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: microsoft/azure-skills
Commit: 9d594ab

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.