CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

azure-advisor

Use Azure Advisor. WHEN: "show recommendations", "top Advisor actions", "prioritize recommendations", "service retirements", "update status". Unused-resource discovery and Cost/IdleResources requests use azure-advisor-cost-optimization; generic Cost and cross-category requests stay here. DO NOT USE FOR: fixes (use azure-advisor-actionability).

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A lean, highly actionable MCP-tool skill body with concrete parameter guidance, a clearly sequenced workflow with safety checkpoints, and exemplary use of a single well-signaled reference file. The remaining gaps are minor: small duplicated guidance, no complete example invocation, and no explicit error-recovery loop.

Suggestions

Deduplicate the repeated guidance — 'Prefer Advisor MCP tools over Resource Graph or generic ARM calls' appears in both the intro and the Quick reference, and scope-reuse appears in both the intro and Workflow step 1.

Add one complete example tool invocation (e.g., a JSON parameter set for a prioritized Cost summary) so guidance is copy-paste ready for the most common case.

Add a brief error-recovery note (e.g., what to do when a tool call fails or a continuation token repeats) to strengthen feedback loops in the workflow.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence, never explaining what Azure Advisor or recommendations are, but contains minor redundancy: "Prefer Advisor MCP tools" appears in both the intro and the Quick reference section, and scope-reuse guidance is repeated between the intro and Workflow step 1. This is efficient with a few tokens that could be trimmed, matching the 4 anchor rather than the every-token-earns-its-place 5.

4 / 5

Actionability

Provides concrete, tool-level guidance with exact parameter names and values (`advisor_recommendation_summary` with `prioritized: true`, `sub-category: "ServiceUpgradeAndRetirement"`, `retirement-date: "le:<yyyy-MM-dd>"`, GUID `key` in `recommendation-type-ids`). Not 5 because there is no complete example call or parameter set; the skill defers to live MCP schemas.

4 / 5

Workflow Clarity

A clear five-step numbered sequence with most checkpoints present: confirmation gate before state updates, disclosure of errors and truncation, and explicit labeling of unranked results. Not 5 because there is no explicit error-recovery or validate-retry feedback loop; state updates are confirmation-gated rather than destructive/batch, so the cap of 3 does not apply.

4 / 5

Progressive Disclosure

A well-organized, under-50-line body with a single clearly signaled, one-level-deep reference — "Before generic calls or reporting, read [Workflow](references/workflow.md)" — which exists in the bundle and is loaded conditionally rather than unconditionally. Content is appropriately split between overview and the detailed workflow file, matching the 5 anchor.

5 / 5

Total

17

/

20

Passed

Description

78%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.

A well-structured routing-style description with explicit WHEN triggers and excellent sibling-skill boundary demarcation. Its main weakness is the terse capability statement, which relies on the trigger list to convey what the skill actually does.

Suggestions

Expand the opening clause beyond "Use Azure Advisor" to name concrete capabilities (e.g., retrieve, prioritize, and update the status of Azure Advisor recommendations, and track service retirements) so the 'what' is self-contained.

Add common trigger synonyms such as "cost savings", "dismiss or snooze recommendations", and "what should I fix first" to broaden natural keyword coverage.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ("show recommendations", "prioritize recommendations", "service retirements", "update status"), with minor gaps such as metadata browsing and summary breakdowns. It does not reach 5 because the capability statement is a terse "Use Azure Advisor" that leans on the trigger list rather than explicitly describing what the skill does.

4 / 5

Completeness

Explicitly answers both "what" ("Use Azure Advisor" plus routing of generic Cost and cross-category requests) and "when" via a WHEN clause with concrete trigger phrases. Not 5 because the "what" is a single terse clause rather than a descriptive statement of capabilities, as in the 5 anchor.

4 / 5

Trigger Term Quality

Includes quoted, natural phrases users would say ("top Advisor actions", "prioritize recommendations", "service retirements", "update status"). Not 5 because common variations like "cost savings", "what should I fix first", or "dismiss/snooze recommendations" are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche with explicit boundary guidance: "Unused-resource discovery and Cost/IdleResources requests use azure-advisor-cost-optimization" and "DO NOT USE FOR: fixes (use azure-advisor-actionability)". This explicit sibling routing and negative trigger guidance gives minimal conflict risk, matching the 5 anchor.

5 / 5

Total

17

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

microsoft/GitHub-Copilot-for-Azure

Path

plugins/azure-advisor/skills/azure-advisor/SKILL.md

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.