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

84%

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

The canonical home for this skill is azure-advisor in microsoft/GitHub-Copilot-for-Azure

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 instruction skill with exact tool names, parameter values, and an intent-to-tool mapping, plus a clean single-reference progressive-disclosure structure. The only notable issues are minor sentence-level duplication in the body and the absence of an explicit error-recovery loop for mid-flow failures.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence with no concept explanations, but "Prefer Advisor MCP tools" (line 12 vs line 17) and "Reuse known scope and identifiers" (line 13 vs line 40) are each stated twice, minor instances that could be trimmed. Everything else earns its place, so it sits above anchor 3.

4 / 5

Actionability

For an instruction-only skill the guidance is fully executable: exact tool names (advisor_recommendation_summary, advisor_recommendation_list, advisor_recommendation_update), exact parameter values (prioritized: true, sub-category: "ServiceUpgradeAndRetirement", retirement-date: "le:<yyyy-MM-dd>"), and an intent-to-tool table covering the common cases. No concrete gaps remain.

5 / 5

Workflow Clarity

A clear routing-then-execution sequence with explicit checkpoints: user confirmation before recommendation-state updates, explicit unranked labeling when constraints are unsupported, and mandatory error/truncation disclosure. It falls short of anchor 5 because the body lacks an explicit error-recovery feedback loop (e.g., what to do when a tool call fails mid-drill-down); the destructive/batch cap does not apply since confirmation and disclosure checkpoints are present.

4 / 5

Progressive Disclosure

A concise overview with a single, clearly signaled, condition-gated reference ("Before generic calls or reporting, read [Workflow](references/workflow.md)"); the file exists, is one level deep, and introduces no nested file references. Content is appropriately split between overview and reference with easy navigation.

5 / 5

Total

18

/

20

Passed

Description

73%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 description with excellent trigger phrasing and explicit boundary routing against sibling skills. Its main weakness is the generic capability statement "Use Azure Advisor", which names the domain without stating what the skill actually does.

Suggestions

Replace the generic opening "Use Azure Advisor" with concrete capabilities, e.g. "Retrieve, prioritize, and update Azure Advisor recommendations and track service retirements", so the 'what' is explicit.

Add natural trigger synonyms such as "Advisor suggestions", "Azure recommendations", or "cost-saving recommendations" to broaden keyword coverage.

Use third-person declarative voice (e.g. "Manages Azure Advisor recommendations...") rather than the imperative "Use Azure Advisor".

DimensionReasoningScore

Specificity

The core capability statement is a single generic verb ("Use Azure Advisor"), which only names the domain, but trigger phrases like "prioritize recommendations", "service retirements", and "update status" convey a couple of concrete operations beyond a bare domain mention. It does not list the skill's concrete actions explicitly, so it falls short of anchor 4.

3 / 5

Completeness

Both parts are present: an explicit "WHEN:" clause with concrete trigger phrases answers when, and "Use Azure Advisor" plus routing boundaries answers what. The "what" side is generic (it never states the skill's actual capabilities such as retrieving or updating recommendations), keeping it below anchor 5.

4 / 5

Trigger Term Quality

Quotes natural user phrases such as "show recommendations", "top Advisor actions", "prioritize recommendations", "service retirements", and "update status", giving good keyword coverage. It lacks common synonyms like "Advisor suggestions" or "cost-saving recommendations", so it does not reach comprehensive anchor-5 coverage.

4 / 5

Distinctiveness Conflict Risk

The description explicitly routes overlapping requests to named siblings ("Unused-resource discovery and Cost/IdleResources requests use azure-advisor-cost-optimization", "DO NOT USE FOR: fixes (use azure-advisor-actionability)"), establishing a clear niche with minimal conflict risk.

5 / 5

Total

16

/

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/azure-skills

Path

.github/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.