CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

azure-advisor-actionability

Get remediation instructions for selected Azure Advisor recommendations. WHEN: fix a selected recommendation, generate remediation commands. DO NOT USE FOR: unused-resource discovery, savings or deletion prevalidation (use azure-advisor-cost-optimization).

Quality

90%

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-actionability in microsoft/GitHub-Copilot-for-Azure

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An exemplary lean, instruction-only skill body: tight token budget, concrete tool-level guidance, a clear workflow with error-recovery and validation checkpoints, and clean section organization appropriate to its size. The only gap is the absence of a worked example of the final remediation response format.

DimensionReasoningScore

Conciseness

Every sentence is operational — tool names, parameter constraints, error identifiers, and exact output labels — with zero padding and no explanation of concepts Claude already knows. This is a clear match for 'lean and efficient; every token earns its place', not a 4, which would require noticeable over-explanation to trim.

5 / 5

Actionability

Concrete, executable instruction throughout: call 'advisor_remediation_get once with only recommendationTypeId, never resourceId', an explicit 'RemediationNotFound' fallback branch, and exact source-label strings for the final response. It falls short of anchor 5 only because there is no worked example of the final response format (e.g., a sample CLI/PowerShell remediation block or placeholder-substitution example) covering the common cases.

4 / 5

Workflow Clarity

A numbered five-step sequence with an explicit error-recovery loop ('For RemediationNotFound, empty responses... Retrieve relevant public Microsoft Learn documentation... If none is available, say so') and input validation checkpoints ('ask for missing values, never guess', 'Ask which resource if ambiguous'). The skill presents commands rather than executing them, so the destructive/batch cap does not apply, and the error feedback loop satisfies the top anchor rather than the 'minor validation gaps' anchor below.

5 / 5

Progressive Disclosure

The body is under 50 lines, needs no external references (none exist in the bundle), and is cleanly organized into Quick reference, Workflow, and Final response sections — meeting the rubric's simple-skill exception for a top score on well-organized sections alone.

5 / 5

Total

19

/

20

Passed

Description

82%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 strong description with explicit what/when triggers and excellent sibling-skill disambiguation. Its only weaknesses are limited action coverage (essentially one capability) and a few missing natural synonyms such as 'resolve' or 'address'.

Suggestions

Broaden the action coverage slightly (e.g., 'retrieve and present remediation steps, substitute resource-specific values, cite Microsoft Learn fallback documentation') to lift specificity beyond 1-2 actions.

Add natural trigger synonyms users might say, such as 'resolve' or 'address an Azure Advisor recommendation', to improve trigger-term coverage.

Consider naming the output artifacts (Azure CLI and PowerShell commands) in the description so users searching for 'CLI remediation' or 'PowerShell fix' also match.

DimensionReasoningScore

Specificity

Names the domain ('Azure Advisor recommendations') and one or two concrete actions ('Get remediation instructions', 'generate remediation commands'), but the actions collapse into a single capability, matching the '1-2 concrete actions, not comprehensive' anchor rather than the 'several specific actions' anchor above.

3 / 5

Completeness

Explicitly answers both what ('Get remediation instructions for selected Azure Advisor recommendations') and when ('WHEN: fix a selected recommendation, generate remediation commands') with concrete trigger phrases, plus a DO NOT USE FOR exclusion — a clear match for the top anchor. It is not a 4 because the 'when' is already explicit and trigger-phrase-based, not merely implied.

5 / 5

Trigger Term Quality

Includes natural phrases users would say such as 'fix a selected recommendation', 'generate remediation commands', and 'remediation instructions', but misses common synonyms like 'resolve' or 'address this recommendation', so it falls just short of the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

Carves a clear niche (remediation instructions for selected Advisor recommendations) and explicitly disambiguates from the sibling skill via 'DO NOT USE FOR: unused-resource discovery, savings or deletion prevalidation (use azure-advisor-cost-optimization)', giving minimal conflict risk.

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/azure-skills

Path

.github/plugins/azure-advisor/skills/azure-advisor-actionability/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.