azure-advisor-actionability

by microsoft3.1k

Remediate Azure Advisor recommendations. WHEN: \"fix Advisor recommendation\".

Install

The skill file stays in the publisher's repository.

Paste the copied command in a terminal. It installs this SKILL.md into that agent.

npx skills add microsoft/skills --skill azure-advisor-actionability -a cursor -y

Download skill .github/plugins/azure-advisor/skills/azure-advisor-actionability/SKILL.md on GitHub

Related skills

View all

S
SkillOptSkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
S
skillopt-sleepUse when the user wants their Claude agent to self-improve from past usage, asks about a nightly/offline 'sleep' or 'dream' cycle, memory/skill consolidation, or says things like 'make my agent better
S
skillopt-sleepReference-only OpenClaw adaptation of SkillOpt-Sleep. Use it to study or port the contributed DeepSeek wrapper, not as a ready-to-run installation.

Questions

How do I install azure-advisor-actionability?: Download .github/plugins/azure-advisor/skills/azure-advisor-actionability/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
Where does azure-advisor-actionability live?: The publisher keeps it at https://github.com/microsoft/skills.
Which agents can use azure-advisor-actionability?: Claude, Cursor, and Codex can read a SKILL.md you add from the publisher's repository.

name: azure-advisor-actionability description: "Remediate Azure Advisor recommendations. WHEN: "fix Advisor recommendation"." license: MIT metadata: author: Microsoft version: "1.0.1"

Azure Advisor Actionability

Quick reference

Present remediation for the customer to run; never execute without explicit confirmation. Require the recommendationTypeId GUID and complete affected resourceId; reuse known values, ask for missing values, never guess.

Get resourceId from the user or an exact advisor_recommendation_list affected-resource record. Ask which resource if ambiguous; never use a recommendation instance ID.