Index of every page on this site: llms.txt
All skills
microsoft avatar

/azure-advisor-actionability

@bc67681 official
by microsoftmicrosoft/github-copilot-for-azure258 stars
212
Run it yourself

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

  • 2 files
  • 2 KB
  • MIT
  • Updated 2 days ago
  • GitHub
Use this Skill: https://skilld.dev/gh/microsoft/github-copilot-for-azure/azure-advisor-actionability

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈26 tokens for metadata: the name and description. ≈443 when used: this file. ≈14 more on demand in 1 file.

Description uses 1.3% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈106 characters, or 1.3%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

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.

Workflow

  1. Call advisor_remediation_get once with only recommendationTypeId, never resourceId, before generating guidance or substituting values.
  2. For RemediationNotFound, empty responses, or no usable remediation, state that Advisor remediation is unavailable. Retrieve relevant public Microsoft Learn documentation; ask for the recommendation description if unknown. If none is available, say so; never invent guidance. Report other tool errors without internals, not as empty results.
  3. Use only returned remediation or retrieved Learn guidance, including warnings and verification.
  4. After retrieval, substitute unambiguous placeholders from the exact affected resourceId or confirmed context: subscription, resource group, resource names, full resource ID. Preserve and describe unresolved placeholders.
  5. Preserve step order; separate Azure CLI and PowerShell.

For Advisor guidance, do not generate commands. For hybrid or executable, include every manual, decision, and command step. Omit raw JSON and internal labels.

Final response

Label the source: "Guidance source: Azure Advisor remediation tool" or "Guidance source: publicly available Microsoft Learn documentation" with retrieved learn.microsoft.com citations. Never attribute fallback guidance to Advisor or claim execution.

Source: SKILL.md on GitHub

Skill behaviors

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

Third-party checks

No third-party reports yet.

Provenance

Signed by skilld at bc67681. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 days ago

Capability

metadata
{
  "author": "Microsoft",
  "version": "0.0.0-placeholder"
}

README badge

README badge for microsoft/github-copilot-for-azure/azure-advisor-actionability