All skills
lukemurraynz avatar

/azure-sre-agent

@2cc2455

Design, configure, review, and operate production-grade Azure SRE Agent capabilities: response plans, scheduled tasks, HTTP triggers, custom agents, autonomous and review workflows, approval guardrails, AMBA observability, source RCA, connectors, MCP, governance hooks, WAF reviews, AI Foundry posture, Digital Native governance, postmortem generation, and KT discipline.

Use this Skill: https://skilld.dev/gh/lukemurraynz/hve-agent-skills/azure-sre-agent

This session only. Nothing lands on disk.

referencesbundles-operations.md

≈484 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Bundle Operations Guide

Use this guide to evolve capabilities without changing the core skill.

Bundle-First Rule

When adding or removing capability:

  1. Update bundles first.
  2. Update bundle catalog second.
  3. Update core skill routing only if navigation changes.

This keeps core SKILL.md stable and prevents capability sprawl.

Standard Bundle Components

A capability bundle can include:

  1. agents/
  2. response-plans/
  3. scheduled-tasks/
  4. hooks/
  5. connectors/
  6. checklists/

Capability Assembly Pattern

Assemble production agents by composing bundles:

  1. Start with base-core.
  2. Add one or more domain bundles:
    • aks-production
    • containerapps-production
    • drasi-aks-production
  3. Add policy bundles:
    • governance-kt
  4. Add integration bundles:
    • connectors-observability

Change Workflow

  1. Introduce new capability in a new or existing bundle.
  2. Add/adjust bundle.yaml metadata.
  3. Register in bundles/catalog.yaml.
  4. Add/update acceptance checks.
  5. Test with:
    • historical incident simulation
    • scheduled task "Run task now"
    • hook behavior validation

Versioning Guidance

  1. Patch version: non-breaking tweaks.
  2. Minor version: additive new resources.
  3. Major version: breaking behavior changes.

Document breaking changes in bundle notes.

Bundle Validation Checklist

Before marking a bundle production-ready:

  1. Resource names are environment-neutral.
  2. No hardcoded personal IDs/emails/tokens.
  3. At least one test scenario is documented.
  4. Required dependencies are declared in bundle.yaml.
  5. Rollback path is documented for write actions.

Practical Outcome

This model lets you:

  1. create new agents quickly by composing bundles,
  2. add capability without editing SKILL.md, and
  3. keep long-term maintenance manageable as scope expands.

For composition examples, see capability-matrix.md.

Source: SKILL.md on GitHub

No alerts8d3 checks · Risk SAFE
  • Gen Agent Trust Hub8d

    The Azure SRE Agent skill provides a production-grade framework for managing Azure infrastructure using AI agents. It incorporates extensive safety documentation, approval-based hooks, and least-privilege role templates. The 'low' verdict is assigned due to the inherent risk of indirect prompt injection when the agent processes external incident data and source code, a necessary function for its SRE capabilities.

  • Socket8d

    No alerts

  • Snyk8d

    Risk: LOW · No issues

Signed by skilld at 2cc2455. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Steadyupdated last month
compatibility
Azure SRE Agent; GitHub Copilot agent skills; new projects only
Other metadata
metadata
{
  "last_verified": "2026-08-25",
  "version": "2.23.3",
  "risk": "critical",
  "last_updated": "2026-08-25"
}

README badge

README badge for lukemurraynz/hve-agent-skills/azure-sre-agent