hello-world

KubeVirt AI Helpers

A collection of Claude Code plugins to automate and assist with KubeVirt development workflows.

Overview

This project provides Claude Code plugins for KubeVirt development, including code review and linting workflows. For general Kubernetes, CI/CD, and development workflows, use the OpenShift AI Helpers.

Installation

From the Claude Code Plugin Marketplace

1. Add the marketplace:

   /plugin marketplace add lyarwood/kubevirt-ai-helpers
   

2. Install a plugin:

   /plugin install kubevirt@kubevirt-ai-helpers
   

3. Use the commands:

   /kubevirt:review
   /kubevirt:lint pkg/virt-controller/watch
   /kubevirt:review-ci 12345
   /kubevirt:vep-list --release 1.9
   

Related Helpers

This project is modeled after the OpenShift AI Helpers and focuses on KubeVirt-specific workflows.

When to Use OpenShift AI Helpers

Use OpenShift AI Helpers for:

• Jira workflows: /jira:solve, /jira:create
• Git operations: /git:commit-suggest, /git:branch-cleanup
• CI/CD: /ci:trigger-periodic, /prow-job:analyze-test-failure
• Generic must-gather: /must-gather:analyze
• Session management: /session:start, /session:resume

When to Use KubeVirt AI Helpers

Use KubeVirt AI Helpers for:

• Code review: Review local branch changes using KubeVirt project best practices
• PR CI analysis: Analyze CI failures for specific PRs with root cause identification and remediation suggestions
• CI health monitoring: Track overall CI stability, analyze job lanes, and search for failure patterns
• Intelligent CI triage: AI-powered root cause analysis with prioritized recommendations
• CI reporting: Generate comprehensive health reports for stakeholders
• Linting: Run golangci-lint and generate a plan to fix issues with separate commits per linter
• VEP management: List, summarize, and groom KubeVirt Enhancement Proposals (VEPs)

Using Both Together

# Add both marketplaces
/plugin marketplace add openshift-eng/ai-helpers
/plugin marketplace add lyarwood/kubevirt-ai-helpers

# Install plugins from both
/plugin install jira@ai-helpers
/plugin install kubevirt@kubevirt-ai-helpers

# Use commands from both
/jira:solve OCPBUGS-12345 origin
/kubevirt:review

Available Plugins

For a complete list of all available plugins and commands, see PLUGINS.md.

Prerequisites

Healthcheck Tool (for CI analysis commands)

The CI analysis commands (/kubevirt:ci-*) require the healthcheck CLI tool:

# Clone and build healthcheck
git clone https://github.com/lyarwood/healthcheck.git
cd healthcheck
go build
sudo mv healthcheck /usr/local/bin/

# Verify installation
healthcheck --help

The healthcheck tool provides:

• Live Prow data crawling for job lane analysis
• Aggregated ci-health data for quick overviews
• Search capabilities via search.ci.kubevirt.io
• Optional MCP server for advanced AI-powered analysis

Ambient Workflows

These commands are also available as Ambient Code Platform workflows. When creating an Ambient session, attach a workflow from this repository:

workflow_git_url: https://github.com/lyarwood/kubevirt-ai-helpers.git
workflow_path: workflows/kubevirt-review
workflow_branch: main

Available workflows: kubevirt-review, kubevirt-lint, kubevirt-review-ci, kubevirt-vep-list, kubevirt-vep-summary, kubevirt-vep-groom, kubevirt-ci-lane, kubevirt-ci-health, kubevirt-ci-search, kubevirt-ci-triage, kubevirt-ci-report.

See workflows/README.md for details.

Plugin Development

Want to contribute or create your own plugins? Check out the plugins/ directory for examples. Make sure your commands and agents follow the conventions for the Sections structure presented in the hello-world reference implementation plugin (see hello-world:echo for an example).

Ethical Guidelines

Plugins, commands, skills, and hooks must NEVER reference real people by name, even as stylistic examples (e.g., "in the style of ").

Ethical rationale:

1. Consent: Individuals have not consented to have their identity or persona used in AI-generated content
2. Misrepresentation: AI cannot accurately replicate a person's unique voice, style, or intent
3. Intellectual Property: A person's distinctive style may be protected
4. Dignity: Using someone's identity without permission diminishes their autonomy

Instead, describe specific qualities explicitly

Good examples: