Use when preparing or executing a release - verifies changelog content, updates version references, commits release prep, and, when the maintainer explicitly asks, pushes the release tag that triggers automation
Use when working on a GitHub issue - fetches issue details, analyzes codebase, implements fix following project methodology
Use when reviewing a pull request - security-focused review following CLAUDE.md guidelines for breaking changes, malicious patterns, and backward compatibility
Use after making changes to run terraform fmt, validate, and plan against test environment
Use when users need help with kube-hetzner configuration, debugging, or questions - acts as an intelligent assistant with live repo access
Use when documentation needs updating - ensures variables.tf, llms.md, kube.tf.example, and README are in sync
Use when triaging a GitHub issue - analyzes issue, checks for duplicates, categorizes, and drafts response