Skip to content

AI Skills

The Azure lexicon ships several AI skills that teach AI coding agents how to build, validate, and deploy Azure Resource Manager templates from a chant project.

Skills are structured markdown documents bundled with a lexicon. When an AI agent works in a chant project, it discovers and loads relevant skills automatically — giving it operational knowledge about the deployment workflow without requiring the user to explain each step.

When you scaffold a new project with chant init --lexicon azure, the skills are installed to skills/ for automatic agent discovery.

To refresh skills after a lexicon update:

Terminal window
chant update

The chant-azure skill covers the full Azure ARM deployment lifecycle:

  • Buildchant build src/ --output template.json
  • Validatechant lint src/ + az deployment group validate
  • Deployaz deployment group create with parameters
  • Update — incremental or complete deployment modes
  • Deleteaz deployment group delete / az group delete
  • Statusaz deployment group show and operation details
  • Troubleshooting — deployment operation inspection, error resolution

The chant-azure-security skill covers security best practices for Azure ARM templates:

  • Identity & Access — managed identities, RBAC role assignments, least-privilege
  • Network Security — NSG rules, private endpoints, service endpoints
  • Encryption — storage encryption, disk encryption, TLS enforcement
  • Monitoring — diagnostic settings, log analytics, alerts
  • Post-synth checks — maps to lint rules AZR016–AZR029

The chant-azure-patterns skill covers advanced ARM template patterns:

  • Linked Templates — nested and linked template deployments
  • Conditional Resources — conditional provisioning patterns
  • Cross-resource Referencesreference() and resourceId() usage
  • Tagging Strategies — consistent tagging across resources
  • Multi-region — deploying across Azure regions
  • Composites — high-level reusable resource groupings

The chant-azure-aks skill bridges the Azure and Kubernetes lexicons for end-to-end AKS workflows:

  • AKS Cluster — provisioning clusters with managed identities and RBAC
  • ACR Integration — Azure Container Registry attached to AKS
  • Workload Identity — federated identity credentials for pods
  • AGIC Ingress — Application Gateway Ingress Controller setup
  • Observability — monitoring, logging, and alerting for AKS workloads

The lexicon also provides MCP (Model Context Protocol) tools and resources that AI agents can use programmatically:

MCP toolDescription
buildBuild the chant project
lintRun lint rules
explainSummarize project resources
scaffoldGenerate starter files
searchSearch available resource types