AI Skills

llms.txt lists every page for an agent

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.

What are skills?

Skills are markdown documents bundled with a lexicon. An AI agent working in a chant project loads the relevant skills automatically, so it knows the build and deploy steps without the user explaining them.

Installation

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:

chant update

Skill: chant-azure

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

Build — chant build src/ --output template.json
Validate — chant lint src/ + az deployment group validate
Deploy — az deployment group create with parameters
Update — incremental or complete deployment modes
Delete — az deployment group delete / az group delete
Status — az deployment group show and operation details
Troubleshooting — deployment operation inspection, error resolution

Skill: chant-azure-security

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

Skill: chant-azure-patterns

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

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

Skill: chant-azure-aks

The chant-azure-aks skill bridges the Azure and Kubernetes lexicons for 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

MCP integration

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

MCP tool	Description
`build`	Build the chant project
`lint`	Run lint rules
`explain`	Summarize project resources
`scaffold`	Generate starter files
`search`	Search available resource types

chant