AI Commands

AI coding agents and IDE extensions work best when they understand your tools programmatically. These commands expose the CLI's structure, capabilities, and project context in machine-readable formats.

CLI Capabilities

Show the CLI's capabilities in a structured format for AI consumption:

agentuity ai capabilities show

This outputs a machine-readable description of what the CLI can do, useful for:

• AI coding agents that need to understand available commands
• IDE extensions building Agentuity integrations
• Documentation generators

Schema Inspection

Output the CLI's command schema for programmatic consumption:

# Show the full CLI schema
agentuity ai schema show
 
# Generate schema in a specific format
agentuity ai schema generate

The schema includes:

• All available commands and subcommands
• Required and optional parameters
• Parameter types and validation rules
• Command descriptions and examples

Agent Skills Generation

Generate Agent Skills documentation from the CLI schema:

# Generate SKILL.md files
agentuity ai skills generate
 
# Output to custom directory
agentuity ai skills generate --output ./skills

This creates machine-readable skill definitions that enable coding agents (e.g., Claude Code, Cursor, Codex) to discover and use Agentuity CLI capabilities.

Generated files:

• SKILL.md files with YAML frontmatter for each command
• README.md with a skill index

Project Context Files

During development (agentuity dev or bun run dev), the CLI generates AGENTS.md files to help AI coding assistants (e.g., Claude Code, Codex, Cursor) understand Agentuity patterns:

.agents/
└── agentuity/
    └── sdk/
        ├── agent/AGENTS.md   # Agent creation patterns
        ├── api/AGENTS.md     # Route creation patterns
        └── web/AGENTS.md     # Frontend patterns

These files are auto-updated when the CLI version changes and should be added to .gitignore.

Prompt Generation

Generate context-aware prompts for LLMs working with Agentuity projects:

# Generate prompt for building agents
agentuity ai prompt agent
 
# Generate prompt for building APIs
agentuity ai prompt api
 
# Generate general LLM prompt
agentuity ai prompt llm
 
# Generate prompt for web/frontend development
agentuity ai prompt web

Each prompt type includes:

• Relevant SDK patterns and best practices
• Code examples for the target domain
• Common pitfalls to avoid
• Links to documentation

Integration Examples

IDE Extension

Use the CLI to provide autocomplete, validation, and project configuration help:

// Get CLI capabilities for IDE integration
const { execSync } = require('child_process');
 
const capabilities = JSON.parse(
  execSync('agentuity --json ai capabilities show').toString()
);
 
// Use capabilities to build autocomplete, validation, etc.

// Get agentuity.json schema for configuration validation
const schema = JSON.parse(
  execSync('agentuity --json ai schema generate').toString()
);
 
// Use schema to validate project configuration files

AI Coding Agent

# Generate context for an AI agent working on your project
agentuity ai prompt agent > /tmp/agentuity-context.md
 
# Include in your AI agent's system prompt
cat /tmp/agentuity-context.md

Next Steps

• Getting Started with the CLI: Install and authenticate
• Local Development: Run agents locally
• Creating Agents: Build your first agent