1. Schema Validation – Checks that required fields (name, version, description, execution) are present and correctly formatted (e.g., name must start with /).

2. Parameter Verification – Verifies each parameter in the manifest has name, type, and description, and that the execution target (agent/skill/workflow) actually exists in the system.

3. Registry Update – On success, adds the command entry to /registry/commands.json with status active.

Validation Rules

Required Fields

• name : Command name (must start with /, e.g., /api-design)
• version : Semantic version (e.g., 0.1.0)
• description : Human-readable description of what the command does
• execution : Object specifying how to execute the command

Execution Configuration

The execution field must contain:

• type : One of skill, agent, or workflow
• target : Name of the skill/agent/workflow to invoke
  • For skills: Must exist in /registry/skills.json
  • For agents: Must exist in /registry/agents.json
  • For workflows: File must exist at /workflows/{target}.yaml

Optional Fields

• parameters : Array of parameter objects, each with:
  • name (required): Parameter name
  • type (required): Parameter type (string, number, boolean, etc.)
  • required (optional): Whether parameter is required
  • description (optional): Parameter description
  • default (optional): Default value
• status : Command status (draft or active, defaults to draft)
• tags : Array of tags for categorization

Outputs

Success Response

{
  "ok": true,
  "status": "registered",
  "errors": [],
  "path": "commands/hello.yaml",
  "details": {
    "valid": true,
    "status": "registered",
    "registry_updated": true,
    "manifest": {
      "name": "/hello",
      "version": "0.1.0",
      "description": "Prints Hello World",
      "execution": {
        "type": "skill",
        "target": "test.hello"
      }
    }
  }
}

Failure Response

{
  "ok": false,
  "status": "failed",
  "errors": [
    "Skill 'test.hello' not found in skill registry"
  ],
  "path": "commands/hello.yaml",
  "details": {
    "valid": false,
    "errors": [
      "Skill 'test.hello' not found in skill registry"
    ],
    "path": "commands/hello.yaml"
  }
}

Example

Valid Command Manifest

# commands/api-design.yaml
name: /api-design
version: 0.1.0
description: "Design a new API following enterprise guidelines"

parameters:
  - name: service_name
    type: string
    required: true
    description: "Name of the service/API"

  - name: spec_type
    type: string
    required: false
    default: openapi
    description: "Type of API specification (openapi or asyncapi)"

execution:
  type: agent
  target: api.designer

status: active
tags: [api, design, enterprise]

Running the Validator

$ python skills/command.define/command_define.py commands/api-design.yaml
{
  "ok": true,
  "status": "registered",
  "errors": [],
  "path": "commands/api-design.yaml",
  "details": {
    "valid": true,
    "status": "registered",
    "registry_updated": true
  }
}

Invalid Command Example

If the target agent doesn't exist:

$ python skills/command.define/command_define.py commands/hello.yaml
{
  "ok": false,
  "status": "failed",
  "errors": [
    "Agent 'api.designer' not found in agent registry"
  ],
  "path": "commands/hello.yaml"
}

Integration

With Workflows

Commands can be validated as part of a workflow:

# workflows/register_command.yaml
steps:
  - skill: command.define
    args:
      - "commands/my-command.yaml"
    required: true

With Hooks

Validate commands automatically when they're edited:

# Create a hook that validates command manifests on save
python skills/hook.define/hook_define.py \
  --event on_file_save \
  --pattern "commands/**/*.yaml" \
  --command "python skills/command.define/command_define.py" \
  --blocking true

Common Errors

See Also

• Command Manifest Schema – documented in Command and Hook Infrastructure
• Slash Commands Usage – overview in .claude/commands/README.md
• Betty Architecture – Five-Layer Model for understanding how commands fit into the framework
• agent.define – for validating and registering agents that commands can invoke
• hook.define – for creating validation hooks that can trigger command validation

Exit Codes

• 0 : Success (manifest valid and registered)
• 1 : Failure (validation errors or registry update failed)

Files Modified

• Registry : /registry/commands.json – updated with new or modified command entry
• Logs : Command validation and registration logged to Betty's logging system

Dependencies

• Skill Registry (/registry/skills.json) – for validating skill targets
• Agent Registry (/registry/agents.json) – for validating agent targets
• Workflow Files (/workflows/*.yaml) – for validating workflow targets

Status

Active – This skill is production-ready and actively used in Betty's command infrastructure.

Version History

• 0.1.0 (Oct 2025) – Initial implementation with full validation and registry management

Weekly Installs

–

Source

smithery.ai/ski…d-define

First Seen

–