Skip to main content
In teams using coding assistants, sharing and reusing prompts that work is often tedious. A Packmind Command is an executable, step-by-step guide that tells the AI assistant exactly how to perform a development task so your team’s practices are applied consistently and reproducibly. Examples
  • “Add a new REST endpoint” — steps to define the route, implement the handler, add input validation, write tests, and update API docs.
  • “Set up a CI pipeline for a project” — steps to configure the workflow, run lint/tests/build on each push/PR, and report status checks.
The MCP server must be configured to create Commands. See the setup guide: Get started with the MCP server.

​
How to

  1. Open your IDE and your coding assistant in agentic mode.
  2. For this demo, we will create a language-agnostic command. (You can also target a specific language or framework.)
  3. Type this prompt or use the /packmind-create-command skill:
Analyze our codebase and create a Packmind command to add a new endpoint to our API.
Using the Skill — You can also type /packmind-create-command in your AI assistant to invoke the command creator skill directly. This provides step-by-step guidance through the creation process.

​
How it works

The AI agent will automatically follow the command creation workflow which guides it through:
  1. Understanding the process - The agent identifies the development process you want to capture as a command
  2. Structuring the command - The agent breaks down the process into clear, actionable steps with:
    • When to use scenarios - Specific situations where the command applies
    • Context validation checkpoints - Questions to clarify before implementing
    • Step-by-step instructions - Atomic, repeatable actions with optional code examples
  3. Finalization - Once structured properly, the agent calls the save_command MCP tool
Your new command will be available in the Packmind web app, in the Commands panel.
The workflow ensures commands are well-structured and reusable by enforcing clear steps, validation checkpoints, and usage scenarios. This makes them effective for AI agents and team members alike.

​
Alternative: Create Commands from the CLI

You can also create commands directly from your terminal using the Packmind CLI without MCP support.

​
Prerequisites

  1. Install the Packmind CLI:
npm install -g @packmind/cli
  1. Authenticate with your Packmind account:
packmind-cli login

​
Create a Command File

Create a JSON file (e.g., my-command.json) with your command definition: 
{
  "name": "Add a New REST Endpoint",
  "summary": "Step-by-step guide for adding a new REST endpoint with validation, tests, and documentation",
  "whenToUse": [
    "When adding a new API endpoint to the backend service",
    "When extending existing API functionality"
  ],
  "contextValidationCheckpoints": [
    "Do you understand the business requirement?",
    "Do you know the request and response structures?"
  ],
  "steps": [
    {
      "name": "Define the Route",
      "description": "Create the HTTP route with appropriate method and path"
    },
    {
      "name": "Implement the Handler",
      "description": "Write the handler function that processes the request"
    },
    {
      "name": "Add Input Validation",
      "description": "Validate request parameters and body data"
    }
  ]
}

​
Understanding Command Naming

The name field in your playbook is automatically converted to a slug for use in file names and AI agent invocation:
  • Your playbook name: "Add a New REST Endpoint"
  • Generated slug: "add-a-new-rest-endpoint"
  • Used in file: .claude/commands/packmind/add-a-new-rest-endpoint.md
  • AI agent command: /add-a-new-rest-endpoint
Slug Generation Rules:
  • Converts to lowercase
  • Replaces spaces and special characters with hyphens
  • Removes non-alphanumeric characters
  • If a command with the same slug exists, adds -1, -2, etc. for uniqueness
Examples:
  • "Setup CI Pipeline" → "setup-ci-pipeline"
  • "Add@Database Migration!" → "add-database-migration"
  • Duplicate of above → "add-database-migration-1"

​
Submit the Command

Run the CLI command to create the command: 
packmind-cli commands create ./my-command.json
Your new command will appear in the Packmind web app’s Commands panel.
CLI vs MCP Workflow — Use the CLI approach when you already have a command structured and ready, or when you prefer working with files. Use the MCP/AI approach when you want AI assistance in analyzing your codebase and structuring the command.

​
Tips

The quality of the generated command depends mostly on the level of detail you provide. When capturing a Command, you can, for example:
  • Use the current conversation Example 
    Create a Packmind command for adding a new endpoint based on your last suggested changes.
  • Mention example files or directories Example 
    Using the file `MyPageFile.tsx`, create a Packmind command for bootstrapping a new page in the frontend.
  • Use a Git commit diff Example 
    Read commit abcd123 and create a command for migrating an Angular component to React.

​
What Makes a Good Command

  • Clear purpose — The command name and summary clearly explain what it accomplishes
  • Realistic scenarios — The “When to use” section covers actual situations your team encounters
  • Validation checkpoints — Questions clarify prerequisites and assumptions
  • Actionable steps — Each step is specific and can be completed independently
  • Helpful examples — Code snippets demonstrate what to do, not just explain it