Getting Started#

Welcome to doyaken! This comprehensive guide will help you install doyaken and run your first AI-powered development session in minutes.

Prerequisites#

Before installing doyaken, ensure you have:

• Node.js 18 or later (download)
• A code editor (VS Code recommended)
• An API key from one of the supported AI providers (Anthropic, OpenAI, or others)

Installation#

Quick Install (Recommended)#

The fastest way to get started is using npx. This runs doyaken without any permanent installation:

npx @doyaken/doyaken

Global Installation#

For a permanent installation that you can run from anywhere:

# Using npm
npm install -g @doyaken/doyaken

# Using pnpm
pnpm add -g @doyaken/doyaken

# Using yarn
yarn global add @doyaken/doyaken

After global installation, you can run doyaken with:

doyaken
# or the shorthand
dk

Verify Installation#

Check that doyaken is installed correctly:

dk --version

Configuration#

API Key Setup#

doyaken needs an API key to communicate with AI models. Set it as an environment variable:

# For Anthropic Claude (recommended)
export ANTHROPIC_API_KEY="your-api-key-here"

# For OpenAI
export OPENAI_API_KEY="your-api-key-here"

For permanent configuration, add this to your shell profile (~/.bashrc, ~/.zshrc, etc.).

Project Configuration#

Initialize doyaken in your project to create a configuration file:

dk init

This creates a .doyaken/ directory with:

• config.toml - Project settings
• tasks/ - Task management directories
• skills/ - Custom AI skills

Quick Start Workflow#

Step 1: Start doyaken#

Navigate to your project directory and start an interactive session:

cd your-project
dk

Step 2: Describe Your Task#

Give doyaken a task in natural language:

doyaken > "Create a REST API endpoint for user registration"

Step 3: Review the Plan#

doyaken analyzes your codebase and creates an implementation plan. Review it before proceeding:

📋 Implementation Plan:
1. Create UserController with registration endpoint
2. Add input validation schema
3. Implement password hashing
4. Add database migration for users table
5. Write unit tests

Proceed? [Y/n]

Step 4: Watch It Build#

Once approved, doyaken writes the code, following your project's patterns and best practices.

Step 5: Review Changes#

Review the changes, request modifications, or approve:

doyaken > "Add email verification to the registration flow"

Basic Commands#

Here are the essential commands to get you started:

| Command | Description | | ---------------------- | ------------------------- | | dk | Start interactive session | | dk run | Run tasks from taskboard | | dk run 3 | Run 3 tasks in parallel | | dk tasks | List all project tasks | | dk tasks new "title" | Create a new task | | dk skills | List available skills | | dk doctor | Diagnose your setup | | dk init | Initialize a new project |

Example Tasks#

Try these examples to get familiar with doyaken:

Fix a Bug#

doyaken > "Fix the login timeout issue where sessions expire too quickly"

Add a Feature#

doyaken > "Add email verification to the signup flow with a 24-hour expiry"

Refactor Code#

doyaken > "Refactor the authentication module to use dependency injection"

Write Tests#

doyaken > "Add unit tests for the payment processing module"

Code Review#

doyaken > "/review Check the auth module for security vulnerabilities"

Using Skills#

Skills are specialized AI commands for common tasks. Invoke them with a slash:

# Create a detailed implementation plan
doyaken > /plan "Design the multi-tenant architecture"

# Review code for issues
doyaken > /review "Check for security vulnerabilities"

# Refactor code
doyaken > /refactor "Improve the database query performance"

# Generate documentation
doyaken > /document "Create API documentation"

List available skills:

dk skills

Task Management#

doyaken includes built-in task management with a kanban-style workflow:

View Tasks#

dk tasks

Shows tasks organized by status: todo, doing, done.

Create Tasks#

dk tasks new "Implement user dashboard"

Run Tasks#

# Run the next task
dk run

# Run multiple tasks in parallel
dk run 3

Troubleshooting#

Check Your Setup#

Run the doctor command to diagnose issues:

dk doctor

This verifies:

• ✅ Project configuration
• ✅ API key is set
• ✅ AI provider is accessible
• ✅ Dependencies are installed

Common Issues#

"API key not found"

• Ensure your API key environment variable is set
• Restart your terminal after adding it to your shell profile

"Model not available"

• Check your API key has access to the requested model
• Try a different model with --model flag

"Project not recognized"

• Run dk init to initialize doyaken in your project
• Ensure you're in the project root directory

Next Steps#

Now that you're up and running:

• 📖 Read the CLI Reference for all available commands
• ⚙️ Learn about Configuration options
• 🚀 Explore the Dashboard for project management