kiro

Spec-Driven Development Guide

A comprehensive guide to systematic feature development using the three-phase spec process: Requirements → Design → Tasks.

Used by

• @kazini in their spec kit https://github.com/kazini/yask-spec-kit
• Amazon in internal presentations: "It’s the best stuff I have found on [spec driven development]. I will be sharing links back to your repo with full attribution."

Navigation Guide

New to spec-driven development? → Start with Methodology Overview
Ready to create your first spec? → Jump to Process Guide
Looking for examples? → Browse Examples & Case Studies
Need templates? → Get Ready-to-Use Templates
Working with AI? → Learn Prompting Strategies

** Need detailed navigation?** → See Complete Navigation Index - Find content by role, problem, or learning style

Complete Table of Contents

Methodology

Learn the foundational concepts and philosophy behind spec-driven development

• Overview - Core concepts and benefits
• Philosophy - Why spec-driven development works
• When to Use - Decision framework and scenarios

Process Guide

Step-by-step walkthrough of the three-phase workflow

• Requirements Phase - Gathering and structuring requirements using EARS
• Design Phase - Creating comprehensive design documents
• Tasks Phase - Breaking down design into actionable coding tasks
• Workflow Diagrams - Visual process flows and decision points

AI Reasoning

Insights into decision-making frameworks and thought processes

• Decision Frameworks - How choices are evaluated
• Thought Processes - Analysis and prioritization methods
• Examples - Real reasoning chains and decision points

Prompting Strategies

Effective communication techniques for AI collaboration

• Strategies - Core prompting approaches
• Templates - Ready-to-use prompt patterns
• Best Practices - Tips for clear, effective communication

⚡ Execution Guide

Practical guidance for implementing features from specs

• Implementation Guide - Step-by-step execution strategies
• Quality Assurance - Testing and validation techniques
• Troubleshooting - Common issues and solutions

Resources

Curated references and learning materials

• Standards - EARS and industry standards
• Tools - Recommended tools and integrations
• Further Reading - Additional learning resources

Examples

Real-world case studies and complete spec examples

• Simple Feature Specs - Basic feature examples
• Complex System Specs - Large system examples
• Case Studies - Success stories and lessons learned
• Troubleshooting & Pitfalls - Common mistakes and recovery strategies

Templates

Ready-to-use templates and checklists

• Requirements Template - EARS-formatted requirements
• Design Template - Comprehensive design structure
• Tasks Template - Implementation planning format

Quick Start

New to spec-driven development? Start here:

1. Understand the Methodology - Read the Overview to grasp core concepts
2. See It in Action - Review a Simple Feature Spec example
3. Try It Yourself - Use the Requirements Template for your first spec
4. Get Better Results - Apply Prompting Strategies for AI collaboration

Navigation Tips

• Process sections provide step-by-step instructions
• AI Reasoning sections explain the "why" behind decisions
• Prompting sections help you communicate effectively with AI
• Examples show complete, real-world applications
• Templates give you ready-to-use starting points

Cross-References & Related Content

By Workflow Phase

• Planning Phase: Methodology → Requirements → Design → Tasks
• Execution Phase: Implementation Guide → Quality Assurance
• AI Collaboration: Prompting Strategies → AI Reasoning → Best Practices

By Experience Level

• Beginner: Methodology → Simple Examples → Templates
• Intermediate: Process Guide → Prompting Strategies → Case Studies
• Advanced: AI Reasoning → Complex Examples → Decision Frameworks

Quick Problem Solving

• Unclear Requirements → Requirements Phase + EARS Standards
• Design Challenges → Design Phase + AI Decision Frameworks
• Implementation Issues → Implementation Guide + Troubleshooting
• AI Communication Problems → Prompting Best Practices + Troubleshooting

Kiro MCP Server

The Kiro MCP Server exposes Kiro's system prompts and instructions through the Model Context Protocol (MCP), allowing other AI assistants and tools to access Kiro's best practices.

Features

• Resources: Access all Kiro system documentation files via MCP resources
• Tools: Query and retrieve specific system instructions programmatically
• Prompts: Pre-configured prompts for common Kiro workflows

Quick Start

Install and configure the MCP server:

# Using uvx (recommended)
uvx kiro-mcp-server

# Or install with pip
pip install kiro-mcp-server

Add to your MCP client configuration (e.g., ~/.kiro/settings/mcp.json):

{
  "mcpServers": {
    "kiro-prompts": {
      "command": "uvx",
      "args": ["kiro-mcp-server"],
      "disabled": false
    }
  }
}

For more details, see the MCP Server Documentation.

Claude Code Plugin

Kiro is available as an installable Claude Code plugin with 7 skills following the agentskills.io specification.

Quick Install

# In Claude Code
/plugin marketplace add https://github.com/jasonkneen/kiro
/plugin install kiro-spec-driven@kiro-marketplace

Available Skills

Once installed, Claude automatically uses these skills when relevant:

Installation Options

# User scope (available everywhere)
/plugin install kiro-spec-driven@kiro-marketplace

# Project scope (shared via git)
/plugin install kiro-spec-driven@kiro-marketplace --scope project

Validate Skills

./scripts/validate-skills.sh

For more details, see the Plugin Documentation and Skills Documentation.

This guide is designed to be both a learning resource and a reference manual. Jump to any section based on your current needs, or read through sequentially for comprehensive understanding.

** For detailed navigation by role, problem, or learning style, see the Complete Navigation Index**