Build High-Quality Software

Faster with Spec Kit

Spec Kit revolutionizes software development by making specifications executable. With Spec Kit, transform your ideas into working code using AI-powered specification-driven development.

28K+ GitHub Stars

11+ AI Agents

2.3K+ Forks

MIT Open Source

What is Spec Kit’s Spec-Driven Development?

Spec Kit introduces a revolutionary approach that puts specifications first, transforming how developers build software with AI assistance

📋

Traditional Development

Code has been king for decades. Specifications were just scaffolding we built and discarded once the "real work" of coding began. This leads to miscommunication and technical debt.

⚡

Spec Kit’s Approach

With Spec Kit, specifications become executable, directly generating working implementations. Spec Kit helps you focus on product scenarios rather than writing undifferentiated code.

Spec Kit Core Philosophy

Spec Kit’s Spec-Driven Development allows organizations to focus on product scenarios rather than writing undifferentiated code. Spec Kit achieves this with AI-powered specification execution.

🎯

Focus on What

Define what you want to build and why, not the technical implementation details

🤖

AI-Powered

Leverage AI agents to transform specifications into working code automatically

🚀

Faster Delivery

Reduce development time by eliminating the gap between specification and implementation

Quick Start with Spec Kit

Get up and running with Spec Kit in minutes. Follow this Spec Kit tutorial to start building better software today.

1

Install Specify

Install the Specify CLI tool using your preferred package manager.

uv tool install specify-cli –from git+https://github.com/github/spec-kit.git specify –version

2

Initialize Project

Create a new project with your preferred AI agent integration.

specify init my-project –ai claude specify init my-project –ai copilot

3

Create Specification

Use the /specify command to describe what you want to build.

/specify Build a task management app with user authentication, real-time collaboration, and mobile support. Users should be able to create projects, assign tasks, and track progress with Kanban boards.

4

Generate & Implement

Create technical plans and implement your specification automatically.

/plan Use React with TypeScript, Node.js backend, PostgreSQL database /tasks /implement

Spec Kit Usage Guide

Complete Spec Kit documentation for mastering Spec-Driven Development with our comprehensive toolkit

Slash Commands Reference

After running Spec Kit’s specify init, your AI coding agent will have access to these Spec Kit structured development commands:

Command	Description	Usage
/constitution	Create project governing principles and development guidelines	Run first to establish project standards
/specify	Define what you want to build (requirements and user stories)	Focus on the what and why, not tech stack
/clarify	Clarify underspecified areas through structured questioning	Must run before /plan unless explicitly skipped
/plan	Create technical implementation plans with chosen tech stack	Specify architecture, frameworks, and technical decisions
/tasks	Generate actionable task lists for implementation	Breaks down plan into executable steps
/analyze	Cross-artifact consistency & coverage analysis	Run after /tasks, before /implement
/implement	Execute all tasks to build the feature according to plan	Generates working code from specifications

Development Workflow

Follow this structured approach for optimal results with Spec-Driven Development:

Phase 1: Foundation

1. Constitution: Establish project principles
2. Specification: Define requirements clearly
3. Clarification: Resolve ambiguities

/constitution Focus on code quality, testing, UX consistency /specify Build a photo album organizer with drag-and-drop... /clarify

Phase 2: Implementation

1. Planning: Choose tech stack and architecture
2. Tasks: Break down into actionable items
3. Implementation: Generate working code

/plan Use Vite, vanilla JS, SQLite for local storage /tasks /implement

CLI Reference

Complete reference for the specify command-line tool:

Installation Options

uv tool install specify-cli –from git+https://github.com/github/spec-kit.git uvx –from git+https://github.com/github/spec-kit.git specify init my-project specify check

Common Commands

specify init my-project –ai claude specify init my-project –ai copilot specify init my-project –ai cursor specify init . –ai claude specify init –here –ai copilot specify init my-project –ai gemini –no-git specify init my-project –ai claude –debug

Real-World Examples

Learn from these practical examples of Spec-Driven Development in action:

Taskify - Team Productivity Platform

A complete Kanban-style project management tool with multiple users, drag-and-drop functionality, and real-time collaboration.

/specify Develop Taskify, a team productivity platform. Allow users to create projects, add team members, assign tasks, comment and move tasks between boards in Kanban style...

Full-stack Real-time Collaboration

Photo Album Organizer

A local photo management application with drag-and-drop organization, date-based grouping, and tile-based preview interface.

/specify Build an application that can help me organize my photos in separate photo albums. Albums are grouped by date and can be re-organized by dragging and dropping...

Local Storage Drag & Drop Media

Troubleshooting

Common issues and solutions when working with Spec Kit:

Git Credential Manager (Linux)

If you’re having Git authentication issues on Linux:

wget https://github.com/git-ecosystem/git-credential-manager/releases/download/v2.6.1/gcm-linux_amd64.2.6.1.deb sudo dpkg -i gcm-linux_amd64.2.6.1.deb git config –global credential.helper manager

Environment Variables

Set these variables for specific use cases:

export SPECIFY_FEATURE=001-photo-albums export GITHUB_TOKEN=ghp_your_token_here

Spec Kit Supported AI Agents

Choose from 11+ popular AI coding assistants that integrate seamlessly with Spec Kit. These AI agents work perfectly with Spec Kit’s specification-driven approach.

Anthropic’s powerful AI with exceptional specification understanding and multi-language support. Perfect for complex Spec Kit projects requiring context-aware programming and specification-driven development.

Native VS Code integration with enterprise security. Trusted by millions of developers worldwide with seamless GitHub ecosystem integration.

AI-first code editor designed for modern development. Fast performance with intuitive AI integration built for the future of coding.

Google’s advanced AI model with strong reasoning capabilities and comprehensive programming language support.

Advanced AI coding assistant with real-time collaboration features and intelligent code generation capabilities.

OpenAI’s Codex with some limitations. Does not support custom arguments for slash commands due to platform restrictions.

Plus 5 more agents: Qwen Code, opencode, Kilo Code, Auggie CLI, and Roo Code

Download & Install Spec Kit

Get started with Spec Kit using your preferred Spec Kit installation method. Download Spec Kit today and transform your development workflow.

Recommended Installation

Install once and use everywhere with uv tool management:

uv tool install specify-cli –from git+https://github.com/github/spec-kit.git specify –version specify check

Recommended Persistent Easy Updates

One-Time Usage

Run directly without installing for quick testing:

uvx –from git+https://github.com/github/spec-kit.git specify init my-project uvx –from git+https://github.com/github/spec-kit.git specify init my-project –ai claude

Quick Test No Installation Temporary

System Requirements

Required

• ✅ Python 3.8+
• ✅ Git 2.20+
• ✅ Internet connection

Recommended

• ✅ VS Code or Cursor
• ✅ AI Agent subscription
• ✅ uv package manager

Optional

• ⚪ Docker
• ⚪ GitHub CLI
• ⚪ Node.js (for web projects)