GitHub Spec Kit is an open-source toolkit that revolutionizes how developers build software by implementing Spec-Driven Development (SDD)—a methodology where specifications become executable artifacts rather than static documentation. Instead of coding from vague requirements, development teams create detailed specifications that directly generate working implementations through AI assistance.
Traditional software development treats specifications as secondary planning documents that quickly become outdated. Spec Kit flips this paradigm by making specifications the primary driver of code generation. This approach emphasizes defining what and why before addressing the how, resulting in higher quality software with reduced ambiguity and rework.
Modern development teams face several challenges:
Spec Kit addresses these challenges by treating specifications as the single source of truth that generates implementation. When your specification turns into working code automatically through AI assistants like Claude Code, Cursor, or Windsurf, it determines what gets built with precision and consistency.
Spec Kit provides eight specialized slash commands that guide AI coding agents through structured development phases:
| Command | Purpose | When to Use |
|---|---|---|
/speckit.constitution | Establish project governing principles | Project initialization, setting quality standards |
/speckit.specify | Define functional requirements and user stories | Capturing product vision, writing PRDs |
/speckit.plan | Create technical implementation strategies | Architecture decisions, tech stack selection |
/speckit.tasks | Generate actionable task lists | Breaking down work, sprint planning |
/speckit.implement | Execute tasks to build features | Active development, code generation |
| Command | Purpose | When to Use |
|---|---|---|
/speckit.clarify | Resolve underspecified areas | Identifying gaps, edge cases |
/speckit.analyze | Validate cross-artifact consistency | Quality checks, requirement traceability |
/speckit.checklist | Generate quality validation checklists | Pre-deployment verification, code review |
Spec Kit integrates seamlessly with 14+ AI coding agents, making it the most versatile specification-driven development toolkit available:
Fully Supported:
Limited Support:
This broad compatibility ensures teams can adopt Spec-Driven Development regardless of their preferred AI coding tool.
Begin by defining non-negotiable principles that govern your entire project:
# Initialize your spec-driven project
specify init my-project
cd my-project
# Create constitutional guidelines
# Use the /speckit.constitution command in your AI assistant
The constitution document establishes quality standards, architectural constraints, coding conventions, and security requirements that all subsequent work must honor.
Document functional requirements without getting into technical implementation details. Through iterative dialogue with your AI assistant, vague ideas transform into comprehensive Product Requirements Documents (PRDs). The AI asks clarifying questions, identifies edge cases, and helps define precise acceptance criteria—turning days of requirements gathering into hours.
Translate specifications into architectural decisions with documented rationale. The AI generates implementation plans that map requirements to technical choices, ensuring every technology decision traces back to specific product needs. This phase bridges the gap between "what we want" and "how we build it."
Break down plans into actionable development tasks. The AI decomposes complex features into manageable units of work, then executes them systematically. Because each task references the constitution and specifications, generated code maintains consistency with project standards.
Ensure cross-artifact consistency and completeness. These quality assurance commands catch specification gaps, verify requirement traceability, and generate comprehensive testing checklists before production deployment.
Before installing Spec Kit, ensure your system meets these requirements:
Option 1: Persistent Installation (Recommended)
Install Spec Kit globally for repeated use:
uv tool install specify-cli
Option 2: One-Time Execution
Run Spec Kit without installation using uvx:
uvx --from git+https://github.com/github/spec-kit.git specify init my-project
# Complete initialization sequence
specify init my-awesome-app
cd my-awesome-app
specify check
Building applications from scratch is where Spec Kit shines brightest. Teams can:
When evaluating technical approaches, Spec Kit enables parallel experimentation:
Adding features to existing systems benefits from specification clarity:
With 47,600+ GitHub stars and 4,100+ forks, Spec Kit represents one of the most significant open-source experiments in AI-assisted development methodology. The GitHub repository serves as the central hub for:
Released under the MIT License, Spec Kit enables unrestricted use in both open-source and commercial projects, fostering widespread adoption and ecosystem growth.
While Test-Driven Development (TDD) starts with tests that define behavior, Spec-Driven Development (SDD) begins with comprehensive specifications that define both behavior and rationale. SDD complements TDD by providing context that helps AI assistants generate appropriate tests alongside implementation code.
Traditional documentation-after-coding approaches treat specs as afterthoughts that quickly become outdated. SDD inverts this by making specifications the executable source that generates code, ensuring documentation and implementation never drift apart.
Your constitution.md should capture:
Excellent specifications include:
Get the most from AI assistants by:
The Spec Kit project welcomes contributions including:
Spec-Driven Development represents a fundamental shift in how software gets built. As AI coding assistants become more powerful, the quality of their output increasingly depends on the richness of input context. Spec Kit provides the structured methodology that transforms AI from a code completion tool into a true development partner that understands your project's vision, constraints, and quality standards.
Whether you're building greenfield applications, exploring technical approaches, or enhancing existing systems, GitHub Spec Kit offers a proven framework for leveraging AI assistance while maintaining control, consistency, and quality throughout the development lifecycle.
GitHub Spec Kit is an open-source toolkit that enables Spec-Driven Development (SDD), a methodology where specifications become executable artifacts rather than static documentation. It provides slash commands that guide AI coding assistants through structured development phases, transforming detailed specifications into working code while maintaining consistency with project standards.
Traditional development treats specifications as secondary documents that often become outdated. Spec-Driven Development inverts this by making specifications the primary source that generates implementation through AI assistance. This ensures documentation and code never drift apart, reduces ambiguity, and provides AI assistants with rich context for generating higher-quality code.
Spec Kit supports 14+ AI coding assistants including Claude Code, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Qwen Code, OpenCode, Kilo Code, Auggie CLI, CodeBuddy CLI, Roo Code, Codex CLI, Amp, and Amazon Q Developer CLI (limited support). This broad compatibility allows teams to adopt spec-driven workflows regardless of their preferred AI tool.
Yes, GitHub Spec Kit is completely free and open source, released under the MIT License. You can use it for personal projects, commercial applications, or contribute to its development. The only cost is for the AI coding assistant you choose to use with it, which varies by provider.
Install Spec Kit using uv tool install specify-cli, then initialize a project with specify init project-name. Run specify check to verify setup, then launch your AI coding assistant and start with the slash commands to establish project guidelines. Follow with specification commands to define requirements and continue through the structured workflow.
Spec Kit provides eight core commands: constitution establishes project principles, specify defines requirements, plan creates technical strategies, tasks generates actionable work items, implement executes development, clarify resolves gaps, analyze validates consistency, and checklist generates quality verification.
Yes, Spec Kit works excellently for adding features to existing systems (brownfield development). You can define new requirements through specifications without disrupting current code, ensure new features align with existing architecture, and generate implementation tasks that respect legacy constraints while maintaining documentation consistency.
Spec Kit requires Linux, macOS, or Windows, Python 3.11 or higher, Git, the uv package manager, and one of the 14 supported AI coding assistants. Installation is straightforward using uv tool install specify-cli for persistent use or uvx for one-time execution without installation.
SuperClaude: Open-source framework that transforms Claude Code with 19 specialized commands, 9 cognitive personas, and evidence-based development. 70% token optimization, deep research, git integration.
Universal database tool supporting 100+ databases with advanced SQL editor, ER diagrams, and data management. Free open-source Community Edition available.
Context7 is an open-source MCP server by Upstash that provides AI code editors with up-to-date, version-specific documentation through intelligent RAG and semantic caching.