spec-kit
💫 Toolkit to help you get started with Spec-Driven Development
Spec Kit is an open-source toolkit for spec-driven development that enables developers to define software requirements before implementation with any AI coding agent. It provides a structured workflow where specifications become executable, directly generating working code through commands like /speckit.specify, /speckit.plan, and /speckit.implement. The toolkit supports 30+ AI coding assistants and can be customized through extensions, presets, and bundles for team-specific workflows.
Key Features
Use Cases
- 01Building new applications from high-level requirements through structured specification and automated task generation
- 02Modernizing legacy systems by creating specifications for existing codebases and planning iterative enhancements
- 03Exploring multiple implementation approaches in parallel with different technology stacks and architectures
- 04Enforcing enterprise compliance and organizational standards through custom presets and quality checklists
- 05Provisioning entire development teams with role-specific workflows and tooling through curated bundles
- 06Generating project governance documents and technical implementation plans that guide AI-assisted coding
Related Skills
View moreawesome
😎 Awesome lists about all kinds of interesting topics
superpowers
An agentic skills framework & software development methodology that works.
skills
Skills for Real Engineers. Straight from my .agents directory.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
spec-kit — FAQ
What is Spec Kit?+
Spec Kit is an open-source toolkit that implements spec-driven development, a methodology where you define what to build through structured specifications before AI coding agents generate the implementation. It provides CLI commands and templates that guide the process from requirements through to working code.
How do I install Spec Kit?+
Install the Specify CLI using uv with 'uv tool install specify-cli' or from the GitHub repository with 'uv tool install specify-cli --from git+https://github.com/github/spec-kit.git@vX.Y.Z'. After installation, run 'specify init my-project --integration copilot' to initialize a project with your chosen AI coding agent.
Which AI coding agents work with Spec Kit?+
Spec Kit supports 30+ AI coding agents including GitHub Copilot, Claude Desktop, Claude Code, Cursor, Windsurf, Codex CLI, Command Code, and many IDE-based assistants. Run 'specify integration list' to see all available integrations in your installed version.
What are the prerequisites for using Spec Kit?+
You need Python 3.11 or later, Git, uv package manager (or pipx as alternative), and a supported AI coding agent. No API keys are required for Spec Kit itself, though your chosen AI coding agent may require its own authentication.
Is Spec Kit free to use?+
Yes, Spec Kit is open source and licensed under the MIT License, making it free for both personal and commercial use. Community extensions, presets, and bundles are independently created and should be reviewed before installation.
What is the difference between extensions, presets, and bundles?+
Extensions add new commands and capabilities to Spec Kit, such as Jira integration or code review workflows. Presets customize how existing commands work by overriding templates and terminology. Bundles package multiple extensions and presets together into role-based setups installable with one command.
How do I install spec-kit?+
Open the source repository on GitHub and follow its README. spec-kit is a skill — MCP Agents Market links you directly to the official repo.
Is spec-kit free?+
spec-kit is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.