spec-kit
spec-kit is a toolkit that gives AI coding agents step-by-step processes and templates for building features, fixing bugs, and assessing ideas for developers and vibe coders.
What it is good for
- Turning a feature idea into a written spec before coding
- Fixing a bug with a recorded cause and verification
- Deciding whether an idea is worth building
- Keeping an AI coding agent on a consistent process
At a glance
- Who it is for
- Setup difficulty
- Technical ยท Guided command-line setup
Level 4 of 5. You copy and paste commands into a terminal by following the instructions. Comfortable territory for vibe coders.
- Cost
- Free and open source
- Type
- Skill or plugin
- Tasks
- Works with
- GitHub Copilot, Linux, macOS, Windows
How to get started with spec-kit
- Install Python 3.11+ and uv, and have a supported AI coding agent ready.
- Run
uv tool install specify-cliin your terminal. - Run
specify init my-project --integration copilot, thencd my-project. - Launch your coding agent in the project folder.
- Run
/speckit-constitutionin the agent chat, then/speckit-specifywith a description of what to build.
From the project's own documentation. If a step does not match what you see, the official pages have the latest instructions.
Before you try it
- Requires Python 3.11+, uv, and a supported AI coding agent.
- Commands run in the agent's chat, one at a time, with each result reviewed first.
- Community catalog components are not audited, so review their source code before installing.
- Bug fixing and idea assessment are extensions you install separately.
Momentum
- Rank this week
- Not ranked (last #6, week 45, 2026)
- Best rank
- #6 week 45, 2026
- GitHub stars
- 150,013
GitHub numbers as of Nov 16, 2026. Updated weekly.
Ranking history
Official links
Questions
- Is spec-kit free?
- Yes. It is free and open source (MIT license).
- Do I need to know how to code to use spec-kit?
- You do not need to write code, but setup means copying and pasting commands into a terminal by following its instructions.
- What does spec-kit work with?
- According to its own documentation, it works with GitHub Copilot, Linux, macOS, and Windows.
- How do I get started with spec-kit?
- 1. Install Python 3.11+ and uv, and have a supported AI coding agent ready. 2. Run uv tool install specify-cli in your terminal. 3. Run specify init my-project --integration copilot, then cd my-project. 4. Launch your coding agent in the project folder. 5. Run /speckit-constitution in the agent chat, then /speckit-specify with a description of what to build.
- What should I know before trying spec-kit?
- Requires Python 3.11+, uv, and a supported AI coding agent. Commands run in the agent's chat, one at a time, with each result reviewed first. Community catalog components are not audited, so review their source code before installing. Bug fixing and idea assessment are extensions you install separately.
- What is spec-kit good for?
- Turning a feature idea into a written spec before coding, fixing a bug with a recorded cause and verification, deciding whether an idea is worth building, and keeping an AI coding agent on a consistent process.
Similar agents to spec-kit
- OpenSpec
Also adds written plans and slash commands, but focuses on agreeing on specs rather than offering bug fixing and assessment processes.
- BMAD-METHOD
A framework guiding planning and building with explicit decisions, rather than a set of swappable processes and extensions.
- agent-skills
Skill files that make agents follow senior engineering workflows, without spec-driven templates or a command line tool.
- ECC
A plugin with plan, test, review and memory workflows, mainly built around Claude Code.
- Claude Code
A coding agent itself that writes code in the terminal, rather than a process toolkit used with agents.
- Superpowers
Superpowers is a skill plugin that makes coding agents plan, test, and review their work step by step for people building software with AI.