engineering / skill
Spec Kit
Give your AI coding agent structured processes for building features from a spec, fixing bugs and assessing ideas.
At a glance
- Purpose
- Give your AI coding agent structured processes for building features from a spec, fixing bugs and assessing ideas.
- Runs in
- Local agent with shell
- Operating systems
- macOS, Linux, Windows
- Needs
- Runtime: Python 3.11+ and uv; Needs internet: Not stated; Needs accounts or API keys beyond your agent: Not stated
- Files and data
- Reads files: Yes; Writes files: Yes; Sends data to other services: Not stated
- Tool type
- Skill
- Delivery
- From GitHub
- Version
- Latest on the main branch
- Access
- Code on GitHub
- Compatibility
- The README names GitHub Copilot in its examples and says another supported AI coding agent works by replacing copilot with its integration key, on Linux, macOS or Windows, according to the README. It points to an integrations reference for the other supported agents.
- External costs
- The repository is MIT-licensed and states no pricing. Your coding agent or model provider may charge for usage.
- Permissions
- The skills act through your coding agent with the access you give it. According to the README, specify init creates a project, and the skills write reports and artifacts into folders under .specify in that project, for example for bugs and assessments. The README describes skills for implementing features and fixing bugs, which your agent carries out in your project.
- Usage terms
- MIT License, as stated in the repository. See its LICENSE file for the exact terms.
Code on GitHub
github/spec-kit
MIT💫 Toolkit to help you get started with SDD or any other process!
Topics: ai copilot development engineering prd spec spec-driven
Public GitHub data fetched · 0 days old
Skill folders in this repository (2)
Folders that contain a SKILL.md file, from GitHub's file list on .
What it does
Spec Kit is an open source toolkit that, according to the README, gives AI coding agents structured processes, reusable templates and documented outcomes. The README offers three independent entry points that you can start with, customize or replace with your own.Spec-Driven Development ships in core. The README shows a constitution step once per project, then specify, plan, tasks, implement and converge for each feature, each run as a skill in your agent's chat, such as /speckit-specify and /speckit-plan. Bug fixing (assess, fix, test) and idea assessment (intake, research, define, shape, decide) are bundled extensions that you install when needed. The README says the reports and artifacts go into folders under .specify in your project.
The README also describes extensions, presets, workflows and bundles for customizing the processes, and links to documentation with a command line reference.
Who it is for
People who build software with an AI coding agent and want a defined process for specifications, bug fixes or idea assessment.Example tasks
Write project principles with the constitution skill before starting a feature.Specify a feature, plan it, break it into tasks and implement it.
Assess a bug, fix it and test the fix.
Assess an idea with the intake, research, define, shape and decide steps.
Add the bug or assess extension to a project.