What it does
Spec Kit is an open source toolkit that gives AI coding agents structured processes, reusable templates and documented outcomes. You install a specify command-line tool, initialise a project for your chosen coding agent, then run the provided skills inside that agent's chat. The main process is Spec-Driven Development: a constitution once per project, then specify, plan, tasks, implement and converge for each feature, with optional clarification, checklist and consistency-analysis steps. Bug fixing (assess, fix, test) and idea assessment (intake through decide) are optional extensions you add with the CLI. Beyond the built-in processes, extensions, presets, workflows and bundles let you add commands, enforce standards, automate steps or package a setup for a role. Community catalogs are available, and the page warns that listings are not audits, so community code should be reviewed before use. It needs Python 3.11 or later, uv and a supported AI coding agent, on Linux, macOS or Windows.
Capabilities
- specify CLI to install and initialise projects
- Spec-driven flow from specification to plan, tasks and implementation
- Optional bug-fixing and idea-assessment processes
- Extensions, presets, workflows and bundles for customisation
- Community catalogs plus private, self-hosted catalogs
- Integrations for switching between supported coding agents
When to use it
- You want your coding agent to work from a written spec and plan instead of ad hoc prompts
- You need a repeatable bug-fix process with recorded verification
- You want to enforce team standards through presets or custom workflows
- You want to assess an idea with evidence before committing to build it
