Spec-driven workspace for software development with AI
Skaro shows the current project state on a single start page: launch stages, active tasks, phases, progress, and the next point to continue from. This helps preserve context between AI sessions and keep delivery under control.
Tasks turn implementation into a clear working system: what should be done now, what is planned next, and what has already been completed. This helps development move consistently without losing context and keeps daily work connected to architecture and the overall project plan.
Project architecture is stored as a first-class artifact in the repository instead of being left in chats. In Skaro, it can be reviewed, edited, agreed on, and used as a foundation for implementation.
DevPlan captures the project roadmap: milestones, tasks, priorities, and execution order. It can be updated as the project evolves while preserving alignment between the idea, the architecture, and actual implementation.
Key architectural decisions are documented as ADRs with statuses and history. This makes it explicit why a decision was made and prevents the team from repeatedly revisiting the same questions.
The dashboard includes status, diff, stage, unstage, commit, push, branch switching, and automatic commits when a task is completed. Changes produced in AI cycles can be reviewed, packaged, and sent without leaving the working context.
Two commands to get started
skaro init creates the .skaro/ structure in your project, then skaro ui starts the local web dashboard.
Artifacts and working phases
Skaro adds a layer of artifacts and managed phases on top of the repository: from project rules and architecture to tasks, tests, and final review.
Git integration
View changes, inspect diffs, stage files, commit, push, and work with branches directly in the dashboard.
Status and token usage
Track project status, task progress, and token usage by phase, task, model, and role.
AI chats and fix cycles
Contextual AI chats are available for architecture, the project, tasks, and feature planning. Separate fix modes are available for tasks and the full project.
Skills and execution environment
You can connect stack-specific skills and choose where verify commands run: on the host, in a Docker Compose service, or through a command prefix.
Different models for different roles
Skaro lets you assign separate models to architect, coder, and reviewer roles to split architectural, implementation, and validation work.
Architect
Used for architecture, devplan, feature planning, and project import analysis.
Coder
Used for task implementation and fix cycles when you need fast, practical work in code.
Reviewer
Used for clarify, checks, and other phases where questions, validation, and quality control matter most.
Constitution presets for common stacks
Skaro includes ready-made constitution templates for common frontend, backend, and mobile stacks. You can use them as a starting point and adapt them to your project.