A complete agentic skills framework and software development workflow for coding agents that enforces systematic processes like TDD and subagent-driven development.
Superpowers is an agentic skills framework and software development methodology for coding agents like Claude, Cursor, and GitHub Copilot. It provides a complete workflow that ensures agents follow systematic processes including brainstorming, test-driven development, subagent-driven development, and code review automation. The framework solves the problem of ad-hoc AI code generation by enforcing structured methodologies that produce higher quality, more maintainable code.
Developers using AI coding assistants (Claude Code, Cursor, Codex, OpenCode, GitHub Copilot, Gemini CLI) who want to implement systematic software development practices through their agents. Teams looking to standardize AI-assisted development workflows with enforced testing and review processes.
Developers choose Superpowers because it transforms coding agents from simple code generators into systematic engineering partners that enforce best practices automatically. Unlike basic AI coding tools, it provides mandatory workflows that ensure test-driven development, proper planning, and quality review processes without manual intervention.
An agentic skills framework & software development methodology that works.
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
Skills trigger automatically to enforce structured processes like brainstorming and TDD, reducing ad-hoc code generation without manual intervention, as highlighted in the README's workflow description.
Implements true red/green/refactor cycles and deletes code written before tests, ensuring higher code quality and adherence to TDD principles, as emphasized in the philosophy section.
Uses fresh subagents per task with two-stage reviews for spec compliance and code quality, enabling hours of autonomous work without deviation, as described in the subagent-driven-development skill.
Handles isolated Git worktrees, branch creation, and merge/PR decisions automatically, streamlining version control within AI-assisted development, as detailed in the using-git-worktrees skill.
Limited to specific AI coding assistants like Claude, Cursor, and others listed in installation; unsupported tools require manual setup or may not work, as shown in the fragmented installation docs.
Mandatory brainstorming, planning, and review phases can introduce unnecessary steps for trivial coding tasks, potentially slowing down quick fixes or minor changes.
Extending functionality requires following the 'writing-skills' skill with specific guidelines, which may have a steep learning curve for users not familiar with the framework's internals.