</>MCP Agents Market
Skill

superpowers

by obra272.8kShellUpdated 2026-08-13

An agentic skills framework & software development methodology that works.

Claude CodeCursorCodexGitHub Copilot CLIGemini CLIDevin CLIAntigravityGrok Build CLI

Superpowers is an agentic skills framework and complete software development methodology that guides AI coding agents through structured workflows from design to deployment. It enforces test-driven development, systematic planning, and subagent-driven execution, enabling coding agents to work autonomously for extended periods without deviating from approved specifications. The framework provides composable skills that automatically activate at appropriate stages, transforming coding agents into disciplined engineers that brainstorm designs, break work into testable tasks, and verify results before completion.

Key Features

Automatic skill activation based on workflow stage—brainstorming triggers before coding begins, test-driven-development enforces RED-GREEN-REFACTOR cycles
Subagent-driven development with two-stage review (spec compliance check followed by code quality review) for autonomous task execution
Git worktree integration creates isolated development branches with clean test baselines for parallel work streams
Structured planning breaks projects into 2-5 minute tasks with exact file paths, complete code snippets, and verification steps
Socratic brainstorming skill that extracts specifications through questions and presents designs in digestible chunks for approval
Built-in code review workflows with severity-based issue blocking and systematic debugging processes
Composable skills library covering testing, debugging, collaboration, and meta-workflows like skill creation
Cross-platform plugin support for Claude Code, Cursor, Codex, Gemini CLI, GitHub Copilot CLI, Devin CLI, and 10+ other AI coding environments

Use Cases

  • 01Enabling AI coding agents to autonomously implement approved software designs for hours without manual intervention or scope drift
  • 02Enforcing test-first development practices where agents write failing tests, verify failures, implement minimal code, and commit only after green tests
  • 03Coordinating multiple subagents on parallel tasks with automatic spec compliance and quality reviews before integration
  • 04Refining vague project ideas into validated technical specifications through structured questioning before any code is written
  • 05Managing feature branches with isolated worktrees that maintain clean test baselines and provide merge-or-PR workflows at completion
  • 06Creating custom agent skills and workflows that follow testing methodology and work across multiple AI coding platforms

Related Skills

View more

awesome

😎 Awesome lists about all kinds of interesting topics

Skill496.6k

skills

Skills for Real Engineers. Straight from my .agents directory.

Skill219.3k

andrej-karpathy-skills

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

Skill203.1k

claw-code

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

Skill195.1k

superpowers — FAQ

What is Superpowers and how does it work with AI coding agents?+

Superpowers is a skills framework that provides AI coding agents with a structured software development methodology. It automatically activates composable skills at appropriate workflow stages—brainstorming before coding, planning after design approval, test-driven development during implementation—guiding agents through design, planning, testing, and review without requiring manual skill invocation.

How do I install Superpowers for my coding agent?+

Installation varies by platform: Claude Code users run `/plugin install superpowers@claude-plugins-official`, Cursor users type `/add-plugin superpowers`, Codex CLI users search via `/plugins`, and GitHub Copilot CLI users first register the marketplace then install the plugin. Each coding environment has specific installation commands detailed in the documentation, and you must install separately for each platform you use.

Which AI coding clients and platforms work with Superpowers?+

Superpowers supports Claude Code, Antigravity, Codex App and CLI, Cursor, Devin CLI, Factory Droid, Gemini CLI, GitHub Copilot CLI, Grok Build CLI, Kimi Code, OpenCode, Pi, and Hermes Agent. Each platform requires separate installation and may have platform-specific setup steps.

Does Superpowers require API keys or special prerequisites?+

Superpowers itself does not require API keys—it extends the capabilities of your existing AI coding agent. You need a working installation of a compatible coding agent platform (like Claude Code or Cursor) and Git for the worktree and version control features.

Is Superpowers free and open source?+

Yes, Superpowers is released under the MIT License and available for free. Commercial support, additional tooling, and managed spending services are available for enterprise users through Prime Radiant.

What is subagent-driven development in Superpowers?+

Subagent-driven development dispatches a fresh AI subagent for each planned task, with two-stage review checking spec compliance first and code quality second. This allows your primary agent to work autonomously through implementation plans for extended periods while maintaining quality standards and adherence to approved designs.

How do I install superpowers?+

Open the source repository on GitHub and follow its README. superpowers is a skill — MCP Agents Market links you directly to the official repo.

Is superpowers free?+

superpowers is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.

Related searches

Developer Tools SkillsTesting SkillsPlanning SkillsBest MCP ServersBest PluginsBest AgentsTop rated listingsClaude Code toolsBrowse all categories