隐私与广告选择
Git-Stars 会使用必要存储来保障网站运行。可选分析和广告测量脚本默认不加载，只有在你同意后，Google 等合作伙伴才可能按要求使用 Cookie 或类似标识符。 隐私政策
An agentic skills framework & software development methodology that works.
这个仓库详情页对访问者有帮助，但在补足原创证据和对比上下文前，Git-Stars 会暂时避免让它进入搜索索引。
90
评测分
解决的问题
Unlike naive agent prompts that lead to sloppy, untested code, Superpowers imposes a rigorous software engineering process—spec-first, TDD, YAGNI, DRY, and subagent review—that prevents common agent pitfalls like over-engineering, lack of testing, and context loss. It enables agents to work autonomously for hours on complex tasks without deviating from the plan.
部署现实
当前可用的安装信号是：For Claude Code: /plugin install superpowers@claude-plugins-official。这只能作为起点，正式使用前建议让 Codex 或 Claude 检查 README、环境变量、运行时版本和部署目标。
商业可用性
当前记录的许可证是 MIT。这是重要的商业使用信号，但仍应核验许可证全文、依赖许可证、模型/API 条款和商标限制。
能力上限
Developers can build full-stack applications, refactor large codebases, or implement complex features with minimal supervision. The framework supports multi-agent orchestration, automated testing, and iterative refinement, making it suitable for production-grade software development. Real-world use cases include building web apps, APIs, and data pipelines where code quality and reliability are paramount.
Git-Stars 是独立产品，不隶属于 GitHub 或该项目。 分析可能由 AI 辅助生成，依据公开仓库元数据和 README 的短摘要。 我们不镜像完整 README、文档、Issue 或社媒评论。
obra/superpowers 被追踪为 Shell 项目，主要属于 AI Agent 方向。这个评估结合公开 GitHub 元数据、分类信号、短来源摘要和 Git-Stars 编辑规则，而不是复制项目文档。
增长检查：该仓库目前有 273k Star，今日 +320，本周 +3.2k，本月 +16k。这些窗口用于区分持续采用信号和短期曝光峰值。
维护检查：当前活跃度为 一般；最近一次推送距今 62 天，未关闭 Issue 为 336，约占总 Star 的 0.12%。这只是采用信号，不替代工程尽调。
采用检查：24k Fork 和 273k Watcher 反映项目被复用和关注的程度。许可证信号：MIT。商业或内部使用前请核验许可证兼容性。
适用判断：当你需要「AI 原型、LLM 工作流和 Agent 类应用」时，这个项目更值得评估；如果「需要法律审查、安全审计或生产 SLA 保证」，则需要谨慎。
来源检查：Git-Stars 当前为这份报告保留了 1 个明确来源引用，近期增长信号为 16k。最终安装、安全和版本信息仍应以原始 GitHub 仓库为准。
原创分析
充分已经具备问题、能力和结论层面的原创判断。
来源
不足需要更清晰的来源引用。
许可证
充分已记录 MIT，可作为评估依据。
维护
充分仓库元数据中可以看到近期活跃信号。
同类对比
充分已有足够相近项目用于对比。
热度
273k 星标
复用
24k 复刻
关注
273k 关注者
维护
moderate
许可证
MIT
未解决 Issue
336
Superpowers is a complete software development methodology for coding agents, built on composable skills and initial instructions that ensure agents use them effectively.
核心特性
- Brainstorming: Refines ideas through questions and saves a design document. - Subagent-driven development: Dispatches subagents for each task with two-stage review. - Test-driven development: Enforces RED-GREEN-REFACTOR cycle for reliable code.
AI Agent
Agent frameworks, autonomous workflows, and tool-use systems
For Claude Code: /plugin install superpowers@claude-plugins-official80
健康评分
一般
提交活跃度
Oct 9, 2025
创建于
Aug 13, 2026
最近提交
每日同步积累数据后，Star 历史将在此显示。
复刻
未解决
关注者
obra
GitHub 主页affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
NousResearch/hermes-agent
The agent that grows with you
mattpocock/skills
Skills for Real Engineers. Straight from my .agents directory.
anomalyco/opencode
The open source coding agent.
ultraworkers/claw-code
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
✓
许可证
✓
Fork 情况
~ 一般
维护情况
解决的问题
Unlike naive agent prompts that lead to sloppy, untested code, Superpowers imposes a rigorous software engineering process—spec-first, TDD, YAGNI, DRY, and subagent review—that prevents common agent pitfalls like over-engineering, lack of testing, and context loss. It enables agents to work autonomously for hours on complex tasks without deviating from the plan.
能力范围
Developers can build full-stack applications, refactor large codebases, or implement complex features with minimal supervision. The framework supports multi-agent orchestration, automated testing, and iterative refinement, making it suitable for production-grade software development. Real-world use cases include building web apps, APIs, and data pipelines where code quality and reliability are paramount.
结论
Superpowers is ideal for developers who want their coding agents to produce production-quality code autonomously, especially on complex projects. It is less suited for quick prototyping or simple scripts where the overhead of the methodology outweighs the benefits. The key trade-off is upfront investment in learning the methodology for long-term gains in code quality and reduced supervision.