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
Official Compound Engineering plugin for Claude Code, Codex, Cursor, and more
这个仓库详情页已经具备足够的原创分析、来源证据和同类对比，可以作为 Git-Stars 的可索引评测页。
100
评测分
解决的问题
This framework addresses the fragmentation of AI agent capabilities across different coding tools by providing a unified, portable skill layer. It solves the problem of agents starting from scratch on each task, instead enabling cumulative learning and consistent behavior, which reduces repetitive setup and improves efficiency over time.
部署现实
当前可用的安装信号是：/plugin marketplace add EveryInc/compound-engineering-plugin。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 and enhance AI-assisted workflows for code review, research, and iterative development within their existing editors. The plugin enables specialized reviewer and research behaviors, custom tool mappings, and profile-specific configurations, allowing teams to standardize agent behavior across multiple platforms. The ceiling includes fully customized agent pipelines that compound in efficiency, though it is limited to prompt-based skills rather than deep code execution.
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。
EveryInc/compound-engineering-plugin 被追踪为 TypeScript 项目，主要属于 AI App, Automation 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 24k Star，今日 +40，本周 +0，本月 +0。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 70 天，未关闭 Issue 为 92，约占总 Star 的 0.39%。这只是采用信号，不替代工程尽调。
采用检查：2.0k Fork 和 24k 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「TypeScript 技术栈团队评估生态原生工具」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 2 个明确来源引用，近期增长信号为 40。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
充分已附带仓库元数据和 README/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
24k 星标
复用
2.0k 复刻
关注
24k 关注者
维护
moderate
许可证
MIT
未解决 Issue
92
Compound Engineering is a plugin that provides AI skills to make each unit of engineering work easier than the last, focusing on planning, review, and knowledge compounding to reduce technical debt and improve efficiency. It supports multiple AI coding assistants including Claude Code, Cursor, Codex, and others.
核心特性
- Six-step workflow: brainstorm, plan, work, simplify, review, compound - Skills like /ce-brainstorm, /ce-plan, /ce-work, /ce-code-review, /ce-doc-review, /ce-compound - Supports multiple AI coding assistants (Claude Code, Cursor, Codex, etc.)
AI App
End-user AI applications and AI-native product examples
Automation
Workflow automation, integration glue, and orchestration
/plugin marketplace add EveryInc/compound-engineering-plugin70
健康评分
一般
提交活跃度
Oct 9, 2025
创建于
Aug 5, 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
EveryInc
GitHub 主页freeCodeCamp/freeCodeCamp
freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.
openclaw/openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
nilbuild/developer-roadmap
Interactive roadmaps, guides and other educational content to help developers grow in their careers.
vuejs/vue
This is the repo for Vue 2. For Vue 3, go to https://github.com/vuejs/core
n8n-io/n8n
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
✓
许可证
✓
Fork 情况
~ 一般
维护情况
解决的问题
This framework addresses the fragmentation of AI agent capabilities across different coding tools by providing a unified, portable skill layer. It solves the problem of agents starting from scratch on each task, instead enabling cumulative learning and consistent behavior, which reduces repetitive setup and improves efficiency over time.
能力范围
Developers can build and enhance AI-assisted workflows for code review, research, and iterative development within their existing editors. The plugin enables specialized reviewer and research behaviors, custom tool mappings, and profile-specific configurations, allowing teams to standardize agent behavior across multiple platforms. The ceiling includes fully customized agent pipelines that compound in efficiency, though it is limited to prompt-based skills rather than deep code execution.
结论
This plugin is ideal for development teams using multiple AI coding agents who want consistent, compounding skill enhancements without per-tool customizations. It is less suitable for those needing deep, code-level agent modifications or who rely on a single tool with built-in features. The key trade-off is the initial setup complexity across different platforms versus the long-term efficiency gains from standardized, reusable skills.