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
A library of Agent Skills designed to work with the Stitch MCP server. Each skill follows the Agent Skills open standard, for compatibility with coding agents such as Antigravity, Gemini CLI, Claude Code, Cursor.
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。
75
评测分
解决的问题
This framework solves the fragmentation of agent capabilities by providing a standardized, interoperable set of skills that work across multiple coding agents. It eliminates the need to reimplement common functionalities for each agent, reducing duplication and ensuring consistent behavior.
部署现实
当前可用的安装信号是：Install via npm: `npm install @google-labs/stitch-skills` or clone the repo and link locally.。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 Apache-2.0。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 agents that perform file operations, code analysis, web scraping, API interactions, and other common development tasks using pre-built skills. Real-world use cases include automated code review assistants, project scaffolding tools, and intelligent debugging helpers. The ceiling is high: with the open standard, developers can create complex multi-step workflows by composing skills, and the library can grow with community contributions.
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。
google-labs-code/stitch-skills 被追踪为 TypeScript 项目，主要属于 AI Agent, MCP Server, Developer Tool, Infrastructure 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 7.9k Star，今日 +22，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 75 天，未关闭 Issue 为 16，约占总 Star 的 0.20%。这只是采用信号，不替代工程尽调。
采用检查：978 Fork 和 7.9k Watcher 反映项目被复用和关注的程度。许可证信号：Apache-2.0。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 1 个明确来源引用，近期增长信号为 22。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 Apache-2.0，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
7.9k 星标
复用
978 复刻
关注
7.9k 关注者
维护
moderate
许可证
Apache-2.0
未解决 Issue
16
Stitch Skills is a library of reusable, standardized agent skills designed to work with the Stitch MCP server. It provides a collection of modular capabilities that coding agents like Antigravity, Gemini CLI, Claude Code, and Cursor can leverage to perform common tasks, enabling rapid development and interoperability across different AI coding tools.
AI Agent
Agent frameworks, autonomous workflows, and tool-use systems
MCP Server
Model Context Protocol servers, clients, and integrations
Developer Tool
Tools that improve coding, testing, build, and local workflow
Infrastructure
Cloud, deployment, networking, containers, and platform tooling
Install via npm: `npm install @google-labs/stitch-skills` or clone the repo and link locally.63
健康评分
一般
提交活跃度
Jan 16, 2026
创建于
Jul 30, 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
google-labs-code
GitHub 主页codecrafters-io/build-your-own-x
Master programming by recreating your favorite technologies from scratch.
freeCodeCamp/freeCodeCamp
freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.
nilbuild/developer-roadmap
Interactive roadmaps, guides and other educational content to help developers grow in their careers.
awesome-selfhosted/awesome-selfhosted
A list of Free Software network services and web applications which can be hosted on your own servers
practical-tutorials/project-based-learning
Curated list of project-based tutorials
✓
许可证
✓
Fork 情况
~ 一般
维护情况
解决的问题
This framework solves the fragmentation of agent capabilities by providing a standardized, interoperable set of skills that work across multiple coding agents. It eliminates the need to reimplement common functionalities for each agent, reducing duplication and ensuring consistent behavior.
能力范围
Developers can build agents that perform file operations, code analysis, web scraping, API interactions, and other common development tasks using pre-built skills. Real-world use cases include automated code review assistants, project scaffolding tools, and intelligent debugging helpers. The ceiling is high: with the open standard, developers can create complex multi-step workflows by composing skills, and the library can grow with community contributions.
结论
This project is ideal for developers building AI coding agents who want to avoid reinventing the wheel and ensure compatibility across tools. It may be less useful for those needing highly specialized or non-standard agent behaviors. The key trade-off is standardization vs. flexibility: using these skills constrains you to the defined interfaces but provides interoperability and community support.