Code Lib / 代码库

更新于 a month ago

stitch-skills

Name: stitch-skills
Rating: 3.6 (243 reviews)
Author: google-labs-code

Ggoogle-labs-code

0.2k

google-labs-code/stitch-skills

Agent 评分

💡 摘要

一个用于转换和记录 Stitch 设计项目的标准化技能库，兼容多种 AI 编程助手。

🎯 适合人群

AI 智能体开发者设计系统工程师使用 Stitch 的前端开发人员技术产品经理

🤖 AI 吐槽: “这是一个规划整齐的技能停车场，但目前停放的车辆还太少。”

安全分析中风险

技能可能执行 `scripts/` 目录下的脚本，具有文件系统和网络访问权限，如果安装了恶意技能则存在风险。缓解措施：在安装前审计技能中的所有脚本，并在沙盒环境中运行。

Stitch Agent Skills

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.

Installation & Discovery

Install any skill from this repository using the add-skill CLI. This command will automatically detect your active coding agents and place the skill in the appropriate directory.

# List all available skills in this repository
npx add-skill google-labs-code/stitch-skills --list

# Install a specific skill (e.g., Stitch to React Components)
npx add-skill google-labs-code/stitch-skills --skill react:components --global

Available Skills

design-md

Analyzes Stitch projects and generates comprehensive DESIGN.md files documenting design systems in natural, semantic language optimized for Stitch screen generation.

react-components

Converts Stitch screens to React component systems with automated validation and design token consistency.

Repository Structure

Every directory within skills/ or at the root level follows a standardized structure to ensure the AI agent has everything it needs to perform "few-shot" learning and automated quality checks.

skills/[category]/
├── SKILL.md           — The "Mission Control" for the agent
├── scripts/           — Executable enforcers (Validation & Networking)
├── resources/         — The knowledge base (Checklists & Style Guides)
└── examples/          — The "Gold Standard" syntactically valid references

Adding New Skills

All new skills need to follow the file structure above to implement the Agent Skills open standard.

Great candidates for new skills

Validation: Skills that convert Stitch HTML to other UI frameworks and validate the syntax.
Decoupling Data: Skills that convert static design content into external mock data files.
Generate Designs: Skills that generate new design screens in Stitch from a given set of data.

This is not an officially supported Google product. This project is not eligible for the Google Open Source Software Vulnerability Rewards Program.

五维分析

清晰度8/10

创新性6/10

实用性7/10

完整性6/10

可维护性9/10

优缺点分析

优点

标准化结构确保了一致性和可发现性。
通过 add-skill CLI 为 AI 智能体提供了清晰的集成路径。
专注于自动化设计到代码的工作流程。

缺点

README 中展示的具体技能数量有限。
实用性完全依赖于 Stitch MCP 生态系统的采用。
缺乏技能执行和输出的详细示例。