HoangNguyen0403/agent-skills-standard

Registry 信息

项目简介

一套关于编程语言与框架的智能体技能标准与最佳实践集，旨在帮助我们的AI智能体遵循各框架和编程语言的最佳实践准则。

要点

• 编程语言最佳实践集合
• 特定框架的标准与指南
• 专为AI智能体实施设计
• 多技术覆盖（Android、iOS、Web、后端）
• 基于TypeScript的代码库
• 社区驱动，拥有198个星标和60个分支

使用场景

• 遵循编码标准的AI智能体开发
• 特定框架最佳实践参考
• 编程规范AI模型训练
• 跨平台开发指南
• 自动化系统代码质量保证
• 编程模式教育资源

README 摘要

# Agent Skills Standard [](https://www.npmjs.com/package/agent-skills-standard) [](LICENSE) [](https://github.com/HoangNguyen0403/agent-skills-standard/stargazers) **The portable SDLC standards layer for AI coding agents. Sync once, then work in your own runtime.** **Current release:** `v2.4.6` — stricter BRD/PRD/SRS skills and templates (SMART, Gherkin AC, requirement cards) for EM + AI-agent readability. 259 ready-to-use coding standards for **Cursor, Claude Code, GitHub Copilot, Gemini, Windsurf, Trae, Kiro, Roo** and more — synced, versioned, and optimized to use **85% fewer tokens** than traditional prompt engineering. ```bash npx agent-skills-standard@latest init npx agent-skills-standard@latest sync # Done. Your AI now has portable team standards and SDLC workflows. ``` If `ags -V` still shows an old version after reinstalling, check your PATH order. `~/Library/pnpm` must come before `~/Library/pnpm/bin`, then run `hash -r` and verify with `ags -V` again. --- ## The Problem Every team has coding standards. But AI agents don't know them. You end up repeating the same instructions: _"Use OnPush change detection"_, _"Always wrap errors with context"_, _"No business logic in handlers"_. And every time, you face the same trade-off: - **Too many rules** = AI forgets them, wastes tokens, gets confused - **Too few rules** = AI writes generic code that doesn't match your standards - **Copy-paste `.cursorrules`** = out of date in a week, doesn't scale to teams ## The Solution Agent Ski

话题