HoangNguyen0403/agent-skills-standard

Registry

Summary

A collection of Agent Skills Standard and Best Practice for Programming Languages and Frameworks, designed to help AI Agents follow best practices across various technologies.

Key features

• Collection of best practices for programming languages
• Framework-specific standards and guidelines
• Designed for AI Agent implementation
• Multi-technology coverage (Android, iOS, Web, Backend)
• TypeScript-based repository
• Community-driven with 198 stars and 60 forks

Use cases

• AI Agent development following coding standards
• Reference for framework-specific best practices
• Training AI models on programming conventions
• Cross-platform development guidelines
• Code quality assurance for automated systems
• Educational resource for programming patterns

README excerpt

# 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- **Too few rules** = AI writes generic code that doesn't match your standards - **Copy-paste `.cursorrules`** = out of date in a week, doesn't scale to teams ## The Solution Agent Ski

Topics