harmonyos-ai-skill — security grade SAFE, quality 65/100

Security audit verdict: SAFE · quality 65/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by DengShiyingA · Codex Skill · ★ 226

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is harmonyos-ai-skill safe to install? View the security audit →

About harmonyos-ai-skill

English | 简体中文 🧠 HarmonyOS AI Skill 鸿蒙最大的 AI 编程知识库 · 让 11+ AI 工具真正会写 ArkTS 4417 行实战知识 · 241 个章节 · 105+ 代码示例 · 生产覆盖 API 24,跟踪 HarmonyOS 7 / API 26 Beta1 问 Cursor 怎么写 ArkUI,它给你输出 React 组件? 让 Claude 改 ,它当 改? 问 Copilot 怎么用,它说"这 API 不存在"? 通用大模型从来没系统学过鸿蒙——它们的训练数据里几乎没有 ArkTS、Stage 模

agents-mdai-coding-assistantarktsarkuiclaude-codeclinecontinue-devcopilotcursorgemini-cli

Quick Facts

Stars226
Forks19
LanguageShell
CategoryCodex Skill
LicenseMIT
Quality Score64.7098412233273/100
Open Issues1
Last Updated2026-07-25
Created2026-04-05
Platformsclaude-code, cli, codex, gemini, node
Est. Tokens~15k

Compatible Skills

These tools work well together with harmonyos-ai-skill for enhanced workflows:

  • open-forge — semantic(0.23)+complementary+rare_topics+same_lang+similar_pop+shared_platform (62%)
  • fullstack-mkt-skills — semantic(0.19)+complementary+rare_topics+same_lang+similar_pop+shared_platform (61%)
  • agent-rules-skill — semantic(0.25)+complementary+rare_topics+same_lang+similar_pop+shared_platform (58%)

harmonyos-ai-skill alternative? Top 6 similar tools

Looking for a harmonyos-ai-skill alternative? If you're comparing harmonyos-ai-skill with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • harmony-next.skills by linhay · ⭐ 352

    Offline HarmonyOS NEXT developer skill library for AI coding assistants. Covers API 12–26 declarations, ArkTS/

  • memorix by AVIDS2 · ⭐ 825

    Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Wi

  • rulebook-ai by botingw · ⭐ 609

    Elevate vibe coding to vibe engineering: Get consistent Github Copilot custom instructions, Cursor, Roo Code,

  • awesome-vibe-coding-guide by analyticalrohit · ⭐ 379

    Become 10x Vibe Coder. Awesome Vibe Coding guide, best practices, and tips for efficient and controlled AI ass

  • prompt-architect by ckelsoe · ⭐ 308

    Claude Code skill that transforms vague prompts into structured, expert-level prompts using 7 research-backed

  • ox by sageox · ⭐ 63

    The hivemind for AI coding agents — persistent team context recorded once and recalled across agents, machines

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Shell Agent Tools

Frequently Asked Questions

What is harmonyos-ai-skill?

harmonyos-ai-skill is 鸿蒙(HarmonyOS NEXT)开发知识包,一份源文件自动产出 Claude Code / Cursor / Copilot / Codex / Gemini CLI / Windsurf / ChatGPT 等 11+ AI 工具的配置文件,让 AI 像熟读华为文档的工程师一样帮你写 ArkTS / ArkUI。. It is categorized as a Codex Skill with 226 GitHub stars.

What programming language is harmonyos-ai-skill written in?

harmonyos-ai-skill is primarily written in Shell. It covers topics such as agents-md, ai-coding-assistant, arkts.

How do I install or use harmonyos-ai-skill?

You can find installation instructions and usage details in the harmonyos-ai-skill GitHub repository at github.com/DengShiyingA/harmonyos-ai-skill. The project has 226 stars and 19 forks, indicating an active community.

What license does harmonyos-ai-skill use?

harmonyos-ai-skill is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to harmonyos-ai-skill?

The top alternatives to harmonyos-ai-skill on Agent Skills Hub include harmony-next.skills, memorix, rulebook-ai. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Codex Skill tools