harmony-next.skills — security grade SAFE, quality 66/100

Security audit verdict: SAFE · quality 66/100

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 linhay · Codex Skill · ★ 352

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

🔒 Is harmony-next.skills safe to install? View the security audit →

About harmony-next.skills

English · readme-English HarmonyOS NEXT Agent Skills 给 Gemini CLI、Claude Code、Codex 和其他 AI 编程助手使用的 HarmonyOS NEXT 离线技能包。 API 12–26 的本地 HarmonyOS 参考、ArkTS/ArkUI、NDK、DevEco Studio、模拟器自动化和发布调试工作流。 让 Agent 自动安装 把这段话发给你的 Agent: 展开安装提示词 快速开始 安装后直接提出 HarmonyOS 开发问题。Agent 会按 SKILL.md → KITS.md / TASKMAP.md → IN

ai-coding-assistantapi-26arktsautomation-testingclaude-codecodexdeveco-studiodeveloper-toolsdsh-plugingemini-cli

Quick Facts

Stars352
Forks25
LanguagePython
CategoryCodex Skill
Quality Score66.1149303863943/100
Last Updated2026-09-20
Created2026-03-12
Platformsclaude-code, cli, codex, gemini, python
Est. Tokens~14k

Compatible Skills

These tools work well together with harmony-next.skills for enhanced workflows:

  • ai-phone — semantic(0.34)+complementary+rare_topics+same_lang+similar_pop+shared_platform (66%)
  • agentic-playwright — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (56%)
  • clauder — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (56%)
  • clauder — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (56%)
  • DSkills — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (56%)

harmony-next.skills alternative? Top 6 similar tools

Looking for a harmony-next.skills alternative? If you're comparing harmony-next.skills 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.

  • harmonyos-ai-skill by DengShiyingA · ⭐ 226

    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 1

  • agent-deck by asheshgoplani · ⭐ 995

    Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.

  • quint-code by m0n0x41d · ⭐ 1.3k

    Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and p

  • hol-guard by hashgraph-online · ⭐ 728

    Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, M

  • compose-skill by aldefy · ⭐ 561

    Jetpack Compose Agent Skill — AI-powered coding guidance with actual androidx/androidx source code receipts. W

  • agent-skills by jdrhyne · ⭐ 241

    A collection of AI agent skills for Clawdbot, Claude Code, Codex

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is harmony-next.skills?

harmony-next.skills is Offline HarmonyOS NEXT developer skill library for AI coding assistants. Covers API 12–26 declarations, ArkTS/ArkUI, NDK, DevEco Studio, emulator automation, debugging, publishing, and reproducible lo. It is categorized as a Codex Skill with 352 GitHub stars.

What programming language is harmony-next.skills written in?

harmony-next.skills is primarily written in Python. It covers topics such as ai-coding-assistant, api-26, arkts.

How do I install or use harmony-next.skills?

You can find installation instructions and usage details in the harmony-next.skills GitHub repository at github.com/linhay/harmony-next.skills. The project has 352 stars and 25 forks, indicating an active community.

What are the best alternatives to harmony-next.skills?

The top alternatives to harmony-next.skills on Agent Skills Hub include harmonyos-ai-skill, agent-deck, quint-code. 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