awesome-ascend-skills — security grade SAFE, quality 57/100

Security audit verdict: SAFE · quality 57/100

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 ascend-ai-coding · Agent Tool · ★ 170

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

🔒 Is awesome-ascend-skills safe to install? View the security audit →

About awesome-ascend-skills

Awesome Ascend Skills 这是一个给昇腾 NPU 开发者使用的 skills 仓库。内容按 Skill 组织,可被 Claude Code、OpenCode、Cursor、Trae、Codex 等 AI 编程工具读取。 GitHub Pages: https://ascend-ai-coding.github.io/awesome-ascend-skills/ skills.sh: https://skills.sh/ascend-ai-coding/awesome-ascend-skills 目录 简介 快速开始 安装指南 开发目录 Skill 导航 外部 Skills Skill 工作原理 治理规范 贡献指南 提交 PR 官方文档 许可证 简介 Awesome Ascend Skills 收集昇腾 NPU 开发中常用的排障、部署、迁移和分析经验。仓库里主要有四类内容: 单个 skill:处理一个明确问题,比如 、 领域技能包:把同一方向的多个子 skill 放在一起,比如 官方安装包:按常见工作方向拆好的 bundle,比如 、 外部同步 skills:从其他 Ascend skill 仓库同步进来的内容 当前目录模型: 所有本地 skills 统一位于 是本地 skill 的唯一正式路径 是外部同步 skills 的独立目录,不参与本地路径规则 第一次使用时,不必从完整列表里一个个挑。先看 ,确定自己要装哪个方向,再去 执行命令。 快速开始 我应该先装什么? text Start ├─ 你是第一次使用,或者还不确定该装什么? │ ├─ Yes → 先安装 │ └─ No → 进入下一步 │ ├─ 你的主要任务是什么? │ ├─ 推理 / 模型转换 / 服务部署 │ │ └─ 安装 + │ ├─ 训练 / 通信 / MindSpeed-LLM │ │ └─ 安装 + │ ├─ Profiling 采集 / 性能瓶颈分析 │ │ └─ 安装 + │ ├─ 算子开发 / Triton 迁移 / op-plugin 接

Quick Facts

Stars170
Forks59
LanguagePython
CategoryAgent Tool
Quality Score57.3831938771983/100
Open Issues19
Last Updated2026-09-18
Created2026-02-14
Platformspython
Est. Tokens~25k

Compatible Skills

These tools work well together with awesome-ascend-skills for enhanced workflows:

  • skills-agent-proto — semantic(0.27)+complementary+same_lang+similar_pop+shared_platform (59%)
  • awesome-skills — semantic(0.26)+complementary+same_lang+similar_pop+shared_platform (59%)
  • Awesome-OKF — semantic(0.25)+complementary+same_lang+similar_pop+shared_platform (59%)
  • arkon — semantic(0.25)+complementary+same_lang+similar_pop+shared_platform (59%)
  • stash — semantic(0.25)+complementary+same_lang+similar_pop+shared_platform (59%)

awesome-ascend-skills alternative? Top 2 similar tools

Looking for a awesome-ascend-skills alternative? If you're comparing awesome-ascend-skills with other agent tool tools, these 2 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • claude-plugins by Kamalnrf · ⭐ 564

    Lightweight registry to discover, install, and manage all public Claude plugins and agent skills for your favo

  • tutor-skills by RoundTable02 · ⭐ 400

    A Claude Code skill that turns PDFs, docs, and codebases into Obsidian study vaults

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is awesome-ascend-skills?

awesome-ascend-skills is A comprehensive knowledge base for Huawei Ascend NPU development, structured as distributed Agent Skills. https://ascend-ai-coding.github.io/awesome-ascend-skills/. It is categorized as a Agent Tool with 170 GitHub stars.

What programming language is awesome-ascend-skills written in?

awesome-ascend-skills is primarily written in Python.

How do I install or use awesome-ascend-skills?

You can find installation instructions and usage details in the awesome-ascend-skills GitHub repository at github.com/ascend-ai-coding/awesome-ascend-skills. The project has 170 stars and 59 forks, indicating an active community.

What are the best alternatives to awesome-ascend-skills?

The top alternatives to awesome-ascend-skills on Agent Skills Hub include claude-plugins, tutor-skills. 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 Agent Tool tools