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 joeseesun · Agent Tool · ★ 386
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is qiaomu-meta-skill safe to install? View the security audit →
qiaomu-meta-skill 把一句「把这个流程做成 Skill」，变成一个真正能被发现、能稳定触发、能通过验证、还能一键开源的 Skill。 安装以后，你只需要把提示词、SOP、聊天记录、旧 Skill、脚本或一个模糊想法交给 Agent： 它会自己完成：需求收敛 → 同类检索 → 取长避短 → Skill 设计 → 触发评测 → 格式校验 → README → API 泄露检查 → PR → Release → npx 安装验证。 v2.8.1 本地候选已验证： 35/35 单元测试、23/23 触发评测、0 个包校验问题。公开发布证据以 Releases 为准。 为什么我做了这个 Skill 正在变成 Agent 时代真正可复用的软件单元，但“写一份 ”离一个好用的 Skill 还很远： 描述写得太宽，会到处误触发；写得太窄，又永远叫不出来。 把一段长 Prompt 换个文件名，不会自动变成可靠工作流。 不研究已有方案，很容易重复造一个更差的轮子。 本地能跑，不代表别人能安装，更不代表可以安全发布。 README、许可证、版本、密钥泄露、PR、Release 和安装证明，经常在最后一步一起失控。 Anthropic 与 OpenAI 的官方 奠定了很好的基础。乔木元 Skill 在此之上补齐了我实际做几十个 Skill 时最需要的一段：先搜索再创造、用证据控制质量，并把成品安全发布给别人使用。 初始方法来自搭档姚老师的 [](https://github.com/
| Stars | 386 |
| Forks | 62 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 64.1613542798462/100 |
| Last Updated | 2026-08-04 |
| Created | 2026-05-20 |
| Platforms | python |
| Est. Tokens | ~17k |
Looking for a qiaomu-meta-skill alternative? If you're comparing qiaomu-meta-skill with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic
A Claude Code skill that turns PDFs, docs, and codebases into Obsidian study vaults
Evaluate agent skill quality. Find the weakest link. Fix it. Prove it worked.
🧑🎨 A collection of agentic skills that works
Agent skill: generate Mermaid diagrams (.mmd), validate via Kroki-first loop, export PNG/SVG/PDF via mmdc or K
Hand-drawn Excalidraw diagrams from natural language. 5 patterns, 8-color semantic palette, Kroki API or local
Explore other popular agent tool tools:
qiaomu-meta-skill is 把工作流变成可研究、可评测、可发布的乔木 Agent Skill | Turn workflows into researched, tested, release-ready agent skills.. It is categorized as a Agent Tool with 386 GitHub stars.
qiaomu-meta-skill is primarily written in Python. It covers topics such as agent-skills, ai-workflow, qiaomu.
You can find installation instructions and usage details in the qiaomu-meta-skill GitHub repository at github.com/joeseesun/qiaomu-meta-skill. The project has 386 stars and 62 forks, indicating an active community.
qiaomu-meta-skill is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to qiaomu-meta-skill on Agent Skills Hub include SkillEvaluator, tutor-skills, SkillCompass. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: