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 →
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is qiaomu-syc safe to install? View the security audit →
qiaomu-syc AI 写情绪，最容易犯的错是把情绪写出来。 qiaomu-syc 用短句、精确数字、行为细节和留白，让读者自己感受到它。 中文 · English 中文 是一个中文写作 Agent Skill。它把孙宇晨公开长文中呈现出的克制散文技法，拆解成一套可复用的写作流程： 情绪高峰反而用最短的句子 用精确数字代替抽象感受 把情绪藏进行为、物件和身体反应 用并置制造落差，不替读者下结论 每一节用一句克制的判断收住 它适合情感叙事、第一人称回忆、人物故事和已有文本改写。它不复制原文，也不冒充原作者。 先看效果 你说： Agent 会这样写： 没有“失落”“难过”或“遗憾”。但东西还在。 一行安装 安装后重启你的 Agent，然后直接用自然语言触发。 你可以直接这样说 text qiaomu-syc 改写这段文字，去掉感叹号、排比句和 AI
| Stars | 68 |
| Forks | 6 |
| Category | AI Tool |
| License | MIT |
| Quality Score | 57.9671611964164/100 |
| Last Updated | 2026-08-27 |
| Created | 2026-08-27 |
| Est. Tokens | ~17k |
Looking for a qiaomu-syc alternative? If you're comparing qiaomu-syc with other ai tool tools, these 3 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Skip to content github / docs Code Issues 80 Pull requests 35 Discussions Actions Projects 2 Security Insights
Skill to talk to Claude about your projects over the phone
.NET MAUI skills for GitHub Copilot and Claude Code
Explore other popular ai tool tools:
qiaomu-syc is 模拟孙宇晨（SYC）散文体写作风格：极度克制的短句节奏、数字锚点密集、情绪从不直接说破、 哲学式收束句、冰山叙事法。用于生成、改写或润色中文散文、情感叙事、个人陈述类文章。 触发词：SYC风格、孙宇晨文风、克制散文、冰山叙事、数字锚点散文、qiaomu-syc。. It is categorized as a AI Tool with 68 GitHub stars.
You can find installation instructions and usage details in the qiaomu-syc GitHub repository at github.com/joeseesun/qiaomu-syc. The project has 68 stars and 6 forks, indicating an active community.
qiaomu-syc is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to qiaomu-syc on Agent Skills Hub include redesigned-pancake, claude-code-voice-skill, maui-skills. 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: