sun-style-writing — security grade SAFE, quality 46/100

Security audit verdict: SAFE · quality 46/100

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 KKKKhazix · Codex Skill · ★ 248

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

🔒 Is sun-style-writing safe to install? View the security audit →

About sun-style-writing

孙割写作.skill 从孙割19年白月光的痛彻心扉中蒸馏出来的无上心法 十种手法 · 安装 · 使用 · 反馈 一颗卵子,三点五微克。 五千万美元现金,两点五吨。 一段沉默,十一秒。 后来,有人把这些东西装进了一个 .skill 文件。 它不含卵子。 也不含美元。 只含写法。 sun-style-writing 从《我的女友景甜》中拆出十种中文叙事手法。它教模型写动作、数字、物件和沉默。该交代的事实交代清楚。该解释的感情,不解释。 装上以后,模型不会变成孙割。账户里不会多出五千万美元,楼下也不会停一架 A330。 文章会少几个宇宙。 先看一段 普通模型写离职: 走出公司大门的那一刻,我百感交集。三年的青春仿佛在身后缓缓落幕。 它用了“百感交集”“青春”和“落幕”。 三个词。 孙割写法: 前台把我的工牌剪断。 剪刀卡了两次。 她换了一把。 两把剪刀。 一个字也没有哭。 十种手法 名字都在下面。不是十项任务,不需要全部完成。 | 反复与变

agent-skillschinese-writingclaude-codecodexliterary-writingprompt-engineeringwriting

Quick Facts

Stars248
Forks39
CategoryCodex Skill
LicenseMIT
Quality Score45.6232555820503/100
Open Issues3
Last Updated2026-08-27
Created2026-08-27
Platformsclaude-code, codex
Est. Tokens~15k

Compatible Skills

These tools work well together with sun-style-writing for enhanced workflows:

  • tianming-skill — semantic(0.53)+complementary+similar_pop+shared_platform (59%)
  • writing-agent — semantic(0.53)+complementary+similar_pop+shared_platform (58%)
  • academic-humanizer — semantic(0.53)+complementary+similar_pop+shared_platform (58%)
  • chinese-longnovel-skill — semantic(0.48)+complementary+similar_pop+shared_platform (57%)

sun-style-writing alternative? Top 6 similar tools

Looking for a sun-style-writing alternative? If you're comparing sun-style-writing 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.

  • qu-ai-wei by LifelongLazyLearner · ⭐ 547

    去 AI 味:去除简体中文 AI 写作痕迹 / Chinese humanizer skill

  • agent-skills by jdrhyne · ⭐ 241

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

  • SkillForge by tripleyak · ⭐ 855

    A skill creator that proves its skills work. Evidence-driven skill creation for Claude Code and Codex: baselin

  • ai-skills by sanjay3290 · ⭐ 422

    24 cross-platform agent skills for Claude Code, Cursor, Codex & Gemini CLI — databases, messaging, research, T

  • claude-skills by OneWave-AI · ⭐ 313

    200+ production-ready Claude Code skills for sales, marketing, design, engineering, and AI agent architecture.

  • aiwg by jmagly · ⭐ 218

    Cognitive architecture for AI-augmented software development. Specialized agents, structured workflows, and mu

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Frequently Asked Questions

What is sun-style-writing?

sun-style-writing is 从孙割19年白月光的痛彻心扉中蒸馏出来的无上心法. It is categorized as a Codex Skill with 248 GitHub stars.

How do I install or use sun-style-writing?

You can find installation instructions and usage details in the sun-style-writing GitHub repository at github.com/KKKKhazix/sun-style-writing. The project has 248 stars and 39 forks, indicating an active community.

What license does sun-style-writing use?

sun-style-writing is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to sun-style-writing?

The top alternatives to sun-style-writing on Agent Skills Hub include qu-ai-wei, agent-skills, SkillForge. 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