Chinese-WebNovel-Skill — security grade SAFE, quality 59/100

Security audit verdict: SAFE · quality 59/100

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 Tomsawyerhu · Codex Skill · ★ 693

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

🔒 Is Chinese-WebNovel-Skill safe to install? View the security audit →

About Chinese-WebNovel-Skill

Chinese-WebNovel-Skill 这是一个面向中文网文写作的 Codex skill。 它现在的核心不是一份很长的总 prompt,而是一套 的模块化设计。 知乎回答贴: 为什么很多网文作者都非常自信,认为AI在创作领域无法取代自己? 设计思路 这套 skill 主要分四层: 只保留全局原则、流程约束和模块路由,不再把所有写作知识堆在一个文件里。 每个高频问题拆成独立模块,单独处理教程、运行规则、正例、反例。 提供本地小说语料、结构摘录和检索索引,支持“先匹配素材,再构思,再写作”。 提供检索脚本和少量模板资产,把模块判断进一步落成可执行动作。 这样做的目的很简单: 主 skill 保持短、稳、可维护 具体问题用具体模块处理 模型先诊断问题层级,再调用对应材料 避免一个巨型 prompt 同时兼顾开头、转场、对白、逻辑、审查,最后全部变钝 架构图 下面这张图对应当前版本的整体产品架构,展示了路由层、专项模块、语料底座和统一审查闭环之间的关系。 当前模块 当前已接入这些专项模块: 模块总入口: references/modules/README.md 每个模块默认都按同一套结构组织: 个别模块会额外附带模板资产,例如 下的卷纲和章纲模板。 模块职责总览 作用:把一句简介压成题材、消费点、hook、premise、故事引擎、长度判断和第一卷方向。 位置:最上游的前置规划模块,决定“值不值得写、该怎么开”。 作用

agentclaude-codecodexdesignmodulesnovel-writingskills

Quick Facts

Stars693
Forks82
LanguagePython
CategoryCodex Skill
Quality Score58.5427746771585/100
Open Issues2
Last Updated2026-08-28
Created2026-04-15
Platformsbrowser, claude-code, codex, python
Est. Tokens~15k

Compatible Skills

These tools work well together with Chinese-WebNovel-Skill for enhanced workflows:

  • NovelClaw — semantic(0.25)+complementary+same_lang+similar_pop+shared_platform (59%)
  • DSkills — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (58%)
  • thesis-skills — semantic(0.20)+complementary+same_lang+similar_pop+shared_platform (57%)

Chinese-WebNovel-Skill alternative? Top 6 similar tools

Looking for a Chinese-WebNovel-Skill alternative? If you're comparing Chinese-WebNovel-Skill 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.

  • terrashark by LukasNiessen · ⭐ 310

    Terraform Skill for Claude Code and Codex. LLMs hallucinate a lot with Terraform - TerraShark fixes this. It e

  • ui-craft by educlopez · ⭐ 309

    Design engineering system for AI coding agents — ship UI with craft-level quality. Install as an agent skill.

  • chinese-novelist-skill by PenglongHuang · ⭐ 2.8k

    🎭 AI 写小说:从零生成 10-50 章完整中文小说,三层问答 · 创作记忆 · 悬念钩子 · 自动校验,长篇网文连载皆宜|开源免费,适配主流 coding agent|AI novel writing skill

  • awesome-design-skills by bergside · ⭐ 2.2k

    List of 67 awesome DESIGN.md and SKILL.md design skill files for agentic tools like Claude Design, Google Stit

  • typeui by bergside · ⭐ 1.9k

    Build better UI with AI

  • ios-simulator-skill by conorluddy · ⭐ 1.2k

    An IOS Simulator Skill for ClaudeCode. Use it to optimise Claude's ability to build, run and interact with you

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is Chinese-WebNovel-Skill?

Chinese-WebNovel-Skill is 中文网文小说写作skill. It is categorized as a Codex Skill with 693 GitHub stars.

What programming language is Chinese-WebNovel-Skill written in?

Chinese-WebNovel-Skill is primarily written in Python. It covers topics such as agent, claude-code, codex.

How do I install or use Chinese-WebNovel-Skill?

You can find installation instructions and usage details in the Chinese-WebNovel-Skill GitHub repository at github.com/Tomsawyerhu/Chinese-WebNovel-Skill. The project has 693 stars and 82 forks, indicating an active community.

What are the best alternatives to Chinese-WebNovel-Skill?

The top alternatives to Chinese-WebNovel-Skill on Agent Skills Hub include terrashark, ui-craft, chinese-novelist-skill. 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