by jiaw-Zh · Codex Skill · ★ 92
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 92 |
| Forks | 13 |
| Language | Python |
| Category | Codex Skill |
| Quality Score | 61/100 |
| Last Updated | 2026-06-18 |
| Created | 2026-05-07 |
| Platforms | codex, python |
| Est. Tokens | ~14k |
长篇小说生成 SKILL 原始项目：AINovelGenerator 一个面向百万/千万字长篇的 AI 写作 SKILL，解决长篇小说后期走形的核心问题。 为什么需要这个 AI 写长篇小说有一个根本性问题：上下文窗口装不下整部作品。即使是 1M token 的窗口，对 300 万字的小说也远远不够。结果是： 早期设定被后期章节覆盖稀释，角色性格漂移 数值、能力、物品归属前后矛盾 伏笔埋了忘了回收，或回收时对不上原文 配角消失几十章后再出场，agent 只能现编 同类桥段反复出现，读者审美疲劳 这个 SKILL 用结构化记忆系统解决上述问题，而不是靠"更大的上下文窗口"。 核心特色 分层摘要冻结 将作品摘要拆为六层：L0（正文）→ L1（单章）→ L2（chunk）→ L3（篇章）→ L4（卷）→ L5（全书）。每层写定后冻结，不再被后续章节覆盖。彻底消除"电话传话"式的早期细节稀释。...
Looking for a long-novel-writer alternative? If you're comparing long-novel-writer 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.
我要码字，这可能会是最好用的小说写作软件。51mazi是一款专为小说创作开发的桌面端写作软件，它不仅集成了随机取名，小说地图设计、关系图谱、人物档案，时间线等创作辅助工具，还集成了AI写作、AI生成封面，AI生成人物图等
Agent Skills for end-to-end story writing in markdown, packaged as Codex and Claude Code plugins.
天命 · AI长篇小说协同创作/写作Skill — 模块化提示词工程系统 (Claude Skill / Prompt Engineering for Novel Writing)
面向 Codex 的长篇中文小说生产 Skill：以可恢复的 Markdown 工作流贯通灵感、规划、章节写作、审校与连续性管理。
Novel Engine is a desktop app that lets you construct novels. Seven AI agents handle the editorial pipeline —
A Codex/Claude skill that maintains per-repo operating theory documents.
Explore other popular codex skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: