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 zenstory-ai · Claude Skill · ★ 6.8k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is oh-story-claudecode safe to install? View the security audit →
English | 中文 oh-story-claudecode 网文写作 skill 包，覆盖长篇与短篇网络小说的扫榜、拆文、写作、去AI味、封面图全流程。内置适配 Claude Code、OpenCode、ZCode、OpenClaw、Codex CLI、Reasonix；能读取项目文件的 Web AI / Agent 环境也可按通用 skills 路径使用。 核心思路 套路 = 确定性的情绪满足 专业作者的方法论三步走： 扫榜：分析热门榜单，洞察题材、人设、切入点。 拆文：拆解大纲节奏与剧情素材，建立个人模块库。 商业化写作：学习并运用钩子、爽感、期待感等核心技巧。 围绕四条线展开：爆款逆向 · 剧情模块化重组 · 上下文状态分层管理 · 人机协同。 v0.7.6 起：重点在正文那一段。写正文的 有三条规则一直在空转——「写完必须立即统计字数」给的是一条 Bash 命令，可它的工具白名单里没有 Bash，同一句话又禁掉了模型估算，于是「字数达标是硬性要求」背后没有任何可执行判据；「返回前报出句长分布」同样只能编，而主会话正拿它做质量校验；「正文逐项展开细纲」是最高优先级的明令，放宽的那半边却只写在主 skill 里、从不进 spawn 提示词，子代理只看见限制，就按一个情节点一段平推成流水账。三条都已修好，实跑首次落盘即进验收区间（对照组不到下限的 73%）。新增细纲照搬检测：细纲把情节点写成成品散文句时正文只剩誊抄，配套的「复沓锚句」字段让必须逐字进正文的原话（誓言、系统面板、案卷原话）不被误判。另外 Claude Code 上用 Bash 重定向写正文也会被大纲/追踪守卫拦下，以及每次会话固定加载的文本再降两成（开书 −30%、回炉 −41%）。本版 为 25，已部署项目需重新运行 并新开会话。 v0.7.5 起：稳定版。补上 Claude Code 写正文守卫缺的追踪检查点门——另三端从 v0.7.3 起就有，主力端此前会静默写出若干章没有追踪的正文；长篇 每次触发都整份进上下文的 SKILL.md 从 82 KB 降到 54 KB（开书三阶段抽成按需读的 ，日更不再为用不上的建纲步骤付费）；清掉一批过度累加的限制指令，其中一条把正文里普通的「他说」判成了违规。本版 为 24，已部署项目需重新运行 并新开会话。 v0.7.4 起：全是修复。 不再把用户自己的书登记成对标（此前会出现「对标目录内容跟自己设定完全相同」）；story-setup 重部署不再把 Reasonix / generic 项目误判成 OpenClaw，多端部署也不再每次开会话误报参考包缺失；Stage 6 文风统计在 Windows 上不再必挂。spawn 的 硬门禁改成提示——版本不匹配照常并行，只有 agent 文件缺失才降级 solo。本版 为...
| Stars | 6,776 |
| Forks | 971 |
| Language | JavaScript |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 60.5450133842557/100 |
| Open Issues | 11 |
| Last Updated | 2026-09-11 |
| Created | 2026-04-22 |
| Platforms | browser, claude-code, codex, node |
| Est. Tokens | ~17k |
These tools work well together with oh-story-claudecode for enhanced workflows:
Looking for a oh-story-claudecode alternative? If you're comparing oh-story-claudecode with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
网文/小说写作 skill 包，覆盖长篇与短篇网络小说的扫榜、拆文、写作、去AI味、封面图全流程 | An all-in-one skill pack for long- and short-form web ficti
🎭 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
Open-source 24/7 Cowork app for OpenClaw, Hermes, Claude Code, Codex, OpenCode and 20+ more CLI Agent | Custom
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memo
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budget
说人话｜中文优先的去 AI 味改写 skill：保事实、分场景、改完可直接发。Chinese-first rewrite skill for Codex / Claude Code / Cursor / ChatGPT
Explore other popular claude skill tools:
oh-story-claudecode is 网文/小说写作 skill 包，覆盖长篇与短篇网络小说的扫榜、拆文、写作、去AI味、封面图全流程 | An all-in-one skill pack for long- and short-form web fiction.. It is categorized as a Claude Skill with 6.8k GitHub stars.
oh-story-claudecode is primarily written in JavaScript. It covers topics such as agent-skills, ai-agent, ai-writing.
You can find installation instructions and usage details in the oh-story-claudecode GitHub repository at github.com/zenstory-ai/oh-story-claudecode. The project has 6.8k stars and 971 forks, indicating an active community.
oh-story-claudecode is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to oh-story-claudecode on Agent Skills Hub include oh-story-claudecode, chinese-novelist-skill, AionUi. 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: