← 返回 Skills 市场
zton100

novel-writing

作者 zton100 · GitHub ↗ · v1.2.0 · MIT-0
cross-platform ✓ 安全检测通过
842
总下载
0
收藏
4
当前安装
5
版本数
在 OpenClaw 中安装
/install novel-writing
功能描述
AI长篇网文创作技能包。用于解决长篇网络小说创作中的核心痛点:上下文丢失、文风不一致、设定冲突、节奏失控、多线混乱、质量不稳、读者反馈无法内化。触发场景包括:开始新书、规划大纲、撰写章节、管理伏笔、检测冲突、读者反馈分析、批量创作质量控制。
使用说明 (SKILL.md)

novel-writing

AI长篇网文创作技能包,解决长篇连载中的7大痛点。

核心架构

novel/
├── settings/          # 世界观设定档案
│   ├── world.md       # 世界观总览
│   ├── characters/    # 角色声线卡
│   ├── geography/     # 地理/势力
│   └── rules.md       # 世界规则
├── chapters/          # 章节档案
│   ├── outline.md     # 大纲
│   └── arc-N/         # 分卷
├── tracker/           # 追踪器
│   ├── foreshadowing.md  # 伏笔追踪
│   ├── conflicts.md    # 冲突记录
│   └── feedback.md    # 读者反馈
└── state.json          # 当前写作状态

工作流程

1. 开书初始化 novel init \x3C书名>

创建项目结构,加载默认模板。

2. 设定录入 novel setting \x3C类型> \x3C内容>

录入角色/地理/规则设定,自动检测与现有设定的冲突。

3. 大纲规划 novel outline \x3C章节范围> \x3C一句话概要>

生成章节大纲,标注伏笔埋入点。

4. 撰写章节 novel write \x3C章号> \x3C正文>

自动召回相关设定+前5章摘要,按文风指南输出。

5. 伏笔检测 novel check \x3C章号>

检查本章埋入的伏笔是否已在后续章节收回。

6. 冲突检测 novel conflict \x3C新内容>

检测新内容是否与已有设定冲突。

7. 反馈入库 novel feedback \x3C章节> \x3C反馈内容>

将读者反馈存入追踪器,写相关章节时自动加载。

伏笔追踪规则

每埋一个伏笔必须登记:

- [章X] 事件A → 预期回收章Y

连续3章未回收则预警。

文风指南

references/style-guide.md 定义:

  • 叙事语气(简洁/华丽/悬疑/热血)
  • 句式偏好(长句/短句比例)
  • 禁忌词表

状态文件

state.json 记录:

  • 当前卷/章
  • 已埋未收伏笔数
  • 本日产出字数
  • 最后修改时间

每次 novel write 后自动更新。

安全使用建议
This skill appears internally consistent and operates locally: it creates and modifies files under a novel/<project> directory and does simple conflict/foreshadowing checks. Before installing/running: (1) review the included scripts/novel.py to confirm you are comfortable executing a Python CLI from an unknown source; (2) run it from a directory where writing novel/<name>/ is safe (it will create and update files and state.json); (3) note there are no network calls or secret requests, so credential exposure risk is low; (4) understand that 'automatic recall' and style enforcement are responsibilities of the agent/LLM using these files — the script itself only manages and checks files; (5) consider keeping backups of important work and inspect/validate the code if you need stronger guarantees about behavior or want to remove/modify any automatic file writes.
能力评估
Purpose & Capability
Name/description (long-form novel authoring: outline, chapters, foreshadowing, conflict checking, feedback tracking) match the included content and CLI script: the code creates/reads/writes files under novel/<project>, keeps state.json, and provides conflict/foreshadowing/feedback utilities. No unrelated credentials or binaries are requested.
Instruction Scope
SKILL.md describes AI behaviors like '自动召回相关设定+前5章摘要, 按文风指南输出' which relies on the agent reading the local project files; the provided script implements local file I/O, outline/conflict/feedback tracking, and basic checks. There is no network I/O or access to system paths outside the novel/ workspace. Note: some SKILL.md wording implies automated stylistic transformation by an LLM — the script itself only manages files and checks.
Install Mechanism
No install spec (instruction-only skill) and no external downloads; a single benign Python CLI file is included. Nothing is fetched from the network or extracted during install.
Credentials
The skill does not request environment variables, credentials, or config paths. The code does not read sensitive environment variables or external auth tokens.
Persistence & Privilege
always:false and normal autonomous invocation settings. The skill only reads/writes files inside its own novel/<name> workspace and does not modify global agent configuration or other skills.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install novel-writing
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /novel-writing 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.2.0
Version 1.2.0 - Improved: Updated documentation in SKILL.md for clarity and structure. - No functional changes to code; core workflow and features remain as previously described.
v1.1.1
- Minor update to internal code structure in scripts/novel.py. - No changes to user-facing features or documentation.
v1.1.0
novel-writing 1.1.0 更新日志 - 更新脚本 scripts/novel.py 文件,包含功能改进或修复。 - 其余文档、核心结构和操作流程未进行更改。
v1.0.1
- Documentation improvements in SKILL.md for workflow steps and architecture. - Minor clarifications for feature descriptions and process explanations.
v1.0.0
- Initial release of the novel-writing skill. - Provides an AI-powered toolkit for long-form web novel creation, addressing issues like context loss, inconsistent style, setting conflicts, pacing, subplot management, quality stability, and reader feedback integration. - Features include project initialization, structured outline planning, chapter writing with automatic recall of key context, foreshadowing and conflict tracking, and feedback management. - Offers workflow commands for setting management, outline generation, chapter composition, foreshadowing checks, conflict detection, and reader feedback analysis. - Includes a modular project structure for settings, chapters, tracking, and state management.
元数据
Slug novel-writing
版本 1.2.0
许可证 MIT-0
累计安装 5
当前安装数 4
历史版本数 5
常见问题

novel-writing 是什么?

AI长篇网文创作技能包。用于解决长篇网络小说创作中的核心痛点:上下文丢失、文风不一致、设定冲突、节奏失控、多线混乱、质量不稳、读者反馈无法内化。触发场景包括:开始新书、规划大纲、撰写章节、管理伏笔、检测冲突、读者反馈分析、批量创作质量控制。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 842 次。

如何安装 novel-writing?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install novel-writing」即可一键安装,无需额外配置。

novel-writing 是免费的吗?

是的,novel-writing 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

novel-writing 支持哪些平台?

novel-writing 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 novel-writing?

由 zton100(@zton100)开发并维护,当前版本 v1.2.0。

💬 留言讨论