← Back to Skills Marketplace
Chapter Outliner
by
yuzhihui886
· GitHub ↗
· v3.0.0
· MIT-0
158
Downloads
0
Stars
0
Active Installs
6
Versions
Install in OpenClaw
/install chapter-outliner
Description
章节大纲生成器 - 基于 15 节拍系统生成小说章节大纲。当需要根据故事大纲和章节号创建详细写作大纲时使用,支持字数分配、角色参考、风格注入。
README (SKILL.md)
Chapter Outliner - 章节大纲生成器
Overview
根据小说项目文件(outline.md, style.yml, characters/)和章节号,自动生成结构化的 15 节拍章节大纲,包含字数分配、角色参考和风格备注。
使用场景:
- 需要为具体章节创建详细写作大纲
- 需要确保章节符合 15 节拍结构
- 需要分配字数到各个节拍
- 需要整合角色档案和风格配置
15 节拍系统
| 阶段 | 节拍 | 名称 | 用途 |
|---|---|---|---|
| 铺垫 | 1 | 钩子 | 吸引读者注意 |
| 2 | 设定 | 建立场景背景 | |
| 3 | context | 提供上下文 | |
| 转折 | 4 | inciting | 引入冲突 |
| 5 | 发展 | 情节推进 | |
| 6 | turning | 转折点 | |
| 7 | 转折 | 方向变化 | |
| 高潮 | 8 | 对抗 | 矛盾激化 |
| 9 | 发展 | 高潮铺垫 | |
| 10 | 高潮 | 冲突顶点 | |
| 11 | 转折 | 高潮转折 | |
| 结局 | 12 | 解决 | 问题解决 |
| 13 | 收尾 | 情节收尾 | |
| 14 | 余韵 | 情感延续 | |
| 15 | 结局 | 章节结束 |
CLI 使用
# 基本用法
python3 scripts/generate_outline.py --book-dir projects/my-novel --chapter 1
# 指定字数
python3 scripts/generate_outline.py \
--book-dir projects/my-novel \
--chapter 5 \
--word-count 5000
# 输出到文件
python3 scripts/generate_outline.py \
--book-dir projects/my-novel \
--chapter 10 \
--output outlines/chapter-10.md
# 简写
python3 scripts/generate_outline.py -d ./project -c 5 -w 3000 -o output.md
参数说明
| 参数 | 必填 | 说明 |
|---|---|---|
--book-dir / -d |
✅ | 小说项目目录路径 |
--chapter / -c |
✅ | 章节编号 |
--word-count / -w |
❌ | 目标字数(默认 3000) |
--output / -o |
❌ | 输出文件路径(缺省则只显示) |
项目目录结构
projects/my-novel/
├── outline.md # 故事大纲(可选)
├── style.yml # 风格配置(可选)
├── characters/ # 角色档案(可选)
│ ├── 主角.yml
│ └── 配角.yml
└── chapters/
└── outlines/ # 章节大纲输出
输出大纲格式
# 第 1 章 大纲
**字数目标**: 3000 字
**生成时间**: 2026-04-04 23:30:00
## 章节概述
[来自 outline.md 的章节摘要]
## 15 节拍大纲
### 1. 钩子 (铺垫)
**目标字数**: 135 字
**目的**: 建立场景和基础信息
第 1 节拍 - 待填充
### 2. 设定 (铺垫)
**目标字数**: 157 字
**目的**: 建立场景和基础信息
第 2 节拍 - 待填充
...
## 角色参考
### 林风
私家侦探,35 岁,冷静敏锐...
字数分配规则
| 阶段 | 总占比 | 说明 |
|---|---|---|
| 铺垫 | 15% | 场景建立 |
| 转折 | 20% | 冲突引入 |
| 高潮 | 45% | 核心内容 |
| 结局 | 20% | 收尾解决 |
依赖
- Python 3.8+
- rich (终端渲染)
- PyYAML (配置文件解析)
安装依赖:
pip install -r scripts/requirements.txt
与其他技能集成
与 style-analyzer 集成
# 1. 分析参考文本风格
python3 ../style-analyzer/scripts/analyze_style.py \
--input reference.txt \
--output style.yml
# 2. 生成章节大纲(自动读取 style.yml)
python3 scripts/generate_outline.py \
--book-dir projects/my-novel \
--chapter 1
与 novel-writer 集成
# 1. 生成章节大纲
python3 scripts/generate_outline.py \
--book-dir projects/my-novel \
--chapter 5 \
--output chapters/outlines/chapter-5.md
# 2. novel-writer 根据大纲生成正文
注意事项
- 项目文件(outline.md, style.yml, characters/)均为可选
- 缺少文件时会自动使用默认值
- 输出 Markdown 可直接用于 novel-writer 输入
- 15 节拍名称和阶段可自定义修改
Usage Guidance
This skill includes two code paths: a local generator (scripts/generate_outline.py) that operates on your local project files and is coherent with the README, and an LLM-backed script (scripts/generate_outline_llm.py) that will send your outline, style, and character data to a remote service (coding.dashscope.aliyuncs.com) and requires an environment variable DASHSCOPE_API_KEY. Before installing or running: 1) Treat the LLM script as an opt-in networked feature — do not run it unless you trust the remote service. 2) Ask the skill author to update SKILL.md and metadata to declare the DASHSCOPE_API_KEY requirement and to explain what data is sent, retention policy, and which model/service is used. 3) If you only want offline/local usage, use scripts/generate_outline.py and avoid running the LLM script; consider removing or sandboxing generate_outline_llm.py. 4) Run in an isolated environment (no access to sensitive files or secret env vars) if you must test the LLM script. 5) Verify and fix requirements.txt (add 'requests') and review network calls in the code. If the author provides a clear explanation and explicitly documents the API key and data handling, the concern could be resolved; absent that, do not supply sensitive project content or API credentials.
Capability Analysis
Type: OpenClaw Skill
Name: chapter-outliner
Version: 3.0.0
The chapter-outliner skill bundle is a legitimate tool for generating novel chapter outlines based on a 15-beat narrative structure. It contains a local generator (generate_outline.py) and an LLM-integrated version (generate_outline_llm.py) that uses the Alibaba DashScope API (coding.dashscope.aliyuncs.com) to process story data. The code uses safe YAML loading, follows its stated purpose without obfuscation, and shows no signs of data exfiltration or malicious intent.
Capability Assessment
Purpose & Capability
The stated purpose (generate chapter outlines from local project files) matches the pure-Python local script (scripts/generate_outline.py). However, the repository also includes an LLM-backed script (scripts/generate_outline_llm.py) that calls an external LLM endpoint — this networked capability is not documented in SKILL.md nor declared in the skill metadata and therefore is disproportionate to the advertised local-outliner purpose.
Instruction Scope
SKILL.md describes local CLI usage and only lists Python, rich, and PyYAML as dependencies. It does not mention invoking a remote LLM, nor does it warn that outline.md, style.yml, characters/*.yml and chapters/index.yml will be sent to an external API. generate_outline_llm.py explicitly builds a prompt containing story, style, and character data and posts it to a remote service — that is out-of-scope relative to the SKILL.md instructions and gives the skill broad discretion to transmit user project data.
Install Mechanism
There is no install spec (instruction-only), so nothing is downloaded at install time. That lowers install risk. However, scripts include a runtime network call; also scripts/requirements.txt omits the 'requests' package (which the LLM script uses), indicating sloppy packaging/documentation that could cause surprises at runtime.
Credentials
Skill metadata declares no required environment variables, but generate_outline_llm.py requires DASHSCOPE_API_KEY (read from environment) to call the remote LLM. Requesting an API key for an external service is reasonable for an LLM-backed variant — but omitting this from the declared requirements and SKILL.md is a red flag. In addition, the code will transmit user project content to the external endpoint, meaning that providing that API key and running the LLM script grants the remote service access to potentially sensitive project files.
Persistence & Privilege
The skill does not request persistent privileges (always is false), does not modify other skills' configuration, and does not require system-wide config changes. It runs as a user-invoked CLI, so persistence/privilege concerns are low by themselves.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install chapter-outliner - After installation, invoke the skill by name or use
/chapter-outliner - Provide required inputs per the skill's parameter spec and get structured output
Version History
v3.0.0
v3.0 重做:正确实现为待写章节生成 15 节拍写作大纲,输入 outline.md+style.yml+characters+index.yml,输出给 novel-writer 用的写作指南
v2.0.1
v2.0.1 LLM 版本:新增 generate_outline_llm.py,通过 LLM 分析章节内容生成 15 节拍大纲,默认 qwen3-max-2026-01-23
v2.0.0
按 OPTIMIZATION_PLAN.md 方案重写:读取章节正文 + LLM 分析内容动态生成节拍 + 三幕结构标注 + API 降级机制
v1.0.2
优化版本:新增章节类型检测、三幕结构标注、动态节拍描述(纯规则实现,无需外部 API)
v1.0.1
按规范重新创建:opencode 生成脚本 + Claude Code debug 修复
v1.0.0
初始版本:15 节拍系统、故事位置判断、字数分配、角色/事件关联
Metadata
Frequently Asked Questions
What is Chapter Outliner?
章节大纲生成器 - 基于 15 节拍系统生成小说章节大纲。当需要根据故事大纲和章节号创建详细写作大纲时使用,支持字数分配、角色参考、风格注入。 It is an AI Agent Skill for Claude Code / OpenClaw, with 158 downloads so far.
How do I install Chapter Outliner?
Run "/install chapter-outliner" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Chapter Outliner free?
Yes, Chapter Outliner is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Chapter Outliner support?
Chapter Outliner is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Chapter Outliner?
It is built and maintained by yuzhihui886 (@yuzhihui886); the current version is v3.0.0.
More Skills