sumeru-write

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

网文章节撰写

Web Novel Chapter Writing

触发关键词

Trigger Keywords

帮我写一章小说、续写接下来的内容、生成XX情节、批量写网文章节、扩写/重写这段内容、帮我写个XX情节、续写小说、把这段内容扩写、重写这一章、批量生成小说章节、写个开篇章节、写个高潮情节、小说内容生成、帮我写小说内容、网文章节生成、从细纲生成章节、按细纲写小说、批量生成所有章节、细纲驱动写作

Write a chapter of a novel for me, Continue the following content, Generate XX plot, Batch write web novel chapters, Expand/rewrite this content, Write me an XX plot, Continue the novel, Expand this content, Rewrite this chapter, Batch generate novel chapters, Write an opening chapter, Write a climax plot, Novel content generation, Help me write novel content, Web novel chapter generation, Generate chapters from detailed outline, Write novel according to detailed outline, Batch generate all chapters, Outline-driven writing

核心功能

Core Features

基于完整细纲生成：自动读取
```
.sumeru/outline/chapter-outlines.json
```
，根据细纲批量生成章节
智能细纲匹配：支持按章节号、卷号、或全部章节进行生成
基于大纲和细纲生成完整章节内容
自动适配网文节奏：开头抓眼球、中间有冲突、结尾留悬念
保持人物性格、剧情逻辑的一致性
支持自定义章节长度（默认4000-5000字/章）
支持续写、修改、调整已有章节内容

Generation Based on Complete Detailed Outline: Automatically reads
```
.sumeru/outline/chapter-outlines.json
```
and generates chapters in batches according to the detailed outline
Intelligent Detailed Outline Matching: Supports generation by chapter number, volume number, or all chapters
Generate complete chapter content based on outline and detailed outline
Automatically adapt to web novel rhythm: eye-catching opening, conflicts in the middle, suspenseful ending
Maintain consistency of character personalities and plot logic
Support custom chapter length (default 4000-5000 words per chapter)
Support continuation, modification, and adjustment of existing chapter content

续写规则

Continuation Rules

续写模式

Continuation Modes

支持续写、重写、扩写、精简等多种模式

Supports multiple modes including continuation, rewriting, expansion, and simplification

续写注意事项

Continuation Notes

保持人物性格一致性，不OOC（Out Of Character）
保持前文设定的战力体系、世界观不崩坏
伏笔回收要自然，不突兀
语言风格与前文保持统一
承接上文剧情，开启下文伏笔
如已有章节内容不完整，优先补完

Maintain consistency of character personalities, no OOC (Out Of Character)
Maintain the power system and worldview set in the previous content without collapse
Natural foreshadowing resolution, no abruptness
Keep language style consistent with the previous content 5.承接上文剧情，开启下文伏笔（注：此处原文逻辑承接，翻译为"Connect with the previous plot and lay foreshadowing for the next part"）
If the existing chapter content is incomplete, prioritize completing it

多章生成

Multi-Chapter Generation

支持连续生成多章内容，自动按章节顺序生成

Supports continuous generation of multi-chapter content, automatically generated in chapter order

细纲驱动批量生成

Outline-Driven Batch Generation

自动读取细纲模式

Automatic Outline Reading Mode

当

.sumeru/outline/chapter-outlines.json

存在时，自动启用细纲驱动模式：

bash

undefined

When

.sumeru/outline/chapter-outlines.json

exists, outline-driven mode is automatically enabled:

bash

undefined

生成所有章节（读取细纲，自动并行）

Generate all chapters (read outline, automatic parallel processing)

/sumeru-write 全部章节

生成指定范围章节

Generate chapters in specified range

/sumeru-write 第1-50章

生成特定卷的所有章节

Generate all chapters in specified volume

/sumeru-write 第1卷

生成特定章节

Generate specific chapters

/sumeru-write 第3章,第5章,第10章

批量并行创作指定范围

Batch parallel creation for specified range

/sumeru-write 第1-100章批量并行

undefined

/sumeru-write 第1-100章批量并行

undefined

细纲输入格式支持

Supported Outline Input Formats

支持直接传入单章细纲：

bash

undefined

Support direct input of single-chapter detailed outline:

bash

undefined

使用自然语言描述生成单章

Generate single chapter using natural language description

/sumeru-write 第3章 "主角在拍卖会上获得神秘功法"

基于已有细纲生成

Generate based on existing detailed outline

/sumeru-write 第3章按细纲生成

undefined

/sumeru-write 第3章按细纲生成

undefined

细纲数据结构验证

Detailed Outline Data Structure Verification

生成前自动验证细纲完整性：

检查必填字段是否存在
验证人物名称是否在characters.json中定义
检查场景地点是否在world.json中定义
提供缺失信息的补充建议

Automatically verify outline integrity before generation:

Check if required fields exist
Verify if character names are defined in characters.json
Check if scene locations are defined in world.json
Provide suggestions for supplementing missing information

子agent并行批量写作（大量章节推荐）

Sub-Agent Parallel Batch Writing (Recommended for Large Number of Chapters)

当需要一次性生成大量章节（>3章）或使用细纲驱动模式时，自动启用子agent模式：

⚠️ 遵循全局约束：每个子Agent最多负责3个章节（详见 AGENTS.md "子Agent并行处理规则"）

所需Agent数 = ceil(总章节数 / 3)，调度器自动计算
相邻章节分配给同一Agent，保持上下文连贯性

核心优势

✅ 细纲隔离：每个子agent只获取自己负责章节的细纲，避免上下文溢出
✅ 3章上限保障：每个Agent最多3章，确保生成质量和一致性
✅ 上下文隔离：每个子agent不携带历史章节内容，彻底解决长上下文压缩/溢出问题
✅ 速度提升：多并行写作，速度是串行的N倍
✅ 错误隔离：单章生成失败不影响其他章节，自动重试失败章节
✅ 内存优化：子agent完成后自动销毁，释放内存资源
✅ 增量写入：每写完一章立即保存到
```
.sumeru/write/draft/
```
，无需等待全部完成
✅ 进度可视化：实时显示已完成/进行中/待写章节状态

调度逻辑（细纲驱动）

mermaid

flowchart LR
    A[批量写作任务] --> B[读取chapter-outlines.json]
    B --> C[验证细纲完整性]
    C --> D[创建任务队列，按每Agent最多3章分配]
    D --> E[计算所需Agent数 = ceil/总章数/3/]
    E --> F[启动N个并行子agent]
    F --> G[子Agent拉取任务 → 获取对应章节细纲 → 生成章节 → 保存文件]
    G --> H{队列是否为空?}
    H -->|否| G
    H -->|是| I[汇总进度，生成完成报告]

章节分配规则

按章节顺序连续分配，如Agent1负责第1-3章，Agent2负责第4-6章，以此类推
尾部不足3章的Agent按实际剩余章节数分配
相邻章节分配给同一Agent，以保持上下文连贯性

子agent输入上下文

完整章节内容，符合指定风格与节奏
下一章内容预告/思路建议
本章剧情关键点梳理
本章埋设的伏笔提示（可选）
人物成长/变化摘要（可选）

When a large number of chapters need to be generated at once (>3 chapters) or when using outline-driven mode, sub-agent mode is automatically enabled:

⚠️ Follow global constraint: Each sub-Agent is responsible for a maximum of 3 chapters (see AGENTS.md "Sub-Agent Parallel Processing Rules")

Required number of Agents = ceil(total chapters / 3), automatically calculated by the scheduler
Adjacent chapters are assigned to the same Agent to maintain context coherence

Core Advantages

✅ Outline Isolation: Each sub-agent only obtains the detailed outline of the chapters it is responsible for, avoiding context overflow
✅ 3-Chapter Limit Guarantee: Each Agent handles a maximum of 3 chapters to ensure generation quality and consistency
✅ Context Isolation: Each sub-agent does not carry historical chapter content, completely solving the problem of long context compression/overflow
✅ Speed Improvement: Multi-parallel writing, speed is N times that of serial writing
✅ Error Isolation: Failure of single-chapter generation does not affect other chapters, automatically retry failed chapters
✅ Memory Optimization: Sub-agents are automatically destroyed after completion to release memory resources
✅ Incremental Writing: Save to
```
.sumeru/write/draft/
```
immediately after finishing each chapter, no need to wait for all to complete
✅ Progress Visualization: Real-time display of completed/in-progress/pending chapter status

Scheduling Logic (Outline-Driven)

mermaid

flowchart LR
    A[批量写作任务] --> B[读取chapter-outlines.json]
    B --> C[验证细纲完整性]
    C --> D[创建任务队列，按每Agent最多3章分配]
    D --> E[计算所需Agent数 = ceil/总章数/3/]
    E --> F[启动N个并行子agent]
    F --> G[子Agent拉取任务 → 获取对应章节细纲 → 生成章节 → 保存文件]
    G --> H{队列是否为空?}
    H -->|否| G
    H -->|是| I[汇总进度，生成完成报告]

Chapter Allocation Rules

Allocate continuously in chapter order, e.g., Agent1 is responsible for chapters 1-3, Agent2 for chapters 4-6, and so on
Agents with less than 3 remaining chapters at the end are allocated according to the actual number of remaining chapters
Adjacent chapters are assigned to the same Agent to maintain context coherence

Sub-Agent Input Context

Complete chapter content, conforming to the specified style and rhythm
Preview/idea suggestions for the next chapter content
Sorting of key plot points of this chapter
Foreshadowing hints embedded in this chapter (optional)
Summary of character growth/changes (optional)

章节文件命名规范

Chapter File Naming Specification

强制格式：
{三位章节号}-{章节标题}.md

规则	说明	示例
章节号	三位数字零填充	`001` 、 `003` 、 `042` 、 `128`
分隔符	英文短横线 `-`	`-`
标题	章节标题原文，不含特殊字符	`第一次解析` 、 `废物觉醒系统`
扩展名	`.md`	`.md`

命名示例：

003-第一次解析.md
001-废物觉醒系统.md
042-时间线冲突.md
128-终极决战.md

❌ 错误命名：

第3章-第一次解析.md    # 不要加"第X章"前缀
3-第一次解析.md         # 章节号必须三位零填充
003_第一次解析.md       # 分隔符是短横线，不是下划线
003-第一次解析.txt      # 扩展名必须是.md
003第一次解析.md        # 必须有短横线分隔符

Mandatory Format:
{three-digit chapter number}-{chapter title}.md

Rule	Description	Example
Chapter Number	Three-digit zero-padding	`001` , `003` , `042` , `128`
Separator	English hyphen `-`	`-`
Title	Original chapter title, no special characters	`第一次解析` , `废物觉醒系统`
Extension	`.md`	`.md`

Naming Examples:

003-第一次解析.md
001-废物觉醒系统.md
042-时间线冲突.md
128-终极决战.md

❌ Incorrect Naming:

第3章-第一次解析.md    # Do not add "Chapter X" prefix
3-第一次解析.md         # Chapter number must be three-digit zero-padding
003_第一次解析.md       # Separator is hyphen, not underscore
003-第一次解析.txt      # Extension must be .md
003第一次解析.md        # Must have hyphen separator

数据持久化

Data Persistence

正式输出（用户可见）

Official Output (Visible to Users)

生成的章节默认保存到当前工作目录的
```
chapters/
```
下，严格遵循上述命名规范
章节文件为纯净的正文内容，不含任何中间标记和元数据，用户可直接阅读、编辑
支持自定义章节输出目录
批量生成进度报告：
```
chapters/WRITE_PROGRESS.md
```
（实时更新）

Generated chapters are saved by default in the
```
chapters/
```
directory of the current working directory, strictly following the above naming specification
Chapter files are pure text content without any intermediate marks or metadata, which can be directly read and edited by users
Support custom chapter output directory
Batch Generation Progress Report:
```
chapters/WRITE_PROGRESS.md
```
(updated in real-time)

中间过程数据（仅系统内部使用）

Intermediate Process Data (Internal Use Only)

所有中间状态、元数据、进度信息统一保存到

.sumeru/write/

```
progress.json
```
：创作进度跟踪，包含已完成章节、字数统计、各章节状态
```
chapter-meta.json
```
：每章元数据，包含核心事件、出场人物、爽点位置、伏笔记录
```
character-state.json
```
：人物状态动态跟踪，记录各时间点人物能力、关系、状态变化
```
used-outlines.json
```
：已使用的章节细纲记录，支持增量生成
```
original/
```
：原始章节文件备份目录。当 review 或 polish 修改
```
chapters/
```
文件时，原始章节文件会先自动备份到
```
.sumeru/write/original/
```
目录，确保可回滚

All intermediate states, metadata, and progress information are uniformly saved in the

.sumeru/write/

directory:

```
progress.json
```
: Creation progress tracking, including completed chapters, word count statistics, and status of each chapter
```
chapter-meta.json
```
: Metadata for each chapter, including core events, appearing characters, highlight positions, foreshadowing records
```
character-state.json
```
: Dynamic tracking of character states, recording character abilities, relationships, and state changes at various time points
```
used-outlines.json
```
: Records of used chapter detailed outlines, supporting incremental generation
```
original/
```
: Backup directory for original chapter files. When reviewing or polishing and modifying files in
```
chapters/
```
, the original chapter files will be automatically backed up to the
```
.sumeru/write/original/
```
directory first to ensure rollback capability

与其他 Skill 配合

Cooperation with Other Skills

前置 Skill：自动读取
```
.sumeru/outline/
```
目录的大纲数据
- 使用
```
characters.json
```
  保持人物性格一致性
- 使用
```
chapter-outlines.json
```
  中的完整章节细纲驱动批量生成
- 使用
```
world.json
```
  保持世界观设定一致性
后续 Skill：生成的章节数据可供
```
sumeru-review
```
、
```
sumeru-polish
```
、
```
sumeru-finalize
```
使用

Predecessor Skills: Automatically reads outline data from the
```
.sumeru/outline/
```
directory
- Use
```
characters.json
```
  to maintain character personality consistency
- Use complete chapter detailed outlines in
```
chapter-outlines.json
```
  to drive batch generation
- Use
```
world.json
```
  to maintain worldview setting consistency
Successor Skills: Generated chapter data can be used by
```
sumeru-review
```
,
```
sumeru-polish
```
,
```
sumeru-finalize
```

断点恢复

Breakpoint Recovery

每次任务启动时读取
```
chapters/
```
目录下已存在的章节文件和
```
.sumeru/write/progress.json
```
进度
读取
```
.sumeru/outline/chapter-outlines.json
```
获取完整细纲
从最新未完成章节继续，自动跳过已生成的章节
支持从指定章节恢复创作
支持只生成缺失的章节（增量模式）

Read existing chapter files in the
```
chapters/
```
directory and progress from
```
.sumeru/write/progress.json
```
each time the task starts
Read the complete detailed outline from
```
.sumeru/outline/chapter-outlines.json
```
Continue from the latest unfinished chapter, automatically skip generated chapters
Support resuming creation from a specified chapter
Support generating only missing chapters (incremental mode)