Long Novel Writer

Community

jiaw-Zh

long-novel-writer

当用户需要写长篇小说、扩展小说创意、构建小说架构、生成正文章节或进行章节定稿更新时使用。此技能提供了一套完整的五阶段工作流，通过外部文档驱动状态机的方式，保障百万/千万级别小说的连贯性。

Overview

Publisher	jiaw-Zh
Repository	`long-novel-writer`
Skill name	`long-novel-writer`
Stars	94
Forks	13
Bundled files	8
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
8 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by jiaw-Zh on GitHub. Read the source before you install it.

Installation

Install the Long Novel Writer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/jiaw-Zh/long-novel-writer/tree/main
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/jiaw-Zh/long-novel-writer.git \
  .claude/skills/long-novel-writer

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Long Novel Writer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Long Novel Writer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Long Novel Writer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

长篇小说写作器

核心定位

按"架构先行、分卷推进、状态驱动、检索校验"的方式创作百万至千万字级别小说。

不要一次性生成整部长篇正文。每次只推进一个明确层级：整书架构、卷规划、3-5 章小单元、单章正文、记忆更新、修订审校。

工作流

作品初始化
- 读取或创建作品目录时，先看 references/file-contract.md（文件布局 + 立项 checklist + 导入 checklist）与 references/memory-protocol.md（记忆协议）。
- 场景分支：
  - 用户只有一句创意 → 走 dev 分支的"AI 创建小说"链路：扩展创意 → 提炼构思 → 故事核心 → 小说整体设定；然后走「立项 checklist」。
  - 用户已有设定（无正文）→ 直接走「立项 checklist」：metadata → 设定正典 → 实体档案 → 网文额外项 → 章节目录 → 空壳文件。
  - 用户已有正文但无记忆结构 → 走「导入既有作品 checklist」（13 步），用 reverse_story_bible_prompt / extract_entities_prompt / canon_backfill_prompt 等反推记忆层，然后从 N+1 章继续写。
- story-bible.md 立项/导入时即写定并视为冻结基线，后续修订必须追加「变更记录」。
百万字架构
- 将故事拆成：整书主线 -> 卷 -> 篇章单元 -> 3-5 章 chunk -> 单章。
- 每卷必须有显性目标、隐藏危机、阶段反派或阻力、角色状态变化、伏笔回收表。
- 对千万字目标，默认启用 memory-protocol.md 的分层摘要（L0–L5）+ 实体档案 + 章节索引。禁止只靠"一份不断覆盖的前文摘要"撑长篇。
章节生成
- 写正文前先按 memory-protocol.md 第四节「写前组装协议」加载上下文（9 个固定步骤），不要凭感觉读文件。
- 上下文至少覆盖：story-bible、当前卷/篇章摘要（前期缺失时以 story-bible 替代）、当前 + 下一章 blueprint、最近 3-5 章 L1 brief、上一章结尾段原文、出场实体档案、活跃伏笔、禁用桥段、关键词反查到的相关章节 brief。
- 选择提示词按 references/prompt-workflow.md。第一章用 first_chapter_draft_prompt_v2，后续章节用 next_chapter_draft_prompt_v2。
- 单章正文只输出正文，除非用户要求分析或拆解。
章节落盘与记忆更新
- 正文生成后先跑 memory-protocol.md §5「写后校验闭环」：前置字数门（机械检查 [word_min, word_max]，偏短调 enrich_prompt_v2、偏长调 condense_prompt_v2、偏离 >30% 直接重写）+ 正典冲突检测、硬约束违背、桥段重复、伏笔账本对齐。
- 通过后按固定顺序落盘：
  1. chapter-NNNN.md（L0 正文）
  2. chapter-NNNN.brief.md（L1，300-500 字，写完即冻结）
  3. chapter-NNNN.index.md（YAML 章节索引）
  4. canon/facts.jsonl 追加本章约束性事实（含 known_by）
  5. canon/promises.jsonl 追加本章承诺/誓言变化
  6. canon/progression.jsonl 追加本章境界/能力进阶
  7. canon/timeline.md / canon/rules.md 追加更新
  8. 相关实体档案追加「关键节点」+「变更记录」，更新「最后出场」「已知秘密」
  9. foreshadowing-ledger.md + subplots.md 状态更新
- 到达 chunk/arc/volume 末章时，生成对应 L2/L3/L4 摘要；卷结束时重生成 L5 summaries/global.md（旧版归档到「历史版本」段）。
- 禁止回改已冻结的 L1/L2/L3/L4。事实纠错走 continuity-issues.md + canon retraction 条目 + 实体档案变更记录。
一致性审校
- 对长篇连载，默认进行"设定冲突、角色 OOC、伏笔遗漏、节奏断裂、重复桥段"检查。
- 如果用户接入外部 RAG API 或知识库，保留外部检索能力；不要把"没有本地向量库"理解为不需要长期记忆。本项目的 chapter-*.index.md + 实体档案 + keywords 检索已足够支撑。

提示词使用原则

原始提示词全文在 references/prompts/，先查 references/prompt-index.md。
旧分支提示词适合完整写作链路：角色、世界观、剧情架构、章节目录、章节正文、摘要、知识库、角色状态、一致性。
dev 分支提示词适合从一句创意生成结构化小说基础信息。
可以组合提示词，但不要机械拼贴。先判断任务层级，再选择最小必要 prompt。
用户要求百万/千万字时，优先使用 references/long-serial-method.md 的长篇机制，而不是只放大章节数。
体裁模式由 metadata.md 的 体裁模式 字段控制（网文/严肃文学/通用），决定提示词的写作约束分支。网文模式启用爽点密度、打脸循环、章末钩子等专用规则；严肃文学模式保留潜台词、心理深度等要求。
摘要类提示词在新协议下的用法：chapter_brief_prompt 生成 L1；chunk/arc/volume/global_summary_prompt 分别生成 L2-L5；update_character_state_prompt_v2 输出落入实体档案「当前状态」段 +「变更记录」追加。

输出习惯

用中文回应中文请求。先给可执行结果，再给必要说明。创作时少讲道理，多产出可直接进入作品档案的内容。规划要清晰、有阶段、有回收点；正文要有场景推进、人物行动和情绪压力。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Long Novel Writer AI skill do?

Why use Long Novel Writer on TypingMind?

Because you install it once and use it with any model. Long Novel Writer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Long Novel Writer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jiaw-Zh/long-novel-writer/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Long Novel Writer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Long Novel Writer?

As many as you like. As long as a model supports skills, you can use Long Novel Writer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Long Novel Writer AI skill free?

It is published on GitHub by jiaw-Zh. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Skill Host Compat

affaan-m

CommunityPopular

Lint ECC skills for Codex/Cursor-safe frontmatter and Claude-only substitutions before a skill PR.

Brand Discovery

Use when a brand needs to discover or articulate its identity through structured multi-session interviews. Covers purpose, positioning, audience, personality, voice, narrative, and founder-brand…

Bun Runtime

Bun as runtime, package manager, bundler, and test runner. When to choose Bun vs Node, migration notes, and Vercel support.

Competitive Report Structure

affaan-m

CommunityPopular

Use after benchmark-methodology has produced scored competitor profile cards. Assembles findings into a decision-grade report: landscape map, competitor profiles, benchmarking matrix, white-space…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

长篇小说写作器

核心定位

工作流

提示词使用原则

输出习惯

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now