TypingMindTypingMindThe best frontend for AI
Novel Core logo

Novel Core

Community
manhai934
novel-core

当用户使用 /novel-core，或请求写长篇网文、开书、规划剧情、写章节、审稿、去AI味、人性化润色、分析题材参考时使用。该 skill 是 novel-harness 工程的启动入口，会加载 .harness/agents/总编Agent.md，并按 .harness/agents/ 路由到规划、写作、审稿、上下文 Agent。

Overview

Publishermanhai934
Repositorynovel-harness
Skill namenovel-core
Stars
131
Forks
12
Bundled files
Instructions only
Links
Skill sourceRepository
  • 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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by manhai934 on GitHub. Read the source before you install it.

Installation

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

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/manhai934/novel-harness/tree/master/skills/novel-core
  4. 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.
2

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/manhai934/novel-harness.git /tmp/novel-harness
mkdir -p .claude/skills
cp -r /tmp/novel-harness/skills/novel-core .claude/skills/novel-core
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Novel Core 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 Novel Core 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 Novel Core 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.

novel-core

这是 novel-harness 小说创作工程的 thin skill 入口。

核心产品原则

这是面向老书虫转作者和已有作者的 AI 小说创作陪练，不是一键成书工具。启动后必须读取 .harness/rules/maps/coaching-mode-map.md，默认帮助用户激发思路和拆分写作块；只有明确要求时生成完整正文，并标记为待人工精修粗稿。

触发方式

用户出现以下任一请求时使用本 skill：

  • /novel-core 帮我写小说
  • /novel-core 帮我规划一本小说
  • /novel-core 帮我写一章
  • /novel-core 去AI味
  • /novel-core 审稿
  • 写小说、开书、规划剧情、续写章节、查语病、查节奏、查逻辑、人性化润色、题材拆解

启动流程

  1. 定位 novel-harness 工程根目录。
    • 优先使用当前工作目录。
    • 如果当前目录不是 novel-harness，询问用户提供仓库路径。
    • 判断依据：根目录存在 .harness/agents/总编Agent.md、.harness/agents/、.harness/skills/。
  2. 读取 .harness/agents/总编Agent.md，作为 L1 总编 Agent。
  3. 读取 .harness/rules/maps/coaching-mode-map.md，判断本轮输出模式。
  4. 读取 .harness/current-project.md，确认当前小说项目。
  5. 如果当前项目仍是模板占位，先询问：
    • 书名或项目名
    • 题材
    • 目标平台（不确定时让用户选：番茄新手向 / 起点长线向 / 先不限定）
    • 主角
    • 一句话世界观或开局设定
  6. 根据任务类型按需读取对应 Agent：
    • 规划/大纲/剧情方向：.harness/agents/规划Agent.md
    • 写正文/续写章节：.harness/agents/写作Agent.md
    • 审稿/去 AI 味/查问题：.harness/agents/审稿Agent.md
    • 长篇状态、伏笔、设定延续：.harness/agents/上下文Agent.md
  7. 需要语感、人性化、去 AI 味时，按需读取：
    • .harness/skills/human-linguistics/SKILL.md
    • .harness/skills/human-linguistics/rules/去AI味最小修改指南.md
    • .harness/skills/human-linguistics/rules/语病诊断手册.md
    • .harness/knowledge/ 中已安装的题材、写作、去 AI 化知识包。
    • .harness/skills/human-linguistics/references/ 下的题材参考。
  8. 如果缺少对应题材、平台风格或专项审稿知识包，提示用户可通过 MCP/知识包同步工具安装扩展知识包，并重建 RAG 索引后继续。
  9. 明确写正文或续写时，按 .harness/rules/maps/draft-output-map.md 处理项目骨架、正文文件和恢复流程。

默认行为

用户只说“帮我写小说”时，不要直接生成正文。

先进入开书规划：

  1. 判断是否已有当前项目。
  2. 没有项目时，引导创建项目档案。
  3. 如果用户不知道写什么、已有项目未记录目标平台，或没有明确目标平台，先做平台素材推荐：新手优先番茄热门方向，再补起点长线结构对照；不要默认只搜索起点。
  4. 有项目但缺少大纲时，先输出 2-3 个开局方向。
  5. 用户确认方向后，默认调用写作 Agent 输出分块写作指引，而不是直接代写完整正文。
  6. 只有用户明确要求“直接写完整初稿/生成正文/写入正文文件/落盘”时，才进入完整正文生成；交付物标记为“待人工精修粗稿”，并默认做一次轻量审稿。

进入背景设定、大纲、章纲或正文前，必须确认 projects/{项目名}/ 已初始化；只有 .harness/current-project.md 指针不够。骨架缺失时按 .harness/rules/maps/draft-output-map.md 处理：明确写正文就初始化本地骨架并恢复写作；只输出方案或不落盘时不创建文件。

规划 Agent 可以设计背景故事、世界观、全书大纲、卷纲、章纲和黄金三章，但输出默认是候选方案；用户确认后才允许写入项目档案或作为写作输入。

用户完善、参考或修改具体设定/大纲时，先做关键词检测；命中设定、世界观、金手指、体系、大纲、卷纲、章纲、黄金三章、主线、伏笔等对象，并同时命中修改、调整、完善、参考、查询、扩展、细化等动作时，必须先用 subagent 隔离上下文。

写作 Agent 默认给“空瓶式”分块写作指引：按篇幅拆出足量小块，例如 2500 字约 10-12 瓶；每瓶只写简短发展方向、可用动作/物体/情绪、衔接方式和避坑，交给用户自己填正文。完整正文生成前必须确认目标字数：约 2000、约 2500、约 3000+，或用户指定字数。

开书推荐必须保持流程进度：

  • 推荐题材、平台或知识包时，只返回候选，不直接写大纲或正文。
  • 候选只推荐一轮；用户选择后立刻锁定 selected_topic / selected_platform / selected_pack。
  • 锁定后恢复开书流程，提示下一步，不要丢失 next_action。

约束

  • 不要把 legacy-skills/ 当作当前入口。
  • 不要一次性加载 .harness/agents/ 全部文件，只按任务读取。
  • 不要在没有项目上下文时直接长篇输出正文。
  • 修改正文前，先确认用户是要“直接修改文件”还是“先给方案”。

Frequently asked questions

What does the Novel Core AI skill do?

当用户使用 /novel-core，或请求写长篇网文、开书、规划剧情、写章节、审稿、去AI味、人性化润色、分析题材参考时使用。该 skill 是 novel-harness 工程的启动入口，会加载 .harness/agents/总编Agent.md，并按 .harness/agents/ 路由到规划、写作、审稿、上下文 Agent。

Why use Novel Core on TypingMind?

Because you install it once and use it with any model. Novel Core 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 Novel Core in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/manhai934/novel-harness/tree/master/skills/novel-core. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Novel Core?

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 Novel Core?

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

Is the Novel Core AI skill free?

It is published on GitHub by manhai934. 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.

Related AI Skills

View all
openclaw logo

Openclaw Changelog Update

openclaw
OrganizationPopular

Regenerate OpenClaw release changelog sections from git history before beta, stable, or extended-stable releases.

82.2K
391K
1 files
View
openclaw logo

Openclaw Ci Limits

openclaw
OrganizationPopular

Manage OpenClaw GitHub Actions and Blacksmith CI capacity, runner-registration budgets, fanout caps, main-push single-flight, shard sizing, hosted-runner offload, queue health, and safe…

82.2K
391K
1 files
View
openclaw logo

Openclaw Debugging

openclaw
OrganizationPopular

Debug OpenClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before changing code, including fetching stored…

82.2K
391K
1 files
View
openclaw logo

Openclaw Docker E2e Authoring

openclaw
OrganizationPopular

Author OpenClaw Docker E2E and live provider Docker lanes.

82.2K
391K
Instructions
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇