Novel Review logo

Novel Review

Community
Wooooooooood
novel-review

小说多视角审稿工具。支持编辑视角、读者视角、平台视角、作者视角四维度审稿,提供评分、毒点排查、修改建议。当用户需要审稿件、查毒点、评分数、改文章时使用。触发词:审稿、审查、评分、毒点、修改建议、多视角、质检。

Overview

PublisherWooooooooood
Repositoryai-fiction-writer
Skill namenovel-review
Stars
67
Forks
11
Bundled files
Instructions only
LicenseMIT
Links
  • 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 Wooooooooood on GitHub. Read the source before you install it.

Installation

Install the Novel Review 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/Wooooooooood/ai-fiction-writer/tree/main/纯净版skill/novel-review
  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.

Use it in TypingMind

Enable Novel Review 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 Review 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 Review 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 Review — 多视角审稿

核心思路:好作品是改出来的,专业审稿 = 提前发现读者弃书点

四维审稿体系:

  1. 编辑视角:商业价值、节奏、钩子、爽点
  2. 读者视角:代入感、期待感、情绪满足、弃书风险
  3. 平台视角:各平台推荐机制适配
  4. 作者视角:设定一致性、伏笔回收、角色OOC

工作区规范

.novel/
├── tracking/
│   └── review-reports/      # 审稿报告存档
│       ├── ch01-20260601.md
│       └── ch02-20260602.md
└── references/
    └── 审稿标准.md          # 各平台评分标准

审稿前准备

  1. 重新读取当前正文:审稿前必须读取 chapters/vol{N}-{卷名}/ch{NN}.md 当前版本,禁止基于记忆中的旧版本评价
  2. 核对版本号:报告文件名或元数据中标注版本(如 draft-v1 / draft-v2 / user-revision)
  3. 识别用户本轮改动:若用户说"我又调整了一下",必须在报告中单独评价本轮改动是否有效
  4. 同步报告与正文:报告中的引用、得分、建议必须与当前正文一致

四维审稿体系

1. 编辑视角(商业价值)

审稿要点:

检查项权重合格标准
开篇力20%前500字有钩子,前3000字有爽点
节奏感20%每3章至少1个爽点,无连续3章平淡
钩子密度15%每章结尾有悬念或期待
爽点设计15%爽点类型多样,不重复
人设鲜明15%主角有记忆点,配角不脸谱
题材适配15%符合目标平台读者偏好

编辑审稿输出:

markdown
## 编辑审稿:第{X}章

### 开篇力:{得分}/100
- {问题描述}
- {修改建议}

### 节奏感:{得分}/100
- {问题描述}
- {修改建议}

### 总体评价
- 商业价值:{高/中/低}
- 修改优先级:{P0/P1/P2}
- 核心建议:{一句话总结}

2. 读者视角(代入感与情绪)

审稿要点:

检查项权重合格标准
代入感25%主角有共鸣点,读者能共情
期待感25%有明确的目标和阻碍,读者想知道后续
情绪满足25%爽点到位,憋屈有释放
弃书风险25%无雷点、无毒点、无逻辑硬伤

读者审稿输出:

markdown
## 读者审稿:第{X}章

### 代入感:{得分}/100
- 共鸣点:{描述}
- 疏离感:{描述}

### 期待感:{得分}/100
- 当前目标:{描述}
- 阻碍力度:{描述}
- 读者想知道:{描述}

### 情绪曲线
- 本章情绪峰值:{位置},{情绪类型}
- 本章情绪低谷:{位置},是否合理
- 情绪是否释放:{是/否}

### 弃书风险评估
- 雷点:{有无}
- 毒点:{有无}
- 逻辑硬伤:{有无}
- 总体弃书概率:{低/中/高}

3. 平台视角(推荐机制适配)

各平台标准(在 审稿标准.md 中配置):

平台A示例:

指标权重合格线
读完率30%前3章读完率 > 60%
留存率30%7日留存 > 20%
互动率20%段评/章评密度
更新稳定性20%日更4000+,不断更

平台B示例:

指标权重合格线
收藏率30%新书期收藏/点击 > 5%
追读率30%VIP章节追读 > 30%
月票20%新书月票榜前500
粉丝值20%粉丝活跃度

平台审稿输出:

markdown
## 平台审稿:第{X}章(目标:{平台})

### 读完率预估
- 前3章吸引力:{高/中/低}
- 断章位置:{是否合理}
- 读完率预估:{X}%

### 留存率预估
- 期待感建立:{是否充分}
- 追更动力:{强/中/弱}
- 留存率预估:{X}%

### 推荐机制适配
- 是否符合"读了还想读"标准:{是/否}
- 是否符合"互动引导"标准:{是/否}
- 优化建议:{描述}

4. 作者视角(设定一致性)

审稿要点:

检查项权重合格标准
时间线25%时间逻辑正确,无倒流、无冲突、上下午标注清晰
世界观一致性20%地点/势力/规则/文化与 worldbuilding 一致,地理移动合理
细节逻辑一致性20%每段在场人物明确、位置衔接自然、动机合理、信息有来源
设定一致性10%无前后矛盾、无吃书
伏笔回收15%伏笔有埋有收,不烂尾
角色OOC10%角色言行符合档案设定

作者审稿输出:

markdown
## 作者审稿:第{X}章

### 设定一致性
- 知识库核对:{通过/不通过}
- 矛盾点:{描述}

### 伏笔状态
- 新埋伏笔:{N}个
- 回收伏笔:{N}个
- 待回收伏笔:{N}个(列表)

### 角色OOC检测
- 出场角色:{列表}
- OOC风险:{有无}
- 具体问题:{描述}

### 时间线核对
- 故事日期:{日期}
- 时间逻辑:{正确/错误}
- 问题:{描述}

### 细节逻辑一致性核对
- 段落级在场人物:{清晰/不清晰}
- 位置衔接:{自然/突兀}
- 角色动机:{合理/不合理}
- 信息/道具来源:{有铺垫/无铺垫}
- 知情边界:{无穿帮/有穿帮}
- 微逻辑卡与四问执行:{完整/缺失}
- 问题:{描述}

### 修改后一致性核对(如本章经过修改)
- 修改范围:{描述}
- 是否反向检查前章:{是/否}
- 伏笔/钩子状态是否仍与正文一致:{是/否}
- 逻辑矩阵/知情边界是否已同步:{是/否}
- 问题:{描述}

### 世界观一致性核对
- 地点档案:{通过/不通过}
- 势力关系:{通过/不通过}
- 规则使用:{通过/不通过}
- 地理移动:{通过/不通过}
- 文化禁忌:{通过/不通过}
- 问题:{描述}

毒点排查清单

致命毒点(P0,必须改)

  • 主角三观不正(违法、 unethical 行为无代价)
  • 严重的逻辑硬伤(时间穿越、人物瞬移)
  • 设定前后矛盾(前面说A,后面说B)
  • 世界观核心设定前后矛盾(如金手指规则突变、势力关系无铺垫改变)
  • 角色严重OOC(性格突变无铺垫)
  • 角色行为违反所属势力/种族/职业/阶层设定
  • 时间线矛盾(上一章已结束的事件本章重复、时间倒流)
  • 地理移动矛盾(瞬移、交通时间严重不符)
  • 角色言行超出其知情边界
  • 信息/道具/称呼无前文铺垫
  • 新增配角未建档或档案与正文矛盾
  • 新增地点/势力/规则未建档或与世界building冲突
  • 涉政敏感内容

严重问题(P1,建议改)

  • 连续3章无爽点
  • 章节结尾无钩子
  • 对话过于书面化
  • 描写模板化("嘴角微微上扬"等)
  • 配角脸谱化(纯工具人)
  • 相邻章节重复描写同一动作/神态/解释
  • 解释性旁白过多("他知道"/"这意味着"/"这是为了")
  • 章尾钩子被大段环境描写或内心独白稀释
  • 角色行为与职业/身份档案冲突
  • 地点描写与世界building档案不一致
  • 势力关系使用错误(如把盟友写成敌对)
  • 规则/能力使用模糊或超限
  • 地理移动未交代清楚,存在瞬移嫌疑
  • 段落中人物位置关系不清晰
  • 角色动机不足或行为突兀
  • 信息来源交代不清
  • 未执行动作前四问或微逻辑卡缺失
  • 修改后未更新逻辑矩阵
  • 修改后未更新知情边界
  • 修改后未在 修改记录.md 中留痕

一般问题(P2,可优化)

  • 句长过于单一
  • 标点运用单调
  • 情绪直给("他很愤怒")
  • 信息密度不均
  • 过渡生硬
  • 时代场景出现不合时宜的中英夹杂
  • 角色方言/粗口与其籍贯档案不符
  • 文化风俗细节不准确或与世界building不一致
  • 地点/建筑描写可增加五感细节
  • 势力/组织背景可进一步铺垫

评分标准

总分计算:

总分 = 编辑视角(22%) + 读者视角(28%) + 平台视角(20%) + 作者视角(30%)

评级:

分数评级说明
85-100S级可以直接发
75-84A级接近标准,需针对性修改至85分
65-74B级需要修改,有亮点
55-64C级大修,问题较多
<55D级建议重写

使用方法

单章审稿

用户:帮我审一下第4章
→ 重新读取当前正文
→ 四维度审稿
→ 毒点排查
→ 评分 + 修改建议(基于当前版本)
→ 若用户本轮有调整,单独评价调整效果

批量审稿

用户:帮我审一下前10章
→ 逐章审稿
→ 汇总报告(趋势分析、共性问题)

对标审稿

用户:把我第4章和对标书第4章对比审一下
→ 对标分析
→ 差距识别
→ 改进建议

与写作skill的配合

  1. 写完 → 审稿:每章写完后自动触发审稿
  2. 审稿 → 修改:根据审稿报告修改
  3. 修改 → 再审:修改后再审,直到达到S级(85分以上)
  4. 定稿 → 发布:S级(85分以上)才能发布

Frequently asked questions

What does the Novel Review AI skill do?

小说多视角审稿工具。支持编辑视角、读者视角、平台视角、作者视角四维度审稿,提供评分、毒点排查、修改建议。当用户需要审稿件、查毒点、评分数、改文章时使用。触发词:审稿、审查、评分、毒点、修改建议、多视角、质检。

Why use Novel Review on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Wooooooooood/ai-fiction-writer/tree/main/纯净版skill/novel-review. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Novel Review?

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 Review?

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

Is the Novel Review AI skill free?

Yes. It is published on GitHub by Wooooooooood under the MIT license. 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

Set up your own AI workspace now

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