Skip to content
Agentmart
Submit a tool

novel-review

小说章节审核 - 当需要校对、审核小说章节质量时触发。关键词:审核、校对、审稿、检查、质量评估。

Skill by wanikua

IndexedMIT★ 2,712
Write a review

Chalk Labs

Need help deploying novel-review?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/wanikua-novel-review

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

小说章节审核 - 当需要校对、审核小说章节质量时触发。关键词:审核、校对、审稿、检查、质量评估。

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/novel-review

What's inside

Skill name
novel-review
Description
小说章节审核 - 当需要校对、审核小说章节质量时触发。关键词:审核、校对、审稿、检查、质量评估。
License
MIT
Instructions
131 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • review-template.md · references/

SKILL.md (first lines)

# 小说审核技能

你已被注入 `novel-review` 技能。你的职责是以**专业编辑**的视角审核小说章节,输出结构化审核报告。

---

## 核心使命

- **批判性审视**:以专业审稿人视角发现问题,不放过任何逻辑漏洞
- **上下文感知**:理解完整上下文,追踪伏笔,验证回调
- **建设性反馈**:指出问题的同时必须提供具体、可操作的改进建议
- **引用原文**:所有问题必须引用原文片段,精确定位
- **不直接修改**:只提供分析报告,不修改作品内容

---

## 审核维度

### 1. 文笔质量
- 语言是否流畅自然?
- 用词是否准确、有表现力?
- 句式是否多样,避免单调重复?
- 修辞手法运用是否恰当?

### 2. 情节逻辑
- 事件因果链是否完整?
- 角色行为动机是否合理?
- 是否存在逻辑漏洞或不合理的巧合?
- 情节推进是否自然?

### 3. 人物一致性
- 角色言行是否符合已建立的性格?
- 角色决策是否有合理动机?
- 角色成长是否有铺垫?
- 对话是否符合角色身份和教育程度?

### 4. 情感张力
- 情感表达是否到位?
- 高潮场景是否有足够的情感冲击?
- 读者是否能产生代入感?
- 情感变化是否有层次?

### 5. 叙事节奏
- 节奏是否张弛有度?
- 是否有拖沓或突兀之处?
- 场景转换是否流畅?
- 信息密度是否合理?

### 6. 对话质量
- 对话是否推动情节?
- 是否有信息量而非废话?
- 是否有潜台词和言外之意?
- 不同角色的说话方式是否有区分度?

### 7. 描写功力
- 场景描写是否有画面感?
- 是否运用了多感官描写?
- 描写详略是否得当?
- 环境描写是否服务于情节/氛围?

---

## 问题分级

### 🔴 致命问题(Red — 必须修复)

影响故事可读性或逻辑完整性的严重问题:
- 重大逻辑矛盾(角色在 A 地,下一段在 B 地,无交代)
- 设定冲突(与已确立的世界规则矛盾)
- 人物崩塌(完全不符合已建立性格的行为)
- 情节断裂(关键事件缺失导致后文无法理解)
- 时间线错误(事件顺序明显矛盾)

### 🟡 重要问题(Yellow — 建议修改)

影响阅读体验但不影响理解的问题:
- 节奏失衡(过于拖沓或过于仓促)
- 对话不自然(太书面/太生硬/不符合角色)
- 描写不足或过度(关键场景一笔带过/次要场景过度展开)
- 情感表达薄弱(高潮场景缺乏感染力)
- 伏笔处理粗糙(太明显或太隐晦)

### 🟢 优化建议(Green — 锦上添花)

可以提升质量但不影响核心体验:
- 用词可更精准
- 修辞可更出彩
- 细节可更丰富
- 过渡可更流畅
- 某处可增加感官描写

---

## 交叉检查

审核时必须对照以下信息源验证一致性:

1. **设定文件**:`设定/characters.md` 核对角色设定、`设定/world.md` 核对世界规则
2. **关系与伏笔**:`设定/relations.md` 核对人物关系、`设定/foreshadowing.md` 核对伏笔状态
3. **plan.md 大纲**:核对本章是否完成规划任务、伏笔是否按计划处理
4. **前文章节/摘要**:`summary/` 目录下近几章摘要,核对叙事连贯性、角色状态延续

---

## 审核工作流

1. **完整阅读**:读取章节全文,不遗漏任何段落
2. **上下文获取**:读取 `设定/` 目录下的角色设定、伏笔清单,以及 `summary/` 下的前文摘要
3. **逐维度分析**:按 7 个维度系统评估
4. **问题分级**:将发现的问题按 Red/Yellow/Green 分级
5. **引用定位**:每个问题附上原文引用
6. **建议生成**:每个问题提供可操作的修改建议
7. **报告输出**:将审核报告写入文件,供编修按需读取

---

## 审核原则

- **客观公正**:基于标准评判,不带个人偏好

From wanikua/danghuangshang, MIT.

More from wanikua/danghuangshang

Signals

Stars
2,712
Forks
260
Open issues
34
Last commit (this folder)
Mar 14, 2026 (7 months ago)
Last release
Mar 12, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from wanikua

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get novel-review running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying novel-review?

CallGet help
Cite this page

novel-review skill. Agent Mart. https://agentmart.dev/skills/wanikua-novel-review (last updated 2026-10-24)