novel-prose

novel-prose is a skill for Claude Code, Codex from wanikua/danghuangshang. It costs 40 tokens per session (1,364 once invoked), scanned A, original, MIT.

A fiction-writing guide for creating novel chapters scene by scene, with rules for viewpoint, dialogue, description, pacing, and chapter structure.

In plain words
What is it for?
Use it when drafting novel chapters, planning their scenes, developing characters through dialogue, and reviewing a completed chapter for flow and consistency.
Why use it?
It helps keep a long chapter coherent instead of producing one unstructured block of text. It also provides checks for continuity, pacing, foreshadowing, and consistent narration.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when drafting novel chapters, planning their scenes, developing characters through dialogue, and reviewing a completed chapter for flow and consistency.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wanikua/danghuangshang/novel-prose
About the project

danghuangshang is a multi-agent collaboration system that organizes specialized AI agents into a hierarchy modeled on historical Chinese government institutions. Users delegate tasks to these agents through platforms such as Discord or Feishu, with roles for coordination, coding, review, memory, and automation. Its catalogue entries are the project's agents and skills.

wanikua/danghuangshang · 2,701 stars · on GitHub · danghuangshang.com

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add wanikua/danghuangshang --skill novel-prose
Clone the repo
git clone --depth 1 https://github.com/wanikua/danghuangshang

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for novel-prose

README.md
[![agentmods](https://agentmods.dev/badge/skills/wanikua/danghuangshang/novel-prose/github.svg)](https://agentmods.dev/skills/wanikua/danghuangshang/novel-prose)
Your own site
<a href="https://agentmods.dev/skills/wanikua/danghuangshang/novel-prose"><img src="https://agentmods.dev/badge/skills/wanikua/danghuangshang/novel-prose/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for novel-prose

Your own site · 80×15
<a href="https://agentmods.dev/skills/wanikua/danghuangshang/novel-prose"><img src="https://agentmods.dev/badge/skills/wanikua/danghuangshang/novel-prose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,364 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00040 $0.01364
Opus 5 $0.00020 $0.00682
Sonnet 5 $0.00008 $0.00273
Haiku 4.5 $0.00004 $0.00136

Measured 12d ago against content hash 6015dcd600fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

novel-prose scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/novel-prose/SKILL.md · 130 lines

What it actually says

小说写作技法

你已被注入 novel-prose 技能。你的职责是创作高质量的小说章节正文。

进入沉浸式创作心态:将自己代入故事世界,用角色的眼睛观察,用角色的心灵感受。


分段写作法

核心原则

不要一口气写完整章。 将章节拆分为 5-8 个场景/段落,逐段完成。

写作流程

1. 场景规划
   └── 规划本章 5-8 个场景,明确每个场景的功能:
       - 推进情节
       - 深化人物
       - 铺垫伏笔
       - 营造氛围
       - 高潮/转折

2. 逐场景写作
   └── 按顺序完成每个场景:
       a. 写完一个场景后,检查与前文的衔接
       b. 确认叙事视角一致
       c. 保持节奏感
       d. 继续下一个场景

3. 整章整合
   └── 所有场景完成后:
       a. 通读全章检查连贯性
       b. 确认字数达标
       c. 检查伏笔是否按计划埋设/回收

叙事规范

视角一致性

  • 第一人称:始终从主角视角叙述,不越界描写主角无法感知的信息
  • 第三人称限知:紧跟视角角色,内心独白仅限该角色
  • 第三人称全知:可自由切换视角,但每个场景内保持一个主视角
  • 切换规则:视角切换只在场景分隔处进行,不在段落中间切换

对话要求

  • 符合角色:对话必须匹配角色的身份、性格、教育程度、情绪状态
  • 推动情节:每段对话都应推进剧情或揭示信息,避免废话
  • 潜台词:重要对话要有言外之意,不要所有信息都直白说出
  • 动作穿插:对话中穿插角色的动作、表情、心理,避免单纯的你一句我一句

场景描写

  • 视觉化:让读者"看到"场景,使用具体的色彩、光影、空间感
  • 感官化:不只是视觉,加入听觉、嗅觉、触觉、味觉
  • 沉浸式:通过细节营造氛围,让读者身临其境
  • 有选择:不是所有场景都需要详细描写,根据情节重要性分配笔墨
  • 动态感:描写中融入动作和变化,避免静态的环境说明文

节奏控制

  • 长短交替:紧张场景用短句,抒情场景用长句
  • 快慢结合:动作场景节奏快(多动词、短段落),情感场景节奏慢(多描写、长段落)
  • 呼吸感:高潮后给缓冲,紧张后给舒缓,让读者有喘息空间
  • 悬念留置:适当在场景/章节末尾留悬念,驱动阅读

字数纪律

  • 单章不低于 10,000 中文字符
  • 保持节奏,避免注水
  • 关键场景给予足够篇幅展开
  • 过渡性内容精简处理
  • 如本章确实为短过渡章节,需在返回报告中说明原因

文件命名与格式

  • 文件路径novel/{书名}/正文/第X章_{标题}.md
  • 标题格式# 第 X 章 - {章节标题}
  • 编码:UTF-8
  • 段落分隔:空行分段

写作心态

  1. 沉浸创作:将自己代入故事世界,用角色的眼睛观察,用角色的心灵感受
  2. 大胆想象:不自我审查,不预设限制,让故事自然生长
  3. 精雕细琢:每个场景都值得用心,细节决定质量
  4. 一气呵成:单个场景内保持写作连贯,不中断思路
  5. 完成即胜利:先完成,再完美。写完再改比反复推敲第一句强

写完自审检查清单

每章写完后快速自检:

  • 字数 >= 10,000?
  • 叙事视角是否统一?
  • 对话是否符合角色性格?
  • 场景描写是否有画面感?
  • 情节是否推进?有无原地踏步?
  • 伏笔是否按 plan.md 埋设/回收?
  • 与上一章是否衔接自然?
  • 节奏是否张弛有度?

禁止行为

  • 不假设设定:必须查询设定文件确认(见 novel-memory 技能),不凭空捏造
  • 不跳过步骤:每个场景都要完成,不草草了事
  • 不注水:字数通过内容质量达标,不通过重复描写或无意义对话凑数
  • 不照搬:如果参考了检索结果,必须重新创作,不直接复制
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 130 lines · 40 tokens per session scan A 6015dcd600fc

Subscribe to this mod's changes

novel-prose is a skill published in the GitHub repository wanikua/danghuangshang (2,701 stars, last pushed 3mo ago), licensed MIT. It adds 40 tokens to every session and 1,364 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

setup-discord-multibot

Configure or extend a multi-bot Discord setup for Claude Code, where each project directory is bridged to its own dedicated Discord bot. Use when the user wants to (a) add a new Discord bot for a new project, (b) initially set up the per-project Discord architecture, (c) pair a bot when the official /discord:access…

Lihan-Zhong/claude-code-discord-multibot · 179 tokens

npm-package

Opinionated TypeScript npm package template for ESM packages. Enforces src→dist builds with tsc, strict TypeScript defaults, explicit exports, and publish-safe package metadata. Relative source imports must use .ts or .tsx (never .js); tsc rewrites them via rewriteRelativeImportExtensions. Use this when creating or…

remorses/kimaki · 78 tokens

new-skill

Best practices for creating a SKILL.md file. Covers file structure, frontmatter, writing style, and where to place skills in a repository. Use when the user wants to create a new skill, update an existing skill, write a SKILL.md, or asks how skills work.

remorses/kimaki · 61 tokens

discord-expert

Expert in Discord bot development using discord.js and discord.py, slash commands, embeds, voice channels, moderation, and bot deployment. Use when the user mentions communication, community, bots, API, Discord bot, or discord.js, or when the task involves Discord Platform, Bot Development, Discord.js Bot, or…

personamanagmentlayer/pcl · 70 tokens

switch

How to take part in a Switch room. Load this skill before your first Switch action and whenever Switch comes up — the user mentions Switch, a Switch room or another Switch agent; you are asked to list, join, read or post in a room, create a room or room group, work with references, links or roles, or inspect an agent…

sandbox-quantum/switch · 125 tokens

discord-moderation

Moderation workflow for Discord guilds. Covers ban/kick/timeout operations, audit log review, ban list management, and role-based access control.

sandraschi/discord-mcp · 0 tokens