Agent skill

Novel Structure

by yannikzz in yannikzz/narracat-novel-agent

Narrative structure knowledge for long-form web fiction, covering emotional stakes, tension rhythm, climax layering, foreshadowing payoff pacing, value shifts and event architecture, multi-thread…

AGPL-3.0Auto-check passedWriting & Content

Install Novel Structure

skills CLI
$ npx skills add yannikzz/narracat-novel-agent --skill novel-structure -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install yannikzz/narracat-novel-agent novel-structure --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/yannikzz/narracat-novel-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agent-core/narracat/skills/novel-structure .claude/skills/novel-structure && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
novel-structure
GitHub stars
105
Token cost
~1.7k tokens
SKILL.md length
307 words
Files
12 (incl. references)
Skills in repo
7
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Narrative structure knowledge for long-form web fiction, covering emotional stakes, tension rhythm, climax layering, foreshadowing payoff pacing, value shifts and event architecture, multi-thread…

  • Planning outlines
  • SKILL.md covers 一、情感赌注与节奏, 二、伏笔兑现节奏, 三、价值转换与事件架构 and 四、多线编织, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve Creative writing and fiction

What it does

Novel Structure is an agent skill from yannikzz/narracat-novel-agent. Narrative structure knowledge for long-form web fiction, covering emotional stakes, tension rhythm, climax layering, foreshadowing payoff pacing, value shifts and event architecture, multi-thread weaving, arc design, and chapter ending hooks. Use when planning outlines.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including reference files (for example `references/packs/arc-rhythm.md`, `references/packs/foreshadow-distance.md` and `references/packs/hook-cadence.md`).

It sits in Writing & Content, covering Creative writing and fiction. The repository describes itself as: 面向中国网文作者的 AI 共创桌面应用 | AI-powered desktop writing studio for Chinese web novels. The licence is AGPL-3.0.

When your agent uses it

  • Planning outlines
  • Tasks that involve Creative writing and fiction

Example prompts

  • “/novel-structure”

What it can do on your machine

Read from SKILL.md and the folder at commit 2c49f9f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Novel Structure loads about 1.7k tokens when it runs, and up to ~17k if it reads all its reference files. Until then it costs about 72 tokens; SKILL.md has 307 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~72
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~17k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from yannikzz/narracat-novel-agent at commit 2c49f9f, republished under its AGPL-3.0 licence (© yannikzz). 307 words, ~1,724 tokens.

Download SKILL.mdSave it as .claude/skills/novel-structure/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.
name
novel-structure
description
Narrative structure knowledge for long-form web fiction, covering emotional stakes, tension rhythm, climax layering, foreshadowing payoff pacing, value shifts and event architecture, multi-thread weaving, arc design, and chapter ending hooks. Use when planning outlines.

你是叙事结构的领域知识库。核心问题只有一个:这个故事凭什么让读者放不下?

  • 规划阶段一(书级 storylines / 伏笔注册表、卷级、arc)时,先调用 novel_list_structure_cards(stage="stage-1"),把返回的每张卡用 Read 读完再动手。
  • 规划阶段二·章级细纲时,先调用 novel_list_structure_cards(stage="stage-2"),把返回的每张卡用 Read 读完再动手(断点候选模式除外——它只定收口点不产章纲,不必调)。
  • 规划全书开局(第 1 卷首个 arc 或前三章章纲)时,先调用 novel_list_structure_cards(stage="stage-opening"),把返回的每张卡用 Read 读完再动手(续卷/中段规划不必调)。

一、情感赌注与节奏

情感赌注驱动

每章规划的第一个问题不是「这章发生什么事」,而是**「角色在这章可能失去什么」**。

  • 用具体的情感赌注描述本章风险(「张三可能永远失去李四的信任」,而非一个抽象等级)
  • 赌注越具体、越私人,读者越紧张。「天下苍生」不如「他唯一的朋友」
  • 没有赌注的章节是温吞的——日常铺垫章也要有微赌注(一个小秘密可能被发现、一段关系出现裂痕的苗头)
压抑-释放节奏

情绪不是匀速前进的,而是波浪:蓄压 → 释放 → 再蓄压 → 更大释放。释放强度必须递增——弱释放排在强释放之后是反高潮。

  • 蓄压手段: 角色受辱/被误解/实力被低估、敌人步步紧逼、读者知道危险但角色不知道(戏剧反讽)、配角的痛苦积累
  • 释放手段: 真相揭露、逆袭反击、情感爆发、不可逆选择的后果显现
高潮分层
级别频率功能
微高潮每 1-2 章维持阅读动力(一个小胜利、一个问题解决)
小高潮每个 arc 内部完成一段蓄压的释放
中高潮每个 arc 结尾结算 arc 核心问题
大高潮每卷结尾完成卷级故事弧

(微高潮 1-2 章一次有头部语料实测背书,见 payoff-cadence 包的爽点间隔实证。)

高潮之间必须有谷底——小高潮直接接大高潮,情绪在小高潮已到极点,大高潮反而上不去。长段落无任何级别高潮就是死区。

高潮后禁止直接跳回日常,必须有余波承接:处理高潮后果、角色消化冲击、新格局初现。

卷级节奏模板
位置功能
卷首建置新冲突/新环境,设置卷级悬念(第 1 卷卷首 = 全书开局,另见下一节生死线规则)
~25%第一转折点——主角被卷入卷级核心冲突
中段压力升级,伏笔埋设
~50%中点——虚假胜利或虚假失败,翻转上半段方向
后半段压力最大化,盟友动摇,「一切尽失」
~75%第二转折点——新信息/新觉悟,进入最终对决
卷末卷级高潮——不可逆改变 + 下卷钩子

后续卷的卷首是「续航」:读者已上船,承接上卷余波、建置新舞台即可。全书第 1 卷的卷首是「生死线」——读者还没上船,弃书最密集,规则更硬,见下一节。

卷末高潮不是单章事件,是连续抬升的高潮簇:临近卷末连排多个递增的兑现章(中爽连着大爽),在最高点完成不可逆改变,随后一到两章余波收束并埋下卷钩。簇内强度必须递增,最强一章就是卷的顶点——顶点之后立即收,不再横生新对抗;下卷钩子落在余波章末,不落在顶点章。

全书开局(黄金三章)

全书的开头几章决定读者读不读得下去,是整本书最该重写的位置。规划第 1 卷的首个 arc 时,第一屏怎么搭、有生活怎么落、卖点怎么翻译成事件,先读 opening-hook 与 selling-point-front 两包取具体搭法;本节的四件事、禁区与揭示条款仍按下文执行。开篇结构必须同时立住四件事,且越靠前越满:

  • 立住主角:主角第一时间登场并拥有记忆点——一个鲜明的处境、欲望或反差,让读者记住「这是谁、他想要什么」。不要先铺背景再让主角出场。
  • 抛出核心冲突:全书的核心矛盾(或它的第一个具体化身)在开篇就显形,让读者立刻知道这本书在赌什么。核心冲突来得越晚,开局越冷。
  • 留下钩子:开篇章末必须有一个让人想翻下一页的悬念或威胁,不靠「后面会精彩」的承诺续命。
  • 亮出本书卖点:本书的核心爽点 / 金手指 / 最大看点,黄金三章里至少亮一次相——让读者在上船前就尝到这本书「独一份」的味道。别把卖点的首次兑现拖到开局 arc 的释放期,那时读者可能已经走了。(亮相时机实测见 selling-point-front 包)

开篇强度是收紧的:黄金三章里第一章最关键,第一章里又是开头的第一幕最关键——把最强的钩子和主角的记忆点压到最前面,而不是匀速铺开。

全书开局禁区(命中任何一条,开局就「冷起」,读者在上船前流失):

  • 长楔子 / 世界观倾倒:用大段楔子、设定讲解或历史背景开场,主角和冲突被推到后面。设定要随剧情需要被揭示,不在开篇一次性倾倒。
  • 焦点转配角:开篇把镜头交给配角或群像,主角迟迟不登场或被稀释,读者找不到代入对象。
  • 系统对话开场:用一段系统/金手指的功能介绍或冷冰冰的对话作为静态开场,没有处境、没有人物、没有冲突。

世界观揭示随剧情需要铺开,不追求开局前置:头部网文的揭示密度前 20 章只略高于后期(约三成对约两成半),从不开局灌设定。每次揭示挂在剧情动作上——角色为解决眼前问题被迫接触新规则,读者顺带学会世界观;纯解说式揭示章是流失点。男频/设定重题材揭示密度整体更高,按题材校准。

二、伏笔兑现节奏

伏笔不是悬念的存款,读者需要阶段性的「利息」。

伏笔 vs 悬念——两个不同的工具:伏笔是隐线,读者当时可能不注意,事后恍然大悟,好伏笔在于深和隐;悬念是活扣,读者明确知道「有事悬着」。两者配合:伏笔提供深度感(「原来如此」),悬念提供紧迫感(「然后呢」)。

小结算机制——兑现不一定是大揭秘,有效的小结算包括:

  • 暗示被验证(「果然如此」的满足感)
  • 伏笔转化为具体代价(角色因此失去/得到了什么)
  • 谜题的局部解答(回答一个小问题,暴露一个更大的问题)
  • 纯「提及」不算兑现——伏笔被角色再次想起但没有产生新信息或新后果,不是结算

质量标准——好伏笔在于深度和隐秘性,不在于数量;歧义/双关技法:联系邻近上下文是表面含义,知道真相后才看出真正意图;伏笔必须与主线有联系,不能脱离大纲独立存在;只埋不兑现的区段越长,读者的耐心透支越重——每卷都要有揭示动作。

伏笔布距红线(治失序):按层级控制埋设到兑现的跨度——小伏笔在 arc 内快兑、中伏笔卷内兑现、只有贯穿全书的大伏笔才跨卷;任何伏笔(尤其小伏笔)跨度过长读者必忘=死伏笔;长线伏笔必须用中继 clue(阶段性小揭示/反复道具)续命,不能埋下后几百章无声。真人布距范例见 ${CLAUDE_PLUGIN_ROOT}/skills/novel-structure/references/packs/foreshadow-distance.md。

三、价值转换与事件架构

价值转换——章节的核心指标

每章必须有至少一个明确的价值转换——某个对角色有意义的价值从正面翻到负面,或反过来(「信任→怀疑」「安全→暴露」「希望→绝望」)。找不到价值转换的章节需要重新设计——它可能只是一段信息说明,不是叙事。更高层级(arc/卷/全书)的价值转换必须比章节级更剧烈、更不可逆。

事件定义

事件 = 有主体、有选择、有代价的叙述单元。

  • ✅ 事件:「张三发现食物被偷 → 追查发现是李四 → 对质后李四揭示原因(张三面临选择:揭发还是包庇)」
  • ❌ 非事件:「张三感到不安」「气氛变得紧张」「暗流涌动」

状态改变事件(满足其一即算):关系变化 / 目标变化 / 信息增量 / 位置变化(带来新约束或机会)/ 风险变化 / 资源变化。

硬后果
  • 硬后果事件:关系/资源/位置/风险中至少一项不可逆改变(失去盟友、暴露身份、错过唯一时间窗口)
  • 信息增量事件:读者或角色获得新信息,但处境未实质改变

每章至少一个硬后果事件;纯信息增量的章不该连续堆叠。

因果链与主角可靠性

事件不能孤立:A 事件的后果应触发 B 事件;删掉某事件后续不受影响 = 该事件无贡献,替换或赋予因果。

主角不应永远正确。误判、过度推断、遗漏关键线索是真实感和戏剧弹性的来源——误判必须有后续后果(信任损失、错过时机、被利用),不能无痛回收。

四、多线编织

  • 多线在一条共同主线贯穿下展开;每条支线承担明确功能:推动主线或塑造人物
  • 各线剧情分量对等,不要「主线精彩支线鸡肋」

三种编织模式:

  • 交替式:章/节间切换不同视角或地点。切换选情绪自然断裂点,不硬切;节奏可等长(A→B→A→B)或不等长(主次分明);偶尔在段落中段切换让读者意外
  • 汇聚式:多条线朝同一事件点收敛。前段各自独立,中间互相影响,终点交汇;收敛前让读者感到「有线正在接近」——A 线提到一个名字、B 线场景出现 A 待过的地点痕迹
  • 复调式:同一事件从不同角色视角反复呈现,每次揭示前一次遗漏的信息,读者逐渐拼出全貌。适用于重大冲突、谜案揭示、生死抉择

编织规则:

  • 用代表事件作节点(两线在场、一明一暗或暗线成果显现的时刻),在节点处整合或分裂故事线
  • 每条线有具体物理线索(人/物/地点),固定线索两端:出发点和目的地
  • 明线直接呈现,暗线间接呈现(结果暗示、他人口述、场景痕迹);暗线活跃时当前视角线不一定知道——读者比角色知道得多,这是戏剧张力
  • 线索分布有节奏:不过于集中(一章塞满所有线的进展)也不过于稀疏;一条线长期缺席读者会直接遗忘,用旁敲侧击、间接提及让读者感到「另一条线还在进行中」

多线入场/收线红线(治塌平):故事线不要全在第 1 章入场——主线开场立住,副线随剧情需要错峰进场(势力线在进入该势力时、感情线在对象登场时);也不要全堆到全书末尾收线——中段就该收掉一些线(一个宿敌了结、一个阶段目标达成)再开新线,维持「开线-收线」的编织呼吸。真人错峰范例见 ${CLAUDE_PLUGIN_ROOT}/skills/novel-structure/references/packs/storyline-weave.md。

五、戏剧规划

名场面

每卷规划两三个名场面——足以让读者对别人复述的场景。

名场面 = 长期铺垫 + 情境压力 + 角色决断 + 不可逆后果

  • 铺垫:通过伏笔、角色发展、关系建立,让读者对这一刻有情感投入——名场面的力量主要来自铺垫,而非场面本身,铺垫章要当一等公民规划
  • 压力:角色被推入必须行动的极端环境,没有退路
  • 决断:角色做出体现其本质的选择——意外但合乎角色逻辑
  • 后果:不可撤回,世界因此改变

六种原型:燃(绝境逆转)、泪(牺牲不可挽回)、爽(长期蓄压释放)、智斗(计中计+信息差)、抉择(不可能三角+代价)、顿悟(真相揭示+世界观重构)。一卷的名场面不应全同原型。

中点设计

每卷约 50% 位置设中点——把卷劈成方向不同的上下两半:

  • 虚假胜利:上半段问题看似解决 → 下半段走向更大失败,再逆转
  • 虚假失败:上半段希望破灭 → 下半段触底反弹,走向真正胜利

翻转必须写成可指认的情节动作(证人翻供、盟友亮明真实身份、主角发现一直误解了目标),不是抽象的「气氛变了」。检验:上半段事件链整体指向方向 X,下半段整体指向相反方向;若只是同一方向强度递增,中点退化为普通高潮。

转折类型多样化

一卷内的转折不应全是同一类型。参考类型:信息揭示(高频)、身份揭示(中频)、背叛(低频,用多贬值)、局势逆转(中高频)、代价型(中频)、误判型(中频)、故事线汇合(低频,需精密设计)。

六、arc 设计

章节不是孤立单位。一个 arc 是网文副本粒度的完整故事弧线:

触发 → 蓄压 → 对抗升级 → 高潮释放 → 收尾过渡 → 下一 arc 触发

  • arc 核心问题在 arc 内结算:末章给出明确的 yes/no 答案
  • arc 结束时世界有不可逆改变——这是 arc 的「结账」,没有结账的 arc 读完像没读
  • arc 之间递推:「解决了问题 A,但引发了更大的问题 B」——种子在本 arc 内已可见,不是凭空冒出
  • 卷先以 arc 为粒度规划,再拆章

冲突五阶段——每条重要冲突线标注当前位置:对比(差异已建立未碰撞)→ 反差(开始摩擦)→ 冲突(不可调和的对抗)→ 转折(力量对比改变)→ 和解(新平衡)。一卷结束所有冲突仍停在「对比」= 展开太慢。

困境阶梯——主角困境随全书推进升级:

阶困境核心问题
能力打不过 / 做不到「我做不到」
选择两个都想要只能选一「选哪个」
价值做正确的事代价巨大「值得吗」
身份我以为我是谁 vs 我真正是谁「我是谁」
存在意义 / 牺牲 / 终极代价「即使赢了,意义在哪里」

全程只有能力困境 = 角色深度不够。全书约一半进度应触及价值困境,末段应走到身份或存在困境。

arc 长度红线(治匀速):副本长短必须随张力变化、不要全卷匀速等长——紧凑开局/转折副本压短,蓄势/高潮副本拉长;副本内部每 2-6 章要有一次钩子/反转/困境的脉动(实测背书见 arc-rhythm 包),不把张力摊平成一个大块。具体真人节奏见 ${CLAUDE_PLUGIN_ROOT}/skills/novel-structure/references/packs/arc-rhythm.md。

七、场景与章末

场景转换
  • 情绪衔接(前场景情绪自然过渡)、同一画面衔接(相同视觉元素连接时空跳跃)、同一主体衔接(跟随角色/物品进入新场景)
  • 现代读者习惯蒙太奇跳跃:另起一行直接写新地点/新人物即可,需要时一句时间/地点提示
章末收束

章末钩类型学以章纲 end_hook 四值枚举为单一口径:suspense(悬念)/ danger(危机)/ emotional(情绪)/ none(显式无钩)。具体收束手法(事件悬念、对话戛然、日常裂缝、情绪留白、行为回声、视角切换)各归哪个枚举、怎么轮换,见 hook-cadence 包——规划章级细纲时先读它。

  • 强弱搭配看卷的位置:arc 末章、卷末章倾向 danger / suspense 强钩;余波章可用 emotional 或显式 none 缓冲
  • 相邻几章换着收,读者对固定收束节奏会疲劳;连续无钩是追读死区(提交门会告警)
  • 卷末章用强钩承接「不可逆改变 + 下卷钩子」的结构功能
结构多样性

连续几章的开篇或结尾手法不应让读者感觉单调——这是读者体验判断,不是字段匹配。章节的场景组合不得与前几章高度相似(「日常→赶往地点→固定互动→训练/闲谈→伏笔暗示」连续复制即模板化);同一道具或场景反复出现且功能不变时,引入新元素或赋予旧物新功能。

© yannikzz, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 11 other files (references) in agent-core/narracat/skills/novel-structure of yannikzz/narracat-novel-agent.

  • SKILL.md
  • references/packs/arc-rhythm.md
  • references/packs/foreshadow-distance.md
  • references/packs/hook-cadence.md
  • references/packs/opening-hook.md
  • references/packs/pack-index.json
  • references/packs/payoff-cadence.md
  • references/packs/pressure-release.md
  • references/packs/selling-point-front.md
  • references/packs/stakes-ladder.md
  • references/packs/storyline-weave.md
  • references/packs/twist-mechanics.md

Open the folder on GitHubat commit 2c49f9f

Compare with similar skills

Novel Structure next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Novel Structure compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Novel Structure this skillyannikzz/narracat-novel-agent105—~1.7kAutomated safety check: PassAGPL-3.0
Story Multi-Perspective Reviewzenstory-ai/oh-story-claudecode7.4k3 repos~3kAutomated safety check: PassMIT
Short Web Fiction Trend Scanzenstory-ai/oh-story-claudecode7.4k2 repos~1.2kAutomated safety check: PassMIT
InkOS Creative HarnessNarcooo/inkos10k1 repos~1.1kAutomated safety check: PassAGPL-3.0
Novel Arteternityspring/shuohao-skills4.3k—~1.1kAutomated safety check: NotesApache-2.0
SepiaNanako0129/sepia3.1k—~3.6kAutomated safety check: PassMIT

Similar skills

  • Story Multi-Perspective Review

    zenstory-ai/oh-story-claudecode

    Reviews Chinese web-novel text with several reviewer agents in parallel, falling back to a single-agent pass, and reports structure, character, prose and setting problems with fixes.

    7.4k GitHub starsUsed in 3 repos~3k tokens
    Writing & ContentAuto-check passed
  • Short Web Fiction Trend Scan

    zenstory-ai/oh-story-claudecode

    Scans popular short web-fiction rankings on Chinese platforms such as Dianzhong and Heiyan to surface trending emotional hooks, themes and topic candidates with an expiry warning.

    7.4k GitHub starsUsed in 2 repos~1.2k tokens
    Writing & ContentAuto-check passed
  • Drives long-form fiction, scripts, storyboards, interactive films and long-document translation through InkOS, with every change made by a typed action.

    10k GitHub starsUsed in 1 repo~1.1k tokens
    Writing & ContentAuto-check passed
  • Novel Art

    eternityspring/shuohao-skills

    给 AI 短剧出美术设定集(场景 + 叙事道具):场景的设计意图、一致性锚点、光照时段变体、 空景提示词;道具的戏剧功能、状态变体、尺度参照、白底无手提示词。

    4.3k GitHub stars~1.1k tokensUpdated 2 days ago
    Writing & ContentAuto-check: notes
  • Sepia

    Nanako0129/sepia

    Make AI-generated writing read as human-written, in fiction and in professional prose.

    3.1k GitHub stars~3.6k tokensUpdated yesterday
    Writing & ContentAuto-check passed
  • Story Toolbox Router

    zenstory-ai/oh-story-claudecode

    Routes a Chinese web-novel writing request to the matching tool in a 13-skill toolbox, covers author habit memory, and can launch a local dashboard for browsing a project.

    7.4k GitHub stars~1.7k tokensUpdated today
    Writing & ContentAuto-check passed

More from yannikzz/narracat-novel-agent

  • Release App

    yannikzz/narracat-novel-agent

    Cut and publish a new NarraCat-app version — bump the version number, build the Windows x64 package in CI, package + sign + notarize the macOS build locally, and publish both platforms into one…

    105 GitHub stars~1.6k tokensUpdated 3 days ago
    Auto-check: notes
  • Release Guard

    yannikzz/narracat-novel-agent

    View or change NarraCat-app's internal-test release gate / remote kill switch (the release-guard Cloudflare Worker in workers/release-guard).

    105 GitHub stars~495 tokensUpdated 3 days ago
    Auto-check passed
  • Novel Reference Analysis Method

    yannikzz/narracat-novel-agent

    A reference work analysis method providing text decomposition and five-dimension extraction framework (premise / world / characters / structure / style, with narrator voice sub-framework under…

    105 GitHub stars~1.1k tokensUpdated 3 days ago
    Auto-check passed
  • Novel Web Craft

    yannikzz/narracat-novel-agent

    Web-fiction craft material library consumed by the /write brief compressor — retention mechanics (hooks, pacing, conflict clarity, dialogue load, payoff delivery, chapter-end pull) kept as…

    105 GitHub stars~695 tokensUpdated 3 days ago
    Auto-check passed
  • Novel Memory Integration

    yannikzz/narracat-novel-agent

    Guide for answering natural language questions about novel content by querying NovelMemory MCP read tools from the main conversation.

    105 GitHub stars~392 tokensUpdated 3 days ago
    Auto-check passed
  • Novel Style Reference

    yannikzz/narracat-novel-agent

    A real-novel writing style reference library backed by the novelquerystylereference MCP tool.

    105 GitHub stars~391 tokensUpdated 3 days ago
    Auto-check passed

Questions about Novel Structure

What does Novel Structure do?

Narrative structure knowledge for long-form web fiction, covering emotional stakes, tension rhythm, climax layering, foreshadowing payoff pacing, value shifts and event architecture, multi-thread…. Novel Structure is an agent skill from yannikzz/narracat-novel-agent. Narrative structure knowledge for long-form web fiction, covering emotional stakes, tension rhythm, climax layering, foreshadowing payoff pacing, value shifts and event architecture, multi-thread weaving, arc design, and chapter ending hooks.

When should I use Novel Structure?

Novel Structure fits situations like: planning outlines; tasks that involve Creative writing and fiction.

How do I install Novel Structure in Claude Code?

Run `npx skills add yannikzz/narracat-novel-agent --skill novel-structure -a claude-code`. Or copy the skill folder (agent-core/narracat/skills/novel-structure in yannikzz/narracat-novel-agent) into .claude/skills/novel-structure in your project. Claude Code loads it when a task matches its description.

How do I install Novel Structure in Codex?

Run `npx skills add yannikzz/narracat-novel-agent --skill novel-structure -a codex`. Or copy the skill folder (agent-core/narracat/skills/novel-structure in yannikzz/narracat-novel-agent) into .agents/skills/novel-structure in your project. Codex loads it when a task matches its description.

Can I use Novel Structure in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add yannikzz/narracat-novel-agent --skill novel-structure -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/novel-structure, .gemini/skills/novel-structure, .github/skills/novel-structure and .opencode/skills/novel-structure in your project.

What does Novel Structure need to run?

SKILL.md names no scripts, command-line tools or credentials: Novel Structure is instructions for the agent only.

Does Novel Structure access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Novel Structure safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Novel Structure use?

Novel Structure is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Novel Structure use?

About 1.7k tokens (SKILL.md is roughly 6.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 16k tokens, read only when the agent opens those files.

What are the alternatives to Novel Structure?

Skills that share tags, products or a category with Novel Structure: Story Multi-Perspective Review (zenstory-ai/oh-story-claudecode, 7.4k stars), Short Web Fiction Trend Scan (zenstory-ai/oh-story-claudecode, 7.4k stars), InkOS Creative Harness (Narcooo/inkos, 10k stars) and Novel Art (eternityspring/shuohao-skills, 4.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Novel Structure?

yannikzz (a GitHub user) maintains it in yannikzz/narracat-novel-agent, which has 105 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 7, 2026.

Source: yannikzz/narracat-novel-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.