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.
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…
$ npx skills add yannikzz/narracat-novel-agent --skill novel-structure -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install yannikzz/narracat-novel-agent novel-structure --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ 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-srcUse ~/.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/
Install the "novel-structure" agent skill from https://github.com/yannikzz/narracat-novel-agent/tree/main/agent-core/narracat/skills/novel-structure into .claude/skills/novel-structure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "novel-structure", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/yannikzz/narracat-novel-agent/tree/main/agent-core/narracat/skills/novel-structureType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add yannikzz/narracat-novel-agent --skill novel-structure -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install yannikzz/narracat-novel-agent novel-structure --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/yannikzz/narracat-novel-agent.git skills-src && mkdir -p .agents/skills && cp -r skills-src/agent-core/narracat/skills/novel-structure .agents/skills/novel-structure && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "novel-structure" agent skill from https://github.com/yannikzz/narracat-novel-agent/tree/main/agent-core/narracat/skills/novel-structure into .agents/skills/novel-structure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "novel-structure", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add yannikzz/narracat-novel-agent --skill novel-structure -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install yannikzz/narracat-novel-agent novel-structure --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/yannikzz/narracat-novel-agent.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/agent-core/narracat/skills/novel-structure .cursor/skills/novel-structure && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "novel-structure" agent skill from https://github.com/yannikzz/narracat-novel-agent/tree/main/agent-core/narracat/skills/novel-structure into .cursor/skills/novel-structure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "novel-structure", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/yannikzz/narracat-novel-agent.git --path agent-core/narracat/skills/novel-structure--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add yannikzz/narracat-novel-agent --skill novel-structure -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install yannikzz/narracat-novel-agent novel-structure --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/yannikzz/narracat-novel-agent.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/agent-core/narracat/skills/novel-structure .gemini/skills/novel-structure && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "novel-structure" agent skill from https://github.com/yannikzz/narracat-novel-agent/tree/main/agent-core/narracat/skills/novel-structure into .gemini/skills/novel-structure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "novel-structure", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install yannikzz/narracat-novel-agent novel-structureInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add yannikzz/narracat-novel-agent --skill novel-structure -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/yannikzz/narracat-novel-agent.git skills-src && mkdir -p .github/skills && cp -r skills-src/agent-core/narracat/skills/novel-structure .github/skills/novel-structure && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "novel-structure" agent skill from https://github.com/yannikzz/narracat-novel-agent/tree/main/agent-core/narracat/skills/novel-structure into .github/skills/novel-structure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "novel-structure", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add yannikzz/narracat-novel-agent --skill novel-structure -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install yannikzz/narracat-novel-agent novel-structure --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/yannikzz/narracat-novel-agent.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/agent-core/narracat/skills/novel-structure .opencode/skills/novel-structure && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "novel-structure" agent skill from https://github.com/yannikzz/narracat-novel-agent/tree/main/agent-core/narracat/skills/novel-structure into .opencode/skills/novel-structure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "novel-structure", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
novel-structureNarrative 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. 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.
Read from SKILL.md and the folder at commit 2c49f9f. It shows what the files ask for, not the result of running them.
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.
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.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
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.
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.
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.
The full file from yannikzz/narracat-novel-agent at commit 2c49f9f, republished under its AGPL-3.0 licence (© yannikzz). 307 words, ~1,724 tokens.
.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.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?
novel_list_structure_cards(stage="stage-1"),把返回的每张卡用 Read 读完再动手。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)。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)。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」**。
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。
| 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。
| 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:
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):
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。
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:
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。
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 = 有主体、有选择、有代价的叙述单元。
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。
每章至少一个硬后果事件;纯信息增量的章不该连续堆叠。
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。
三种编织模式:
编织规则:
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。
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
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。
每卷约 50% 位置设中点——把卷劈成方向不同的上下两半:
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。
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)。
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
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。
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。
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
SKILL.md and 11 other files (references) in agent-core/narracat/skills/novel-structure of yannikzz/narracat-novel-agent.
Open the folder on GitHubat commit 2c49f9f
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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Novel Structure this skillyannikzz/narracat-novel-agent | 105 | — | ~1.7k | Automated safety check: Pass | AGPL-3.0 | |
| Story Multi-Perspective Reviewzenstory-ai/oh-story-claudecode | 7.4k | 3 repos | ~3k | Automated safety check: Pass | MIT | |
| Short Web Fiction Trend Scanzenstory-ai/oh-story-claudecode | 7.4k | 2 repos | ~1.2k | Automated safety check: Pass | MIT | |
| InkOS Creative HarnessNarcooo/inkos | 10k | 1 repos | ~1.1k | Automated safety check: Pass | AGPL-3.0 | |
| Novel Arteternityspring/shuohao-skills | 4.3k | — | ~1.1k | Automated safety check: Notes | Apache-2.0 | |
| SepiaNanako0129/sepia | 3.1k | — | ~3.6k | Automated safety check: Pass | MIT |
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.
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.
Narcooo/inkos
Drives long-form fiction, scripts, storyboards, interactive films and long-document translation through InkOS, with every change made by a typed action.
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。
Nanako0129/sepia
Make AI-generated writing read as human-written, in fiction and in professional prose.
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.
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…
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).
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…
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…
yannikzz/narracat-novel-agent
Guide for answering natural language questions about novel content by querying NovelMemory MCP read tools from the main conversation.
yannikzz/narracat-novel-agent
A real-novel writing style reference library backed by the novelquerystylereference MCP tool.
Categories
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.
Novel Structure fits situations like: planning outlines; tasks that involve Creative writing and fiction.
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.
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.
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.
SKILL.md names no scripts, command-line tools or credentials: Novel Structure is instructions for the agent only.
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.
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.
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.
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.
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.
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.