Storybook Generator logo

Storybook Generator

Community
weaiw
storybook-generator

生成儿童绘本、图画书、连续故事插画和绘本项目包。Use when the user asks to create a children's picture book, storybook MVP, page-by-page illustration prompts, consistent characters across pages, bilingual/trilingual layouts, KDP-ready publishing notes, or a complete story-to-images workflow. 默认先建立故事节奏、角色圣经、视觉风格和逐页提示词,再用 image_gen 逐页生成并做一致性 QA。

Overview

Publisherweaiw
Repositorystorybook-generator-skill
Skill namestorybook-generator
Stars
51
Forks
15
Bundled files
10
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.

  • 10 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by weaiw on GitHub. Read the source before you install it.

Installation

Install the Storybook Generator 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/weaiw/storybook-generator-skill/tree/main
  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.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/weaiw/storybook-generator-skill.git \
  .claude/skills/storybook-generator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Storybook Generator 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 Storybook Generator 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 Storybook Generator 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.

绘本生成器

把一个故事想法、短文、教育主题或角色设定,先做成低成本绘本 MVP,再进入连续出图:选题场景、故事骨架、页码节奏、角色/场景/风格圣经、逐页 imagegen 提示词、封面方案、样书排版检查和保存规则。

先读这些参考

按任务需要读取,不要一次塞满上下文:

  • references/story-structure.md:绘本故事结构、页数节奏、文字密度和适龄改写。做故事拆页前读取。
  • references/character-continuity.md:角色一致性、场景一致性、跨页视觉锚点。生成多页前读取。
  • references/visual-styles.md:可选绘本画风、手绘风/小黑风迁移原则、禁止项。选风格或写提示词前读取。
  • references/prompt-workflow.md:逐页提示词模板、批量出图流程、保存命名规则。用户要生成图片时读取。
  • references/layout-and-pinyin.md:后期排版、封面标题、徽章、拼音-中文-英文三语正文、文字防重叠规则。用户要求成品页、封面优化、文字上图、加拼音或加英文时读取。
  • references/reference-corpus-lessons.md:从绘本参考语料提炼出的故事节奏、构图、文字区和页面类型经验。用户要求参考绘本、提升绘本质量或优化 skill 时读取。
  • references/story-text-structure-lessons.md:绘本参考语料的逐页文案结构、句式功能、翻页钩子和重复升级模式。用户要求逐页文案结构学习、文案改写或结构拆页时读取。
  • references/commercial-publishing-workflow.md:选题验证、KDP 书稿链路、封面/描述/系列扩展、低成本 MVP 上架思路。用户要求把绘本做成可上架商品、Amazon KDP、书籍商业化或先测概念时读取。
  • references/qa-checklist.md:成书检查、儿童内容安全、文字和一致性返工规则。交付前读取。

工作流

1. 判断交付模式

  • 用户要“生成 / 出图 / 做成绘本 / 直接做”:默认产出项目规划并逐页调用 image_gen。
  • 用户只要“方案 / 分镜 / prompt / 不出图”:只输出对应文档或提示词,不调用图片生成。
  • 用户指出已生成绘本的问题,例如“文字和画面对不上 / 多手 / 故事不连贯 / 第 N 页有问题”:进入修复模式,先按问题类型定位到页计划、提示词、图片或排版层,再局部改文案、改 prompt、重出图或重排版。
  • 用户给了年龄、主题、页数、比例、风格时直接使用;没给时采用默认值:3-8 岁、12 页内页 + 封面、方形或横版绘本、温暖手绘风。

修复模式不要默认整本推倒。先输出:

  • 问题页码和问题类型。
  • 根因属于故事结构、图文契约、角色肢体、画面文字还是后期排版。
  • 最小修复动作:改文字、改 prompt 重出 -v2、修页计划、或重新导出带字页面。
  • 哪些旧图保留,哪些新图替换。

2. 先做绘本项目骨架

读取 references/story-structure.md,把输入整理为:

  • 目标读者年龄和阅读场景
  • 具体选题场景、家长购买理由、潜在教育意义
  • 一句话主题和情绪关键词
  • 主角、愿望、阻碍、转折、结尾
  • 页数与每页承担的叙事功能
  • 每页正文草稿,单页不堆长句;如做双语/三语版,同时给出拼音、中文、英文三行文本
  • 页间因果链:上一页状态 -> 本页触发 -> 本页动作/发现 -> 下一页钩子
  • 图文契约:页面文字里每一个可见名词/动作,画面提示词里都必须有对应视觉证据

如果用户给的是成人主题或知识点,先儿童化:用具体动作、可见物件和小冲突表达,不把抽象概念硬塞进画面。

不要一上来让 AI “写一本儿童书”。先做 MVP:选题 -> 三段大纲 -> 逐页文案 -> 角色档案 -> 分镜提示 -> 封面方案 -> 排版样书 -> 上架前自检。 如果用户明确要做成商品或上架内容,再把链路扩展为:概念验证 -> 故事结构 -> 角色/风格圣经 -> 逐页插图 -> 封面 -> KDP/平台描述 -> 系列扩展 -> 版式导出。

3. 建立一致性圣经

读取 references/character-continuity.md,先写:

  • 主角固定外观:年龄感、体型、发型/毛色、衣服、配饰、表情基调
  • 配角固定外观和关系
  • 场景世界观:地点、季节、时间、道具、色彩锚点
  • 每页必须延续的视觉锚点

多页出图时,每一页提示词都要重复角色圣经的关键外观,不要只写“同一个角色”。

对有人物的页面,提示词必须写清楚可见手臂/手的数量和用途,例如“只露出两只手:右手托小兔灯,左手抱小熊;不要第三只手、不要多余手指、不要融合手臂”。如果角色被道具遮挡,也要说明哪些手不可见。

4. 选择视觉路线

读取 references/visual-styles.md,选 1 条主风格。默认优先:

  • 温暖手绘绘本:纸张质感、柔和水彩/彩铅、干净构图
  • 纸纹童趣手绘:借鉴手绘 PPT skill 的浅纸纹、低饱和淡彩、手写感,但降低信息图属性
  • 小黑绘本:借鉴小黑 skill 的极简怪诞主体,但做成儿童友好的连续故事,不复刻既有小黑正文配图构图

不要混用太多风格。一本书保持线条、质感、色彩、角色比例和镜头距离稳定。

5. 逐页生成

读取 references/prompt-workflow.md。每页只讲一个动作或情绪变化,提示词包含:

  • 绘本页类型和比例
  • 固定角色外观
  • 当前页动作、场景、情绪和镜头
  • 主风格的材质、线条、色彩和留白
  • 负面约束:不要照片、3D、商业海报、复杂文字、错字、水印、版权角色
  • 图文契约:页面文字提到的关键物必须出现在画面中;画面没有把握生成的物,不要写进正文

默认一页一图生成。封面、内页、封底分开生成,不把多页拼成一张。

5.1 文字上图策略

内页正文默认采用“小黑 skill 同类原理”:先生成无文字插画,再用确定性的 HTML/PPT/canvas 排版把中文正文压到图上或导出样书页。这样可以稳定控制字体、字号、位置和错字。

封面可以优先让 image_gen 直接生成完整标题与副标题,因为封面需要整体构图、字体质感、光影和插画融在一起。仅限短标题和短副标题,生成后必须逐字检查;如果出现错字、漏字、乱码或字形过怪,先重出封面,必要时再退回后期排版。

除封面外,只有在这两种场景才让 image_gen 直接生成画面内文字:

  • 门牌、标签等 2-6 个字的短文字。
  • 用户明确要求文字作为画面元素的一部分。

普通正文不要交给 image_gen 写在画里;必须在 sample-book.html、PPT、PDF 或后期排版层添加。若要交付“带字图片”,导出排版后的整页 PNG,而不是让模型把正文画进插画。

如果用户要求封面优化、内页像参考图、加拼音、加英文、文字压图或成品页排版,先读取 references/layout-and-pinyin.md。封面默认采用少元素方案:圆润中文标题字体、根据插画取色的轻渐变、约 50% 透明深色描边和柔和阴影,避免堆贴纸/标注线;优先在封面生图阶段一次生成标题和副标题。内页默认优先用整幅插画 + 底部半透明三语正文条:拼音在上、中文居中、英文在下;只有在出图阶段已明确预留大面积文字区时,才使用左文右图/大留白版式。

6. QA 与返工

交付前读取 references/qa-checklist.md,检查:

  • 故事是否有起承转合,不只是插画合集
  • 角色是否跨页一致
  • 每页动作是否清楚,能否不用大段文字也看懂
  • 页面文字和画面是否逐项对上:文字说“墙上有小手”,画面里就必须有清楚的小手形黑影;否则改文字或重出图
  • 是否适龄、安全、没有吓人或成人化表达
  • 图中文字是否少、准、可读;封面标题和副标题必须逐字正确,内页正文错字严重时删除图中文字,后期排版另加
  • 人物是否只有合理数量的手、脚、手指;儿童绘本里异常肢体必须重出
  • 家长能否一眼知道这本书解决什么具体问题
  • 样书是否统一页面尺寸、字体、安全边距和文字压图规则;三语版是否保持拼音、中文、英文层级清楚

不合格时先判断问题类型:

  • 故事断裂:先修 02-page-plan.md 的因果链,再重写相关页提示词。
  • 图文不一致:优先改正文或改当前页提示词;不要让文字解释画面不存在的东西。
  • 肢体错误:直接重出该页,提示词里明确可见肢体数量和遮挡关系。
  • 文字错乱:改为后期排版文字,重新生成无文字插画。

保存与交付

在 workspace 内工作时,把产物保存到:

text
storybook/<book-slug>/

推荐结构:

text
storybook/<book-slug>/
  00-storybook-brief.md
  01-character-style-bible.md
  02-page-plan.md
  03-cover-plan.md
  04-sample-book-notes.md
  prompts/
    page-00-cover.md
    page-01.md
  images/
    00-cover.png
    01.png

不要覆盖已有成图;需要替换时保存为 01-v2.png 或先向用户确认。

输出口径

规划阶段简短但完整:页数、角色、风格、每页一句。生成阶段报告生成了哪些页、保存路径、哪些页需要二次修。不要长篇解释风格理论。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Storybook Generator AI skill do?

生成儿童绘本、图画书、连续故事插画和绘本项目包。Use when the user asks to create a children's picture book, storybook MVP, page-by-page illustration prompts, consistent characters across pages, bilingual/trilingual layouts, KDP-ready publishing notes, or a complete story-to-images workflow. 默认先建立故事节奏、角色圣经、视觉风格和逐页提示词,再用 image_gen 逐页生成并做一致性 QA。

Why use Storybook Generator on TypingMind?

Because you install it once and use it with any model. Storybook Generator 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 Storybook Generator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/weaiw/storybook-generator-skill/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Storybook Generator?

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 Storybook Generator?

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

Is the Storybook Generator AI skill free?

Yes. It is published on GitHub by weaiw 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 👇