TypingMindTypingMindThe best frontend for AI
Manga Full Stack logo

Manga Full Stack

Community
SwotAtmk
manga-full-stack

AI漫剧全栈技能包：基于19份专业资料整合的AI漫剧全流程制作技能，覆盖分镜提示词（14要素公式）、角色一致性控制（五维框架+参考图锁定+参数固化）、剧本结构设计（三段式+万能故事公式）、多风格体系（3D动漫/古风玄幻/赛博朋克/暗黑悬疑）与50+运镜提示词模板。

Overview

PublisherSwotAtmk
Repositoryinfinite-creation
Skill namemanga-full-stack
Stars
112
Forks
30
Bundled files
1
LicenseMIT
Links
Skill sourceRepositoryHomepage
  • 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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the Manga Full Stack 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/SwotAtmk/infinite-creation/tree/main/skills/manga-full-stack
  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/SwotAtmk/infinite-creation.git /tmp/infinite-creation
mkdir -p .claude/skills
cp -r /tmp/infinite-creation/skills/manga-full-stack .claude/skills/manga-full-stack
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Manga Full Stack 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 Manga Full Stack 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 Manga Full Stack 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.

AI漫剧全栈技能包

基于19份专业资料整合的AI漫剧全流程制作技能，覆盖分镜提示词、角色一致性、剧本结构、风格体系、运镜模板、工具选型等核心能力。

技能概述

本技能将AI漫剧制作的全链路知识系统化，提供：

  • 分镜提示词生成：基于14要素公式，自动生成高质量分镜提示词
  • 角色一致性控制：五维框架+参考图锁定+参数固化
  • 剧本结构设计：三段式结构+万能故事公式+节奏控制
  • 风格体系应用：3D动漫/古风玄幻/赛博朋克/暗黑悬疑等多风格支持
  • 运镜模板库：50+运镜提示词模板，覆盖基础/进阶/视角/转场
  • 工具选型指导：一站式工具/生图工具/配音工具对比推荐

适用场景

  • 创作AI漫剧（静态分镜或动态视频）
  • 设计分镜脚本和提示词
  • 解决角色一致性问题
  • 选择合适的AI制作工具
  • 优化剧本结构和节奏

执行方式

1. 分镜提示词生成

输入：剧本/故事描述/场景需求 输出：符合14要素标准的分镜提示词

执行步骤：

  1. 解析输入内容，提取核心主体、动作、场景
  2. 确定风格定义（3D动漫/古风/赛博等）
  3. 选择镜头语言（景别+运镜+视角）
  4. 配置光影效果和画质参数
  5. 添加负面提示词
  6. 输出完整提示词

提示词公式：

[核心主体(权重1.5-1.7)] + [细节特征] + [动作/状态] + [场景环境] + [风格定义] + [镜头语言] + [光影效果] + [画质要求] | 负面提示词

2. 角色一致性控制

输入：角色设定描述 输出：角色DNA档案+一致性控制方案

执行步骤：

  1. 建立角色DNA档案（外貌/服饰/神态/体型）
  2. 生成角色参考图提示词（正面/侧面/45度/背面）
  3. 提供工具锁定方案（Midjourney --cref/--cw/--seed 或 SD LoRA）
  4. 输出跨镜头一致性检查清单

五维一致性框架：

  • 外貌一致性：360度视图参考库
  • 服饰一致性：服饰拆解图
  • 动作一致性：常用动作库
  • 情绪一致性：标准表情模板
  • 镜头语言一致性：固定景别呈现方式

3. 剧本结构设计

输入：故事核心/题材类型 输出：结构化剧本大纲+分镜脚本

执行步骤：

  1. 确定故事核心：【人物】+【困境】+【转折】+【视觉钩子】
  2. 搭建三段式框架：开端(0-1min)-冲突(1-6min)-解决(6-8min)
  3. 设计分镜脚本：10大核心模块（镜号/景别/运镜/画面/台词/时长/风格/转场/备注/参考）
  4. 节奏控制：每30秒1个小钩子，每4-5镜头1个小高潮

4. 风格体系应用

支持风格：

  • 3D动漫风格（国漫质感、电影级渲染）
  • 古风玄幻国漫（东方美学、飘逸流畅）
  • 暗黑系悬疑漫（冷色调、阴森诡谲）
  • 赛博朋克/科幻（霓虹灯光、高对比度）
  • 治愈系少女漫（马卡龙色、柔和细腻）
  • 日系热血少年漫（线条硬朗、动态感十足）

执行步骤：

  1. 根据题材确定主风格
  2. 提取风格核心关键词
  3. 配置色调/线条/光影参数
  4. 输出风格化提示词

5. 运镜模板调用

运镜类型库：

  • 基础运镜：推/拉/摇/移/定（5大类）
  • 进阶运镜：跟镜/升降/旋转/俯冲/甩镜
  • 视角切换：POV/俯视/仰视/微距/上帝视角
  • 转场衔接：叠化/闪切/划镜/淡入淡出/匹配转场

执行步骤：

  1. 根据场景需求选择运镜类型
  2. 调用对应模板
  3. 配置速度/焦距/焦点参数
  4. 输出运镜提示词

6. 工具选型推荐

工具分类：

  • 一站式制作工具：即梦AI/星月梦AI/巨日禄AI/Sora2
  • 生图工具：Midjourney/Stable Diffusion/DALL·E 3/即梦AI
  • 配音工具：剪映AI配音/魔音工坊/冬瓜配音

推荐逻辑：

  • 新手快速出片 → 即梦AI
  • 批量生产小说推文 → Runway/巨日禄
  • 二次元风格定制 → Niji Journey + 剪映
  • 长番剧/微型番剧 → 萌动AI
  • 专业团队/IP项目 → ELSER.AI

核心知识库

完整知识库文档位置：

  • knowledge/AI漫剧制作系统知识库.md

包含：

  • 分镜提示词核心公式
  • 分镜脚本10大核心模块
  • 景别体系详解
  • 运镜提示词体系（50+模板）
  • 角色一致性控制体系
  • 风格提示词体系
  • 背景场景提示词模板
  • 人物提示词通用公式
  • 50种人物面部表情提示词
  • 剧本结构模板
  • 多格分镜模板
  • 动态分镜模板
  • 系列漫剧连贯模板
  • 工具选型指南
  • 变现路径
  • 行业趋势

最佳实践

分镜提示词最佳实践

  1. 核心主体权重1.5-1.7：确保AI聚焦主角
  2. 细节描述具体化：用"少女齐肩短发"而非"少女短发"
  3. 必加负面提示词：畸形肢体、多手指、模糊边缘、错位眼睛、杂乱背景
  4. 固定Seed值：保证跨镜头一致性

角色一致性最佳实践

  1. 建立角色DNA档案：详细记录外貌/服饰/神态/体型
  2. 生成多角度参考图：正面/侧面/45度/背面
  3. 使用工具锁定功能：Midjourney --cref/--cw/--seed
  4. 参数固化三原则：固定模型版本、锁定核心参数、统一提示词结构

剧本结构最佳实践

  1. 前3秒强钩子：开篇即冲突
  2. 每30秒1个小钩子：保持观众注意力
  3. 三段式结构：开端-冲突-解决
  4. 结尾留悬念：引导下一集

工具选型最佳实践

  1. 新手优先即梦AI：零门槛、角色一致性强
  2. 商业项目用巨日禄：工业化生产、资产复用
  3. 二次元用Niji Journey：画面质感顶尖
  4. 配音用剪映/魔音工坊：与剪辑流程无缝衔接

输出示例

分镜提示词示例

masterpiece, high quality, 沈惊鸿:1.6(17岁少年，黑发黑眸，面容清秀，灰色宗门服破损) 
盘坐运功，周身紊乱灵气光点，宗门禁地洞府，深夜，
镜头缓缓推近，冷色调侧逆光，浅景深，
3D国漫风格，电影级渲染，8K超清画质 | 
畸形肢体、多手指、模糊边缘、错位眼睛、杂乱背景

角色DNA档案示例

角色名：沈惊鸿
核心特征：17岁少年，鹅蛋脸，剑眉星目，左眼下方有一颗泪痣，黑色碎发
发型发色：黑色碎发，略显凌乱
服饰细节：灰色粗布宗门服（破损），腰间挂着断刀（锈迹斑斑）
神态气质：眼神坚定带倔强，嘴角习惯性紧抿
身高体型：175cm，偏瘦但结实

剧本结构示例

【人物】沈惊鸿，17岁宗门废柴弟子
【困境】被师门驱逐，断刀反噬
【转折】悬崖之下觉醒断刀诀
【视觉钩子】断刀发出金光，穿透云层

三段式结构：
- 开端（0-1min）：师门驱逐，断刀反噬
- 冲突（1-6min）：悬崖坠落，生死一线
- 解决（6-8min）：觉醒断刀诀，断刀发出金光

注意事项

  1. 角色一致性优先：先建立角色DNA档案，再生成分镜
  2. 风格统一：全剧使用同一风格定义，避免视觉割裂
  3. 参数固化：确定Seed值后全程复用
  4. 节奏控制：每30秒1个小钩子，每4-5镜头1个小高潮
  5. 工具选型：根据项目规模和风格需求选择合适工具

相关资源

  • 知识库：knowledge/AI漫剧制作系统知识库.md
  • 断刀杀神项目：F:\断刀杀神-第一季-v2\
  • 视频提示词生成技能：skills/video-prompt-generator/SKILL.md
  • Seedance 2.0视频生成技能：skills/seedance2.0-video-gen/SKILL.md

技能创建时间：2026-07-15 资料来源：19份AI漫剧专业资料（13 docx + 6 xlsx）

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 Manga Full Stack AI skill do?

AI漫剧全栈技能包：基于19份专业资料整合的AI漫剧全流程制作技能，覆盖分镜提示词（14要素公式）、角色一致性控制（五维框架+参考图锁定+参数固化）、剧本结构设计（三段式+万能故事公式）、多风格体系（3D动漫/古风玄幻/赛博朋克/暗黑悬疑）与50+运镜提示词模板。

Why use Manga Full Stack on TypingMind?

Because you install it once and use it with any model. Manga Full Stack 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 Manga Full Stack in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/SwotAtmk/infinite-creation/tree/main/skills/manga-full-stack. 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 Manga Full Stack?

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 Manga Full Stack?

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

Is the Manga Full Stack AI skill free?

Yes. It is published on GitHub by SwotAtmk 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.

Related AI Skills

View all
anthropics logo

Docx

anthropics
OrganizationPopular

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document',…

21.8K
184K
59 files
View
openclaw logo

Openclaw Docker E2e Authoring

openclaw
OrganizationPopular

Author OpenClaw Docker E2E and live provider Docker lanes.

82.2K
391K
Instructions
View
openclaw logo

Openclaw Parallels Smoke

openclaw
OrganizationPopular

Prepare, snapshot, run, rerun, debug, or interpret OpenClaw Parallels guest install, onboarding, gateway smoke, and upgrade checks across macOS, Windows, and Linux.

82.2K
391K
Instructions
View
openclaw logo

Openclaw Update

openclaw
OrganizationPopular

Route routine updates of an existing local or remote OpenClaw Gateway to its installation owner, with automatic session recovery. Defer to deployment-specific skills when available.

82.2K
391K
1 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇