manga-animation

完整的漫剧(动画漫画)生成工作流 skill。当用户想要:创作漫画剧集、生成动画短片、制作分镜脚本、设计原创角色、生成动漫风格视频片段、将故事想法转化为可视化内容,或任何涉及"漫剧""动漫创作""分镜""人设""画风设定""AI生成动画""参考图生成"的请求时,必须使用此 skill。 流程覆盖:剧本创作 → 分镜设计 → 人设+画风设定 → 分镜图生成(方舟图像)→ 视频生成(方舟图生视频)。每个阶段结束后必须等待用户确认再继续。即使用户只说"给我做个漫画动画"也应立即触发本 skill。

3,891 stars

Best use case

manga-animation is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

完整的漫剧(动画漫画)生成工作流 skill。当用户想要:创作漫画剧集、生成动画短片、制作分镜脚本、设计原创角色、生成动漫风格视频片段、将故事想法转化为可视化内容,或任何涉及"漫剧""动漫创作""分镜""人设""画风设定""AI生成动画""参考图生成"的请求时,必须使用此 skill。 流程覆盖:剧本创作 → 分镜设计 → 人设+画风设定 → 分镜图生成(方舟图像)→ 视频生成(方舟图生视频)。每个阶段结束后必须等待用户确认再继续。即使用户只说"给我做个漫画动画"也应立即触发本 skill。

Teams using manga-animation should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/polecomic/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/a574824551/polecomic/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/polecomic/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How manga-animation Compares

Feature / Agentmanga-animationStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

完整的漫剧(动画漫画)生成工作流 skill。当用户想要:创作漫画剧集、生成动画短片、制作分镜脚本、设计原创角色、生成动漫风格视频片段、将故事想法转化为可视化内容,或任何涉及"漫剧""动漫创作""分镜""人设""画风设定""AI生成动画""参考图生成"的请求时,必须使用此 skill。 流程覆盖:剧本创作 → 分镜设计 → 人设+画风设定 → 分镜图生成(方舟图像)→ 视频生成(方舟图生视频)。每个阶段结束后必须等待用户确认再继续。即使用户只说"给我做个漫画动画"也应立即触发本 skill。

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# 漫剧生成 Skill

## 核心原则

**每个阶段完成后必须暂停,展示产物,等用户确认或修改后再进入下一阶段。**
禁止一口气跑完所有阶段——用户需要在每个关卡看到结果并决定是否调整。

```
[阶段1] 剧本 ──→ ⏸ 用户确认
   ↓
[阶段2] 分镜表 ──→ ⏸ 用户确认
   ↓
[阶段3] 人设 + 画风 ──→ ⏸ 用户确认
   ↓
[阶段4] 分镜图生成(call_image_api.py)──→ ⏸ 用户确认图像质量
   ↓
[阶段5] 视频生成(call_video_api.py)
```

---

## 技术栈

| 用途 | 模型 | SDK 调用方式 |
|------|------|------------|
| 图像(人设图 + 分镜图) | `doubao-seedream-5-0-260128` | `client.images.generate` |
| 视频(图生视频) | `doubao-seedance-1-0-lite-i2v-250428`(调试)<br>`doubao-seedance-1-0-pro-250528`(正式) | `client.content_generation.tasks.create` |

**只需一个 Key**:`ARK_API_KEY`(方舟平台统一鉴权)

```bash
export ARK_API_KEY="your_key_here"
# 或在脚本顶部直接填写 ARK_API_KEY = "..."
```

---

## 阶段1:剧本创作

**参考:** `references/script-template.md`

- 若用户提供**完整剧本** → 跳过,直接进阶段2
- 若用户提供**创意/想法** → 输出:世界观、角色清单、三幕大纲、分场景剧本(含台词/动作/情绪)

保存:`output/[剧名]/script.md`

**⏸ 检查点**:展示剧本,询问是否调整,确认后进阶段2。

---

## 阶段2:分镜设计

**参考:** `references/storyboard-guide.md`

同时输出两个文件:

### storyboard.md(供人阅读)
完整分镜表格,见 storyboard-guide.md

### storyboard.json(供脚本调用)

```json
{
  "title": "剧名",
  "art_style_prefix": "",
  "shots": [
    {
      "shot_id": "S01_01",
      "duration": 4,
      "description_cn": "中文画面说明",
      "image_prompt": "静态画面的英文描述,不含运动",
      "video_prompt": "运动方式描述,如 character walking slowly forward",
      "characters": ["CHAR_001"],
      "dialogue": "台词/音效",
      "reference_image": null
    }
  ]
}
```

**image_prompt vs video_prompt 分工:**
- `image_prompt`:描述画面构成(景别、角色、场景、光线),用于生成静态分镜图
- `video_prompt`:只描述运动(镜头运动 + 角色动作),图生视频时用

**⏸ 检查点**:展示分镜表,提示用户此处调整最省钱,确认后进阶段3。

---

## 阶段3:人设 + 画风设定

**参考:** `references/character-guide.md`

### 3A. 输出角色人设卡:`characters/CHAR_001.md`

人设卡必须包含可直接用于 Prompt 的精确外貌描述,以及完整的图像生成 Prompt。示例结构:

```markdown
## CHAR_001 — [角色名]
年龄/性别/身份/性格关键词

### 外貌
发型发色 / 眼睛 / 体型 / 标志性特征(疤痕/纹路/配件)

### 服装(日常 / 战斗)

### 图像生成 Prompt(英文,完整可直接使用)
17-year-old teenage boy, [detailed appearance], [clothing],
full body front view, white background,
anime style, cel shading, shonen manga, high quality, masterpiece, sharp focus

ref_image_path:
```

### 3B. 确定画风,填入 storyboard.json

```json
"art_style_prefix": "anime style, shonen manga, cel shading, vibrant colors, high quality, masterpiece"
```

### 3C. ⚡ 关键步骤:更新脚本的 CHARACTER_PROMPTS

将角色 Prompt 填入 `call_image_api.py` 顶部的字典,每次有新角色都要更新:

```python
CHARACTER_PROMPTS = {
    "CHAR_001": "17-year-old teenage boy, black short hair, ..., full body front view, white background, anime style, ...",
    "CHAR_002": "...",
}
```

**⏸ 检查点**:展示所有人设卡 + 画风设定,确认 Prompt 准确描述了目标形象后进阶段4(开始消耗 API 额度)。

---

## 阶段4:分镜图生成

**脚本:** `scripts/call_image_api.py`
**API:** 方舟 `doubao-seedream-5-0-260128`,size=`2K`

### 运行命令

```bash
# Step 1:生成角色人设参考图
python call_image_api.py characters \
    --output output/[剧名]/characters/images/

# Step 2:生成分镜图(读取 storyboard.json 的 art_style_prefix + image_prompt)
python call_image_api.py storyboard \
    --input  output/[剧名]/storyboard.json \
    --output output/[剧名]/storyboard/frames/
```

脚本完成后自动将帧图路径写回 `storyboard.json` 的 `reference_image` 字段。

**⏸ 检查点**:引导用户打开 `storyboard/frames/` 查看图像,重点检查:
1. 角色外貌是否符合人设
2. 场景氛围/构图是否正确
3. 记录需要重生成的 shot_id(可单独重跑)

确认后进阶段5。

---

## 阶段5:视频生成

**脚本:** `scripts/call_video_api.py`
**API:** 方舟 `doubao-seedance-1-0-lite-i2v-250428`(lite,调试)

前置条件:`storyboard.json` 中所有 shot 的 `reference_image` 已填写。

### 运行命令

```bash
python call_video_api.py batch \
    --input  output/[剧名]/storyboard.json \
    --output output/[剧名]/videos/

# 如图片目录非默认,加 --frames-dir
python call_video_api.py batch \
    --input  output/[剧名]/storyboard.json \
    --output output/[剧名]/videos/ \
    --frames-dir output/[剧名]/storyboard/frames/
```

脚本工作流:提交任务 → 每8s轮询 → 成功后下载 .mp4 → 更新 generation_log.json。

### lite vs pro 切换

```python
# call_video_api.py 顶部修改这一行
ARK_VIDEO_MODEL = "doubao-seedance-1-0-lite-i2v-250428"   # 调试
ARK_VIDEO_MODEL = "doubao-seedance-1-0-pro-250528"         # 正式出片
```

---

## 输出文件结构

```
output/[剧名]/
├── script.md
├── storyboard.md
├── storyboard.json              ← 核心,贯穿阶段2-5
├── art_style.md
├── characters/
│   ├── CHAR_001.md
│   └── images/
│       └── CHAR_001_front.png
├── storyboard/
│   └── frames/
│       ├── S01_01.png           ← 阶段4产物 = 阶段5首帧
│       └── ...
├── videos/
│   └── S01_01.mp4
└── generation_log.json
```

---

## 常见问题快查

| 问题 | 解决方式 |
|------|---------|
| `❌ 未配置 ARK_API_KEY` | 脚本顶部填写,或 `export ARK_API_KEY=xxx` |
| `❌ 找不到参考图` | 先完成阶段4生成分镜图;或用 `--frames-dir` 手动指定 |
| 视频人物外貌与分镜图不符 | `video_prompt` 只描述动作,不重复角色外貌 |
| 图像风格不统一 | 检查 `storyboard.json` 的 `art_style_prefix` 是否已填写 |
| `volcengine SDK` 未安装 | `pip install 'volcengine-python-sdk[ark]' requests` |

Related Skills

ios-animation-implementation

3891
from openclaw/skills

Write Swift animation code using Apple's latest frameworks — SwiftUI animations, Core Animation, and UIKit. Prefer first-party APIs over third-party libraries. Use when implementing iOS animations, writing animation code, building transitions, creating gesture-driven interactions, or converting animation specs/designs into working Swift code. Covers iOS 18 through iOS 26 APIs including KeyframeAnimator, PhaseAnimator, custom Transition protocol, zoom navigation transitions, matchedGeometryEffect, symbol effects, mesh gradients, and SwiftUI-UIKit animation bridging.

ios-animation-design

3891
from openclaw/skills

Design and plan iOS animations with structured specs covering transitions, micro-interactions, gesture-driven motion, and loading states. Use when the user asks to plan, design, or spec out animations for an iOS app — including screen transitions, navigation animations, interactive gestures, onboarding flows, or any motion design work. Also use when the user wants animation recommendations or wants to decide between animation approaches before writing code.

ios-animation-code-review

3891
from openclaw/skills

Reviews iOS animation code for correctness, performance, accessibility, and Apple API best practices. Use when reviewing .swift files containing animation code — withAnimation, .animation(), PhaseAnimator, KeyframeAnimator, matchedGeometryEffect, navigationTransition, CABasicAnimation, CASpringAnimation, UIViewPropertyAnimator, UIDynamicAnimator, symbolEffect, scrollTransition, contentTransition, or custom Transition conformances.

web-animation-design

3891
from openclaw/skills

Design and implement web animations that feel natural and purposeful. Use this skill proactively whenever the user asks questions about animations, motion, easing, timing, duration, springs, transitions, or animation performance. This includes questions about how to animate specific UI elements, which easing to use, animation best practices, or accessibility considerations for motion. Triggers on: easing, ease-out, ease-in, ease-in-out, cubic-bezier, bounce, spring physics, keyframes, transform, opacity, fade, slide, scale, hover effects, microinteractions, Framer Motion, React Spring, GSAP, CSS transitions, entrance/exit animations, page transitions, stagger, will-change, GPU acceleration, prefers-reduced-motion, modal/dropdown/tooltip/popover/drawer animations, gesture animations, drag interactions, button press feel, feels janky, make it smooth.

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891
from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891
from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning