Nanobanana Ppt Visualizer logo

Nanobanana Ppt Visualizer

CommunityPopular
anbeime
nanobanana-ppt-visualizer

平面设计师与内容创作者在制作演示文稿时,当需要将内容大纲转化为高颜值视觉大片,使用此技能可一键生成风格化配图、交互式网页播放器及演示视频,轻松实现从内容规划到视觉呈现的完整闭环,大幅提升汇报演示质感!

Overview

Publisheranbeime
Repositoryskill
Skill namenanobanana-ppt-visualizer
Stars
6.9K
Forks
645
Bundled files
8
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.

  • 8 bundled files

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

  • Open source

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

Installation

Install the Nanobanana Ppt Visualizer 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.
  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/anbeime/skill.git /tmp/skill
mkdir -p .claude/skills
cp -r /tmp/skill/skills/nanobanana-ppt-visualizer/nanobanana-ppt-visualizer .claude/skills/nanobanana-ppt-visualizer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Nanobanana Ppt Visualizer 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 Nanobanana Ppt Visualizer 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 Nanobanana Ppt Visualizer 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.

PPT 视觉增强工具

任务目标

  • 本 Skill 用于:为 PPT 内容生成高质量视觉呈现,包括图片渲染、交互式播放器和视频合成
  • 能力包含:风格化图片生成、HTML 播放器生成、视频素材管理、FFmpeg 视频合成
  • 触发条件:用户需要为 PPT 内容添加视觉效果,或与 ppt-generator Skill 协同工作

前置准备

  • 依赖说明:scripts 脚本所需的依赖包
    pillow>=9.0.0
    python-dotenv>=0.19.0
  • 系统依赖:FFmpeg(可选,用于视频合成功能)
    bash
    # Ubuntu/Debian
    sudo apt-get install ffmpeg
    
    # macOS
    brew install ffmpeg

操作步骤

标准流程(与 ppt-generator 协同)

步骤 1:获取 PPT 内容(协作模式)
  1. 与 ppt-generator Skill 协同:
  2. 接收 JSON 数据,包含:
    • metadata:标题、作者、主题、关键词
    • slides:每页的布局、标题、内容、图片标注
步骤 2:选择视觉风格
  1. 扫描 assets/styles/ 目录,列出可用风格:
    • gradient-glass.md:渐变毛玻璃风格(科技感、商务)
    • vector-illustration.md:矢量插画风格(温暖、教育)
  2. 根据内容主题和场景推荐合适的风格
  3. 智能体生成图片描述提示词,参考风格模板
步骤 3:生成视觉素材
  1. 图片生成(使用智能体能力):

    • 根据每页内容和风格模板,生成图片描述
    • 使用智能体的图像生成能力创建图片
    • 保存为 slide-01.png, slide-02.png 等
  2. 可选:视频生成(需要可灵 AI API):

    • 如果用户需要视频转场,调用可灵 AI API
    • 生成首页预览视频和页面转场视频
    • 使用 scripts/video_materials.py 管理视频素材
步骤 4:生成播放器
  1. 调用 scripts/generate_viewer.py 生成 HTML 播放器:
    • 支持图片轮播、键盘导航、全屏播放
    • 支持视频+图片混合播放(如果生成了视频)
  2. 输出交互式播放器,可直接在浏览器中预览
步骤 5:视频合成(可选)
  1. 如果生成了视频素材,调用 scripts/video_composer.py
    • 使用 FFmpeg 合成完整视频
    • 统一分辨率和帧率
    • 输出 full_ppt_video.mp4

独立使用模式

当用户直接提供 PPT 内容(JSON 格式)时:

  1. 读取用户提供的 JSON 文件或内容
  2. 执行步骤 2-5,生成视觉呈现

协同工作流程

与 ppt-generator Skill 配合

用户请求:"生成一个关于 AI 产品的 PPT"

┌─────────────────────────────────────────────────────────┐
│  ppt-generator Skill                                    │
├─────────────────────────────────────────────────────────┤
│  1. 主题分析师:分析主题,生成大纲                        │
│  2. 模板设计师:推荐布局                                  │
│  3. 内容策划师:规划内容结构                              │
│  4. 文本创作者:撰写内容                                  │
│  5. 视觉设计师:提供配图建议                              │
│  6. 优化编辑师:优化文本                                  │
│  7. PPT 构建师:生成 JSON 数据                           │
└─────────────────────────────────────────────────────────┘
                          ▼ 输出 JSON
┌─────────────────────────────────────────────────────────┐
│  nanobanana-ppt-visualizer Skill                        │
├─────────────────────────────────────────────────────────┤
│  1. 接收 JSON 数据                                       │
│  2. 选择视觉风格                                          │
│  3. 生成图片(使用智能体能力)                            │
│  4. 生成 HTML 播放器                                      │
│  5. 可选:视频合成                                        │
└─────────────────────────────────────────────────────────┘
                          ▼ 输出
              交互式播放器 + 完整视频(可选)

数据格式兼容性

ppt-generator 输出的 JSON 格式与 nanobanana-ppt-visualizer 完全兼容:

json
{
  "metadata": {
    "title": "演示文稿标题",
    "author": "作者姓名"
  },
  "slides": [
    {
      "layout": "TitleSlide",
      "title": "封面标题",
      "content": ["副标题"],
      "notes": "备注"
    }
  ]
}

资源索引

注意事项

  • 本 Skill 与 ppt-generator Skill 完全兼容,可以无缝协作
  • 图片生成使用智能体的图像生成能力,无需第三方 API
  • 视频生成功能需要可灵 AI API(可选),如需使用请配置密钥
  • FFmpeg 是可选依赖,仅在使用视频合成功能时需要
  • 保持与用户的互动,在关键节点(如风格选择)征求反馈

使用示例

示例 1:与 ppt-generator 完整协作

  • 功能说明:两个 Skill 完整协作,从内容到视觉
  • 执行方式:ppt-generator(7 个角色)→ nanobanana-ppt-visualizer(视觉生成)
  • 用户指令:"生成一个关于 AI 产品的 PPT,使用渐变毛玻璃风格"
  • 输出:交互式播放器 + 完整视频(可选)

示例 2:基于现有 JSON 生成播放器

  • 功能说明:接收 JSON 数据,生成播放器
  • 执行方式:nanobanana-ppt-visualizer 独立运行
  • 关键参数:JSON 文件路径、风格选择
  • 命令:python scripts/generate_viewer.py --input ./ppt_data.json --style gradient-glass

示例 3:仅生成图片(无视频)

  • 功能说明:使用智能体生成 PPT 图片
  • 执行方式:智能体(图像生成)+ 脚本(播放器生成)
  • 适用场景:快速预览、静态展示
  • 输出:HTML 播放器 + 图片文件

示例 4:完整视频合成

  • 功能说明:合成包含转场的完整视频
  • 执行方式:脚本(FFmpeg 合成)
  • 前提:已生成图片和视频素材
  • 命令:python scripts/video_composer.py --output ./full_ppt_video.mp4

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 Nanobanana Ppt Visualizer AI skill do?

平面设计师与内容创作者在制作演示文稿时,当需要将内容大纲转化为高颜值视觉大片,使用此技能可一键生成风格化配图、交互式网页播放器及演示视频,轻松实现从内容规划到视觉呈现的完整闭环,大幅提升汇报演示质感!

Why use Nanobanana Ppt Visualizer on TypingMind?

Because you install it once and use it with any model. Nanobanana Ppt Visualizer 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 Nanobanana Ppt Visualizer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/anbeime/skill/tree/main/skills/nanobanana-ppt-visualizer/nanobanana-ppt-visualizer. 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 Nanobanana Ppt Visualizer?

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 Nanobanana Ppt Visualizer?

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

Is the Nanobanana Ppt Visualizer AI skill free?

It is published on GitHub by anbeime. Check the repository for licensing terms. 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 👇