3d-wordcloud-visualizer
3D 词云可视化工具 - 将对话历史或其他文本数据自动转换为炫酷的 3D 地球词云,支持多格式文件导入(JSON/MD/TXT),自动中文分词和词频统计,生成 TOP30 高频词的 3D 可视化效果
About this skill
This skill empowers AI agents to generate captivating 3D word cloud visualizations from various text inputs, including large language model conversation histories, Markdown files, and plain text files. It automatically handles data processing steps such as UTF-8 decoding, deep parsing of JSON structures to extract relevant content, professional Chinese word segmentation, stop word removal, and word frequency calculation. The skill then identifies the top 30 most frequent words and renders them onto a realistic 3D globe using the Three.js engine, complete with star backgrounds and lighting effects. The generated visualization is purely client-side, running directly in a web browser without requiring any server-side processing or data upload, ensuring privacy and security. Users can interact with the 3D globe by dragging to rotate, zooming with the scroll wheel, and panning, alongside an optional automatic rotation feature for dynamic display. This robust tool provides an engaging and insightful way to analyze the textual landscape of dialogues or documents, making complex data easily digestible and visually appealing.
Best use case
The primary use case for this skill is to help users quickly grasp the central themes and frequently discussed topics within extensive text datasets, particularly long conversation logs from AI models. It is ideal for researchers, analysts, or anyone managing large textual corpora who needs an intuitive and interactive method to identify key trends, summarize content, or present data in a visually striking format. By automating the word cloud generation process, it saves significant manual effort in text analysis and enhances data comprehension.
3D 词云可视化工具 - 将对话历史或其他文本数据自动转换为炫酷的 3D 地球词云,支持多格式文件导入(JSON/MD/TXT),自动中文分词和词频统计,生成 TOP30 高频词的 3D 可视化效果
The user will receive an HTML file containing a self-contained web application that, when opened in a browser, allows them to upload their text data and interactively explore a 3D word cloud representation of its most frequent terms on a rotating globe.
Practical example
Example input
请将我的对话历史文件生成一个酷炫的 3D 地球词云。
Example output
好的,我已经为您创建了 `3d_wordcloud_visualizer.html` 文件。请在浏览器中打开它,然后上传您的 JSON、MD 或 TXT 文件以查看交互式 3D 词云。
When to use this skill
- When you need to visualize the dominant keywords and topics from a large conversation history or text document.
- To generate an interactive, client-side 3D word cloud from JSON, Markdown, or TXT files.
- For analyzing Chinese text data, leveraging its automatic segmentation and stop word filtering.
- When you want a privacy-focused text analysis tool that processes data entirely locally.
When not to use this skill
- When you require static, 2D word cloud images without interactive features.
- For very short texts where word frequency analysis offers minimal insight.
- If you need advanced natural language processing features beyond basic word frequency, such as sentiment analysis or deep topic modeling.
- When the primary goal is programmatic text manipulation rather than visual exploration.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/3d-wordcloud-visualizer/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How 3d-wordcloud-visualizer Compares
| Feature / Agent | 3d-wordcloud-visualizer | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | easy | N/A |
Frequently Asked Questions
What does this skill do?
3D 词云可视化工具 - 将对话历史或其他文本数据自动转换为炫酷的 3D 地球词云,支持多格式文件导入(JSON/MD/TXT),自动中文分词和词频统计,生成 TOP30 高频词的 3D 可视化效果
How difficult is it to install?
The installation complexity is rated as easy. You can find the installation instructions above.
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
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Agents for Marketing
A curated list of the best AI agents and skills for marketing teams focused on SEO, content systems, outreach, and campaign execution.
SKILL.md Source
# 3D 词云可视化生成器
将大模型对话历史(或任何文本数据)自动转换为炫酷的 3D 地球词云可视化效果。
## 触发条件
当用户需要以下操作时使用此 Skill:
- 将对话历史可视化
- 生成 3D 词云
- 分析文本关键词分布
- 创建交互式数据可视化
- 导出 3D 词云为图片
## 功能特性
### 核心能力
1. **多格式支持**
- JSON - 自动深度提取对话内容(递归解析 content/message/text/question/answer 字段)
- Markdown - 直接读取全文
- TXT - 直接读取全文
- UTF-8-sig 编码 - 避免中文乱码
2. **自动化数据处理**
- 读取文件 → UTF-8 解码
- 格式解析 → JSON 自动递归提取
- 中文分词 → 使用专业分词库(segmentit)
- 去停用词 → 过滤 "的、了、是、吗" 等无意义词
- 词频统计 → 自动计算权重
- 排序筛选 → 取 TOP30 高频词
- 生成词云 → 自动渲染到地球
3. **3D 地球词云**
- Three.js 渲染引擎
- 真实的 3D 地球模型
- 词云作为纹理映射到地球表面
- 随机配色(15 种预设颜色)
- 星空背景(5000 颗星)
- 光照效果(环境光 + 方向光)
4. **交互功能**
- 鼠标拖拽旋转地球
- 滚轮缩放视角
- 右键平移视角
- 自动旋转展示
- 阻尼效果(更丝滑)
- 范围限制(1.2 - 5.0 距离)
5. **纯前端运行**
- 无需服务器
- 无需后端处理
- 数据不上传云端
- 完全本地处理
## 使用指南
### 基本用法
1. **准备数据文件**
- 使用 `conversation-exporter` Skill 导出对话历史
- 或准备任何 JSON/MD/TXT 文件
2. **生成可视化**
- 在对话中告诉 AI:"生成 3D 词云"
- AI 会自动:
- 创建 HTML 文件
- 包含完整的 3D 渲染代码
- 支持文件上传功能
- 自动解析和生成词云
3. **查看效果**
- 在浏览器中打开生成的 HTML 文件
- 上传你的数据文件
- 等待自动解析和生成
- 观察 3D 词云地球
### 高级选项
- **自定义配色方案** - 修改颜色数组
- **调整词云数量** - 修改 TOP30 为其他数值
- **修改地球大小** - 调整 SphereGeometry 参数
- **调整旋转速度** - 修改 autoRotateSpeed 值
- **自定义停用词** - 修改 stopWords Set
## 数据结构
### JSON 格式要求
支持任意嵌套结构,自动提取以下字段:
- `content`
- `text`
- `message`
- `question`
- `answer`
示例:
```json
{
"conversation_history": {
"timeline": [
{
"date": "2026-03-25",
"type": "skill_installation",
"action": "安装 Skills",
"details": {
"content": "成功安装了 5 个 Skills"
}
}
]
}
}
```
### 关键词统计
- 词频决定文字大小(count * 2.5 像素)
- 自动排序并取 TOP30
- 过滤停用词
- 最小词频限制为 1
## 配置选项
### 文件编码
- 所有文件:UTF-8-sig(带 BOM)
- 目的:避免中文乱码
### 性能优化
- 纹理分辨率:2048x1024(高清)
- 地球细分:64x64
- 星空粒子:5000 个
- 帧率优化:requestAnimationFrame
### 停用词列表
```javascript
const stopWords = new Set([
'的', '了', '是', '我', '你', '在', '有', '和', '就', '都',
'吗', '吧', '呢', '啊', '哦', '嗯', '这个', '那个', '可以',
'然后', '但是', '因为', '所以', '如果', '需要', '谢谢'
]);
```
## 文件输出
### 生成的文件
- `3d_word_cloud_visualizer.html` - 完整的可视化工具
- 包含所有必要的 HTML/CSS/JS 代码
- 支持文件上传功能
- 自动解析和生成词云
- 可在浏览器中直接运行
### 可选导出
- 支持导出当前词云为 PNG 图片(通过浏览器截图)
- 支持导出词云数据为 JSON 格式
## 技术实现
### 依赖库
1. **Three.js** (v0.160.0)
- 3D 渲染引擎
- CDN: https://cdn.jsdelivr.net/npm/three@0.160.0/build/three.min.js
2. **OrbitControls**
- 鼠标交互控制
- CDN: https://cdn.jsdelivr.net/npm/three@0.160.0/examples/js/controls/OrbitControls.js
3. **segmentit** (v2.0.3)
- 中文分词库
- CDN: https://cdn.jsdelivr.net/npm/segmentit@2.0.3/dist/umd/segmentit.min.js
### 无外部依赖
- ✅ 不需要后端服务器
- ✅ 不需要 API Key
- ✅ 不需要数据库
- ✅ 所有代码包含在单个 HTML 文件中
## 注意事项
1. **文件大小**
- 建议单个文件不超过 10MB
- 大文件可能导致浏览器卡顿
2. **关键词数量**
- 默认 TOP30,可根据需要调整
- 过多关键词会影响性能
3. **浏览器兼容性**
- 推荐使用 Chrome、Firefox、Edge 现代浏览器
- 需要支持 WebGL
- IE 11 不支持
4. **网络连接**
- 首次打开需要下载 CDN 资源
- 后续运行可在离线模式(需缓存)
## 错误处理
### 常见问题
1. **文件解析失败**
- 检查文件格式是否正确
- 确保 JSON 语法无错误
- 尝试使用其他格式(MD/TXT)
2. **词云生成失败**
- 检查文件是否包含有效文本
- 确认 segmentit 库加载成功
- 查看浏览器控制台错误信息
3. **3D 渲染失败**
- 检查浏览器是否支持 WebGL
- 确认 CDN 资源加载成功
- 尝试使用不同浏览器
## 安全特性
- ✅ 本地处理,数据不上传云端
- ✅ 无外部 API 调用
- ✅ 无数据持久化
- ✅ 完全由用户控制数据
## 更新日志
- **v1.0** (2026-03-25)
- 初始版本
- 支持 JSON/MD/TXT 三种格式
- 自动中文分词和词频统计
- 3D 地球词云可视化
- 鼠标交互功能
- 星空背景效果
## 示例工作流
### 完整流程
1. **导出对话历史**
- 使用 `conversation-exporter` Skill
- 选择导出格式(推荐 JSON)
- 保存到本地
2. **生成可视化**
- 在对话中:"生成 3D 词云"
- AI 创建 `3d_word_cloud_visualizer.html`
3. **查看词云**
- 浏览器打开 HTML 文件
- 上传导出的对话历史文件
- 等待自动解析和生成
4. **交互探索**
- 拖拽旋转地球
- 滚轮缩放视角
- 观察关键词分布
- 截图保存效果
## 技术亮点
### 纯前端实现
- 无需后端服务器
- 完全本地处理
- 数据安全可控
### 自动化程度高
- 用户只需上传文件
- 自动解析、统计、生成
- 零配置、零操作
### 视觉效果好
- 3D 地球模型
- 词云纹理映射
- 星空背景
- 流畅动画
### 交互体验佳
- 鼠标拖拽旋转
- 滚轮缩放
- 自动旋转展示
- 阻尼效果
## 适用场景
- 对话历史可视化
- 文本关键词分析
- 数据展示演示
- 教育培训演示
- 数据新闻制作
- 交互式报告
## 最佳实践
1. **准备数据**
- 确保文件格式正确
- 检查编码为 UTF-8
- 文件大小适中
2. **生成词云**
- 使用现代浏览器
- 首次打开需要网络(加载 CDN)
- 耐心等待解析完成
3. **探索分析**
- 尝试不同角度观察
- 注意高频关键词
- 对比不同时期数据
4. **保存成果**
- 使用截图工具保存图片
- 记录分析结论
- 分享可视化结果Related Skills
claw2ui
Generate interactive web pages (dashboards, charts, tables, reports) and serve them via public URL. Use this skill when the user explicitly asks for data visualization, dashboards, analytics reports, comparison tables, status pages, or web-based content. Also triggers for: "draw me a chart", "make a dashboard", "show me a table", "generate a report", "visualize this data", "render this as a page", "publish a page", "claw2ui". If the response would benefit from charts, sortable tables, or rich layout, **suggest** using Claw2UI and wait for user confirmation before publishing. Chinese triggers: "做个仪表盘", "画个图表", "做个报表", "生成一个页面", "做个dashboard", "数据可视化", "做个网页", "展示数据", "做个表格", "做个图", "发布一个页面", "做个看板". Additional English triggers: "create a webpage", "show analytics", "build a status page", "make a chart", "data overview", "show me stats", "create a board", "render a page", "comparison chart", "trend analysis", "pie chart", "bar chart", "line chart", "KPI dashboard", "metrics overview", "weekly report", "monthly report".
mermaid-visualizer
Transform text content into professional Mermaid diagrams for presentations and documentation. Use when users ask to visualize concepts, create flowcharts, or make diagrams from text. Supports process flows, system architectures, comparisons, mindmaps, and more with built-in syntax error prevention.
karpathy-jobs-bls-visualizer
Research tool for visually exploring BLS Occupational Outlook Handbook data with an interactive treemap, LLM-powered scoring pipeline, and data scraping/parsing utilities.
matplotlib
Matplotlib is Python's foundational visualization library for creating static, animated, and interactive plots.
claude-d3js-skill
This skill provides guidance for creating sophisticated, interactive data visualisations using d3.js.
mviz
A chart & report builder designed for use by AI.
---
name: article-factory-wechat
humanizer
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.
find-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.
tavily-search
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.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.