从一个技术关键词出发,自动生成前沿技术领域的技术全景图谱。AI Agent Skill for Gemini CLI / Claude Code.
# Technology Mapping Skill
> 从一个技术关键词出发,自动生成前沿技术领域的**技术全景图谱**。
面向 VC 技术尽调场景:搜索全球创业公司 → 逆向溯源创始人 PhD 导师 → 追溯到领域奠基人 → Graphviz 出图。
## 核心产出
一张 SVG 矢量图谱,包含:
- **学者节点**(蓝色)— 按师承链纵向排列,上方为导师
- **公司节点**(绿色/粉色)— 标注"继承/自主/独立/回归"技术来源
- **技术概念节点**(紫色)— 每条技术路线的核心特征
- **里程碑节点**(黄色)— 重大事件时间锚点
- **流派聚类**(虚线框)— 按技术路线分组
每条线都可验证。师承关系优先通过 Wikidata P184 查询,不足时 Web 搜索补充。
## 工作流(6 阶段)
```
Phase 0 领域适应 → domain_profile + 锚点验证
Phase 1 全球目标发现 → 公司/学者/里程碑清单
Phase 2 逆向溯源 → PhD advisor chain 追溯
Phase 3 剪枝 & 聚类 → 按技术路线分流派
Phase 4 可视化输出 → Graphviz SVG 图谱
Phase 5 质量验证 & 报告 → 文字报告 + 溯源验证表
```
## 依赖
| 依赖 | 安装 |
|------|------|
| Graphviz 系统 | `winget install Graphviz.Graphviz` |
| graphviz Python 库 | `pip install graphviz` |
| requests Python 库 | `pip install requests` |
## 参考案例
以下案例由此 Skill 生成,供参考:
| 案例 | 目录 | 技术路线数 |
|------|------|-----------|
| 类脑智能 (Neuromorphic Computing) | `examples/02_neuromorphic_computing/` | 6 |
| 磁约束核聚变 (MCF) | `examples/03_magnetic_confinement_fusion/` | 4 |
| 脑机接口 (BCI) | `examples/04_brain_computer_interface/` | 5 |
## 文件结构
```
technology-mapping/
├── SKILL.md # 6 阶段工作流定义
├── CHANGELOG.md # 版本变更记录
├── README.md # 本文件
├── scripts/
│ └── wikidata_client.py # Wikidata P184 查询脚本
├── references/
│ ├── connection_strength.md # 连接强度评估规范
│ ├── data_schema.md # 节点/边类型定义
│ ├── visual_spec.md # 可视化 + 布局约束规范
│ └── vc_framework.md # VC 分析框架
└── examples/
├── 02_neuromorphic_computing/
├── 03_magnetic_confinement_fusion/
└── 04_brain_computer_interface/
```
## License
MIT
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.