tavily-search-darry

# Tavily Search

Tavily 是一个专业的搜索 API，提供高质量、快速、结构化的搜索结果。

## 功能

### 网络搜索
- **智能搜索** - LLM 优化的搜索结果
- **内容提取** - 自动提取网页内容摘要
- **相关性评分** - 每个结果带有相关性分数

### 新闻搜索
- **时间过滤** - 按天、周、月、年过滤
- **域名过滤** - 指定搜索特定网站
- **深度搜索** - basic/advanced 搜索模式

### 研究工具
- **crawl** - 网页爬取
- **extract** - 内容提取
- **research** - 深度研究

## 使用方式

### 基本搜索

```bash
./search/scripts/search.sh '{"query": "AI 最新进展", "max_results": 10}'
```

### 新闻搜索

```bash
./search/scripts/search.sh '{"query": "科技新闻", "time_range": "week", "max_results": 10}'
```

### 域名过滤

```bash
./search/scripts/search.sh '{"query": "机器学习", "include_domains": ["arxiv.org", "github.com"]}'
```

## 子技能

- `search` - 网络搜索
- `crawl` - 网页爬取
- `extract` - 内容提取
- `research` - 深度研究

## 认证

使用 Tavily API Key 或 OAuth 认证。

获取 API Key: https://tavily.com

---

*Tavily Search, 智能搜索* 🔍

# Agent Skills

## Installation

```bash
npx skills add https://github.com/tavily-ai/skills
```

## Authentication

**No setup required** — Uses OAuth via the Tavily MCP server.

> **Important:** You must have an existing Tavily account. The OAuth flow only supports login — account creation is not available through this flow. If you don't have an account, [sign up at tavily.com](https://tavily.com) first.

On first run, the script will:
1. Check for existing tokens in `~/.mcp-auth/`
2. If none found, automatically open your browser for OAuth authentication

### Alternative: API Key

If you prefer using an API key, get one at [https://tavily.com](https://tavily.com) and add to `~/.claude/settings.json`:
```json
{
  "env": {
    "TAVILY_API_KEY": "tvly-your-api-key-here"
  }
}
```

## Available Skills

| Skill | Command | Description |
|-------|---------|-------------|
| **Search** | `/search` | Search the web using Tavily's LLM-optimized API. Returns relevant results with content snippets, scores, and metadata. |
| **Research** | `/research` | Get research on any topic with citations. Supports structured JSON output for pipelines. |
| **Extract** | `/extract` | Extract clean content from specific URLs. Returns markdown/text from web pages. |
| **Crawl** | `/crawl` | Crawl websites to download documentation, knowledge bases, or web content as local markdown files. |
| **Tavily Best Practices** | `/tavily-best-practices` | Reference documentation for building production-ready Tavily integrations in agentic workflows, RAG systems, or autonomous agents. |