# Tavily Search

> Real-time web search using Tavily API - search the web, extract page content, and get up-to-date information for RAG and research tasks

- Skill: `chainlesschain/tavily-search` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add chainlesschain/tavily-search`
- Raw SKILL.md: https://api.skillmd.com/api/skills/chainlesschain/tavily-search/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Web & Frontend
- License: MIT
- Author: chainlesschain (https://skillmd.com/u/chainlesschain)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/chainlesschain/tavily-search

---


# Tavily Search Skill

Real-time web search and content extraction using the Tavily API.

## Usage

```
/tavily-search <query>
/tavily-search extract <url>
```

## Modes

| Mode | Description | Best For |
| --- | --- | --- |
| `search` (default) | Keyword-based web search | Initial research, finding sources |
| `extract` | Deep content extraction from URL | Detailed analysis, specific pages |

## Setup

Set the `TAVILY_API_KEY` environment variable:

```bash
export TAVILY_API_KEY=tvly-your-api-key-here
```

## Integration Pattern

1. Use `search` for the discovery phase
2. Analyze results to find relevant URLs
3. Use `extract` for detailed content on specific URLs
4. Process extracted content for user needs

## Options

| Option | Values | Description |
| --- | --- | --- |
| `search_depth` | `basic`, `advanced` | Search depth (advanced costs more) |
| `max_results` | 1-20 | Maximum results to return |
| `include_answer` | boolean | Include AI-generated answer summary |

## Cost Considerations

- Search is cheaper than extract
- Use search to filter relevant URLs first
- Only extract URLs that are likely relevant
- `basic` depth is sufficient for most queries