Summary
TL;DR: Web search using Tavily's LLM-optimized API. Returns relevant results with content snippets, scores, and metadata.
Tavily Search connects your AI agent to Tavily's search API, which is designed specifically for LLM consumption. Results come back with content snippets, relevance scores, and clean metadata that your agent can work with directly.
Unlike regular search engines that return HTML-heavy pages, Tavily pre-processes results into structured data. Your agent gets the information it needs without parsing messy web pages.
This is a solid choice if you want high-quality search results that are ready for AI processing. The trade-off is that it requires a Tavily API key, but the result quality is noticeably better for agent workflows.
Use cases
- Running web searches optimized for AI agent consumption
- Getting structured search results with relevance scores and snippets
- Researching topics where clean, pre-processed content matters
- Building agent workflows that chain search results into analysis
Installation
Run this command to install the skill on your OpenClaw agent:
npx clawhub@latest install liang-tavily-searchSecurity scan
The skill's code, instructions, and required credential (TAVILY_API_KEY) are consistent with a simple Tavily web-search wrapper and do not request unrelated access.
SKILL.md
---
name: tavily-search
description: Web search using Tavily's LLM-optimized API. Returns relevant results with content snippets, scores, and metadata.
homepage: https://tavily.com
metadata: {"openclaw":{"emoji":"🔍","requires":{"bins":["node"],"env":["TAVILY_API_KEY"]},"primaryEnv":"TAVILY_API_KEY"}}
---
# Tavily Search
Search the web and get relevant results optimized for LLM consumption.
## Authentication
Get your API key at https://tavily.com and add to your OpenClaw config:
```json
{
"skills": {
"entries": {
"tavily-search": {
"enabled": true,
"apiKey": "tvly-YOUR_API_KEY_HERE"
}
}
}
}
```
Or set the environment variable:
```bash
export TAVILY_API_KEY="tvly-YOUR_API_KEY_HERE"
```
## Quick Start
### Using the Script
```bash
node {baseDir}/scripts/search.mjs "query"
node {baseDir}/scripts/search.mjs "query" -n 10
node {baseDir}/scripts/search.mjs "query" --deep
node {baseDir}/scripts/search.mjs "query" --topic news
```
### Examples
```bash
# Basic search
node {baseDir}/scripts/search.mjs "python async patterns"
# With more results
node {baseDir}/scripts/search.mjs "React hooks tutorial" -n 10
# Advanced search
node {baseDir}/scripts/search.mjs "machine learning" --deep
# News search
node {baseDir}/scripts/search.mjs "AI news" --topic news
# Domain-filtered search
node {baseDir}/scripts/search.mjs "Python docs" --include-domains docs.python.org
```
## Options
| Option | Description | Default |
|--------|-------------|---------|
| `-n <count>` | Number of results (1-20) | 10 |
| `--depth <mode>` | Search depth: `ultra-fast`, `fast`, `basic`, `advanced` | `basic` |
| `--topic <topic>` | Topic: `general` or `news` | `general` |
| `--time-range <range>` | Time range: `day`, `week`, `month`, `year` | - |
| `--include-domains <domains>` | Comma-separated domains to include | - |
| `--exclude-domains <domains>` | Comma-separated domains to exclude | - |
| `--raw-content` | Include full page content | false |
| `--json` | Output raw JSON | false |
## Search Depth
| Depth | Latency | Relevance | Use Case |
|-------|---------|-----------|----------|
| `ultra-fast` | Lowest | Lower | Real-time chat, autocomplete |
| `fast` | Low | Good | Need chunks but latency matters |
| `basic` | Medium | High | General-purpose, balanced |
| `advanced` | Higher | Highest | Precision matters, research |
## Tips
- **Keep queries under 400 characters** - Think search query, not prompt
- **Break complex queries into sub-queries** - Better results than one massive query
- **Use `--include-domains`** to focus on trusted sources
- **Use `--time-range`** for recent information
- **Filter by `score`** (0-1) to get highest relevance resultsVersion history
- Initial release of Tavily Search skill. - Enables web search through Tavily’s API, optimized for LLMs. - Supports result snippets, scores, metadata, and domain/topic filtering. - Provides flexible search depth options and time range filtering. - Authentication via environment variable or config file. - Includes command-line usage examples and documentation.
Related skills
g_pyAngMulti Search Engine
Multi search engine integration with 17 engines (8 CN + 9 Global). Supports advanced search operators, time filters, site search, privacy engines, and WolframAlpha knowledge queries. No API keys required.
g_pyAngMulti Search Engine
Multi search engine integration with 17 engines (8 CN + 9 Global). Supports advanced search operators, time filters, site search, privacy engines, and WolframAlpha knowledge queries. No API keys required.
ide-reaBaidu Search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
ide-reaBaidu Search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
Frequently asked questions
Tavily's API returns structured results designed for LLMs. You get relevance scores, clean content snippets, and metadata instead of raw HTML pages that need parsing.
Installation method
Send this prompt to your agent to install the skill
npx clawhub@latest install liang-tavily-searchSkill data sourced from ClawHub