home / skills / openclaw / skills / tavily-search

tavily-search skill

unsafe

/skills/arun-8687/tavily-search

This skill helps AI agents perform efficient web searches using Tavily API to return concise, relevant results.

This is most likely a fork of the tavily-search-1-0-0 skill from openclaw

npx playbooks add skill openclaw/skills --skill tavily-search

Review the files below or copy the command above to add this skill to your agents.

Files (4)

SKILL.md

1.2 KB

---
name: tavily
description: AI-optimized web search via Tavily API. Returns concise, relevant results for AI agents.
homepage: https://tavily.com
metadata: {"clawdbot":{"emoji":"🔍","requires":{"bins":["node"],"env":["TAVILY_API_KEY"]},"primaryEnv":"TAVILY_API_KEY"}}
---

# Tavily Search

AI-optimized web search using Tavily API. Designed for AI agents - returns clean, relevant content.

## Search

```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
```

## Options

- `-n <count>`: Number of results (default: 5, max: 20)
- `--deep`: Use advanced search for deeper research (slower, more comprehensive)
- `--topic <topic>`: Search topic - `general` (default) or `news`
- `--days <n>`: For news topic, limit to last n days

## Extract content from URL

```bash
node {baseDir}/scripts/extract.mjs "https://example.com/article"
```

Notes:
- Needs `TAVILY_API_KEY` from https://tavily.com
- Tavily is optimized for AI - returns clean, relevant snippets
- Use `--deep` for complex research questions
- Use `--topic news` for current events

Overview

This skill provides AI-optimized web search via the Tavily API, returning concise, relevant results tailored for AI agents. It focuses on clean snippets and structured results to speed up information retrieval and downstream processing. The utility includes options for result count, depth, topical filtering, and direct content extraction from URLs.

How this skill works

The skill calls the Tavily API using an API key to perform searches optimized for machine consumption, returning brief, relevant snippets and metadata. It supports a fast default mode and a --deep mode that performs more comprehensive, slower searches for complex research. A separate extract command fetches and cleans article content from a provided URL for direct use by agents.

When to use it

When you need concise, AI-friendly search results rather than full-page HTML
For quick fact-finding and to gather relevant snippets for agent reasoning
When researching complex topics with the --deep option to expand coverage
When tracking recent events using --topic news and --days to limit recency
When you need cleaned article text extracted from a URL for summarization or analysis

Best practices

Set TAVILY_API_KEY in your environment before using the skill
Start with default search for speed; use --deep only when more depth is required
Limit results with -n to keep responses compact and focused (default 5, max 20)
Use --topic news and --days to restrict results to recent events
Extract URL content when you need full cleaned text rather than snippets

Example use cases

Agent gathering supporting evidence for a short answer: run default search and use top 3 snippets
Background research for a long-form response: run search with --deep and increase -n
Monitoring breaking news on a topic: use --topic news with --days 2 to fetch the latest coverage
Preparing summarization input: run extract on a target article URL to get cleaned content
Archival retrieval for agents working with historical or repo-indexed content

FAQ

How do I authenticate?

Set the TAVILY_API_KEY environment variable with your Tavily API key.

What does --deep do?

--deep enables a more thorough search mode that is slower but returns broader and deeper results for complex queries.

How many results can I request?

Use -n to request up to 20 results; the default is 5.