home / skills / openclaw / skills / tavily-search-1-0-0

tavily-search-1-0-0 skill

unsafe

This skill helps AI agents perform fast, relevant web searches via Tavily API, returning concise results for efficient decision making.

npx playbooks add skill openclaw/skills --skill tavily-search-1-0-0

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 configurable search depth and topics to speed up retrieval for downstream reasoning tasks.

How this skill works

The skill queries the Tavily API to fetch ranked search results and extracts clean snippets suitable for agent consumption. Options let you control result count, enable a deeper research mode, restrict to news, and extract full article content from a URL when needed.

When to use it

When an AI agent needs focused, concise web search results instead of raw HTML
For research tasks requiring deeper, broader coverage using the --deep option
When you need recent coverage limited to news and a specific date range
To extract and summarize the main content from a single article URL
When integrating search into pipelines that expect structured, AI-ready snippets

Best practices

Set result count (-n) to a small number (3–10) for faster, more targeted responses
Use --deep for complex research but expect longer latency
Use --topic news and --days to limit results to recent events
Supply a valid TAVILY_API_KEY and handle rate limits and errors gracefully
Post-process snippets for citation and provenance before presenting to end users

Example use cases

Provide an agent with a concise briefing on a technical topic using --deep for thorough coverage
Monitor recent developments by querying with --topic news and --days 7 for weekly summaries
Quickly extract the main content of a source article to create a short summary or fact-check
Build an assistant that fetches AI-safe snippets for downstream summarization or Q&A
Compare multiple perspectives on a topic by increasing result count and aggregating snippets

FAQ

Do I need an API key?

Yes. You must supply a TAVILY_API_KEY from https://tavily.com to use the service.

What does --deep do?

--deep enables a more comprehensive search mode that returns broader and deeper coverage but is slower.

How do I limit results to recent news?

Use --topic news and add --days <n> to restrict results to the last n days.