A high-performance web search skill for AI agents that leverages the Tavily API to provide token-optimized, real-time internet data.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install tavily-search-simple
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install tavily-search-simple using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Tavily Search?
Tavily Search is a specialized integration within the Openclaw Skills ecosystem designed specifically for LLMs and AI Agents. Unlike traditional search engines, this skill utilizes the Tavily API to fetch and summarize the latest information from across the web in a format that minimizes token consumption. It provides a bridge between static AI models and the dynamic nature of the internet, allowing agents to ground their responses in up-to-date facts, news, and specialized data without overwhelming the context window.
Tavily Search Use Cases
- Fact-checking and grounding AI responses with real-time web data using Openclaw Skills.
- Conducting deep-dive research into specific topics like finance or current events.
- Retrieving summarized content from specific domains while filtering out irrelevant noise.
- Gathering visual context by including images in search results for multimodal tasks.
How Tavily Search Works
- The AI agent triggers the search command with a specific query and optional filters.
- The skill processes parameters such as search depth and topic classification to optimize the request.
- A secure request is dispatched to the Tavily API endpoint using the provided API credentials.
- The skill receives the raw search results and processes them into the requested format, such as raw JSON or readable Markdown.
- The filtered and summarized data is returned to the agent, ready for synthesis within the Openclaw Skills framework.
Tavily Search Setup
To use Tavily Search, you must first obtain a Tavily API key and configure it as an environment variable in your Openclaw Skills environment.
export TAVILY_API_KEY="your_api_key_here"
Alternatively, you can add this key to your ~/.openclaw/.env file. You can then run the search script as follows:
python3 scripts/tavily_search.py --query "your search query"
Tavily Search Data Schema & Taxonomy
The skill returns data based on the specified format parameter to ensure compatibility with different workflows in Openclaw Skills.
| Parameter | Type | Description |
|---|---|---|
| query | string | The primary search term used to fetch data. |
| search-depth | string | Choose between basic, advanced, fast, or ultra-fast processing. |
| topic | string | Categorize search into general, news, or finance themes. |
| format | string | Output data as raw JSON, brave (minimal) JSON, or Markdown (md). |
| include-images | bool | Whether to include relevant image URLs in the output. |
Tavily Search Advanced Features
- Intelligent domain filtering to include or exclude specific websites for targeted research.
- Advanced search depth settings to extract multiple text chunks per source for high-precision retrieval.
- Automatic parameter optimization where the skill adjusts search settings based on query intent.
- Time-range filtering to restrict results to the last day, week, month, or year for fresh content.
- Flexible output formatting to optimize token usage across various Openclaw Skills configurations.
SKILL.md
Loading
Related Openclaw Skills
Texas Electricity Savings Monitor
A professional-grade energy advisor skill that automates the discovery, comparison, and monitoring of residential electricity plans in the Texas market.
Related Works Report Pipeline
A sophisticated workflow that transforms multiple academic paper markdown files into a unified, citation-normalized related-works report with integrated arXiv abstracts.
Tavily arXiv Paper Fetech
An automated pipeline that resolves scientific paper titles into verified arXiv metadata and generates structured research reports.
ICCircle News
An AI agent skill that fetches and aggregates semiconductor industry news and VLSI blog updates from multiple global sources.
Idea Inbox
A powerful automation tool that captures ideas from Feishu private chats and organizes them into a structured Bitable database using AI.
Srbija Voz Status
A powerful transit monitoring skill that scrapes and summarizes live train status and station metadata from Srbija Voz official endpoints.
Featured*
