tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/aysun168/tavily-skill-bakWhat This Skill Does
The tavily-search skill integrates the Tavily API into your OpenClaw agent, providing high-quality, AI-optimized web search capabilities. Unlike traditional search engines, Tavily is specifically designed for LLMs, performing autonomous research to aggregate information from multiple sources and providing clean, actionable data. It excels at extracting key insights from search results, making it the primary tool for queries that require real-time knowledge, fact-checking, or comprehensive research on rapidly evolving topics.
Installation
Installation is handled via the OpenClaw CLI. Run the following command in your terminal: clawhub install openclaw/skills/skills/aysun168/tavily-skill-bak. After installation, you must acquire an API key from https://tavily.com. You can configure this key either by exporting TAVILY_API_KEY as an environment variable or by adding it directly to your openclaw.json configuration file under the tavily object. Once set, the skill is automatically detected and ready for use.
Use Cases
This skill is ideal for tasks involving information synthesis. Use it to perform market research, gather current news updates, verify technical information that may have changed since your model's training date, or generate concise briefings on specific subjects. It is particularly effective when you need a consolidated 'answer' rather than just a list of links, as it can be configured to process content and return a summarized response.
Example Prompts
- "Search for the latest benchmarks and release news for the top LLMs as of late 2026."
- "Research the current impact of climate change policies on global agriculture and summarize the top three findings."
- "Find up-to-date information on the current stock market status for technology companies today."
Tips & Limitations
To optimize performance, define your queries clearly. Use the 'advanced' search depth for complex research topics to get more thorough data, or 'basic' for quick, broad inquiries. Be mindful of your API plan limits, as excessive 'advanced' searches consume more quota. If you are scraping a specific URL rather than searching for information, prefer the web_fetch tool to save your search budget. Ensure your API key is properly masked in environment variables if working in shared or public environments.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-aysun168-tavily-skill-bak": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, external-api
Related Skills
skill-vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
web-access
所有联网操作必须通过此 skill 处理，包括：搜索、网页抓取、登录后操作、网络交互等。 触发场景：用户要求搜索信息、查看网页内容、访问需要登录的网站、操作网页界面、抓取社交媒体内容（小红书、微博、推特等）、读取动态渲染页面、以及任何需要真实浏览器环境的网络任务。
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when (1) a command, tool, API, or operation fails; (2) the user corrects you or rejects your work; (3) you realize your knowledge is outdated or incorrect; (4) you discover a better approach; (5) the user explicitly installs or references the skill for the current task.