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...
数据来源:ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一:命令行安装(推荐)
推荐(无需提前安装 clawhub)
npx clawhub@latest --dir ~/.claude/skills install tavily-skill或使用 clawhub CLI(需提前安装)
clawhub --dir ~/.claude/skills install tavily-skill⚠️ 需要 Node.js 18+,没有 Node?请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二:手动下载安装(无需 Node)
下载 ZIP,解压后将文件夹放到以下路径,重启 Agent 即可:
安装路径
~/.claude/skills/tavily-skill/💡解压后将文件夹放到上方路径,重启 Agent 即可生效
--- name: tavily-search description: "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." homepage: https://tavily.com metadata: { "openclaw": { "emoji": "🔍", "requires": { "bins": ["curl", "jq"] } } } ---
Use Tavily API for real-time web search and content extraction.
✅ USE this skill when:
❌ DON'T use this skill when:
web_fetch toolweb_fetch for specific URLsSet your Tavily API key in one of these ways:
export TAVILY_API_KEY="your-api-key-here"
Add to your openclaw.json:
{
"tavily": {
"apiKey": "your-api-key-here"
}
}
# Search for a topic
curl -X POST "https://api.tavily.com/search" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $TAVILY_API_KEY" \
-d '{
"query": "latest AI developments 2026",
"search_depth": "basic",
"max_results": 5
}' | jq .
# Get detailed research results
curl -X POST "https://api.tavily.com/search" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $TAVILY_API_KEY" \
-d '{
"query": "climate change impact on agriculture 2026",
"search_depth": "advanced",
"max_results": 10,
"include_answer": true,
"include_images": false
}' | jq .
# Search for recent news
curl -X POST "https://api.tavily.com/search" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $TAVILY_API_KEY" \
-d '{
"query": "technology news today",
"search_depth": "basic",
"max_results": 5,
"include_raw_content": false
}' | jq .
query: Search query string (required)search_depth: "basic" or "advanced" (default: "basic")max_results: Number of results (1-10, default: 5)include_answer: Include AI-generated answer (true/false)include_images: Include image URLs (true/false)include_raw_content: Include full page content (true/false)echo $TAVILY_API_KEYIf Tavily API is not available:
web_fetch for specific URLsweb_search with Kimi API (if configured)browser tool安装 Tavily Skill 后,可以对 AI 说这些话来触发它
Help me get started with Tavily Skill
Explains what Tavily Skill does, walks through the setup, and runs a quick demo based on your current project
Use Tavily Skill to use Tavily API for real-time web search and content extraction
Invokes Tavily Skill with the right parameters and returns the result directly in the conversation
What can I do with Tavily Skill in my data & analytics workflow?
Lists the top use cases for Tavily Skill, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/tavily-skill/ 目录(个人级,所有项目可用),或 .claude/skills/tavily-skill/(项目级)。重启 AI 客户端后,用 /tavily-skill 主动调用,或让 AI 根据上下文自动发现并使用。
Tavily Skill 支持 Claude、Cursor、OpenClaw,可与这些 AI 平台无缝集成,扩展其能力。
Tavily Skill 可免费安装使用。请查阅仓库了解许可证信息。
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...
Tavily Skill 属于「Data & Analytics」分类,该分类的技能帮助 AI 智能体在此领域执行专业任务。
Automate my data & analytics tasks using Tavily Skill
Identifies repetitive steps in your workflow and sets up Tavily Skill to handle them automatically