tavily-search
Tavily Search queries the entire web and returns ranked results with relevance scores and optional AI-generated answers in one call. Unlike single-URL fetching, it powers research workflows, competitive analysis, and "what's the latest" questions with configurable search depth, time ranges, and content extraction across multiple pages.
Tavily Search lets you query the web and receive AI-generated answers with ranked, scored results in a single API call.
AI-generated summary based on this skill's SKILL.md
Install
xg-gh-25/SwarmAI/s_tavily-search · repository language: Python
git clone https://github.com/xg-gh-25/SwarmAI
cp -r SwarmAI/backend/skills/s_tavily-search ~/.claude/skills/s_tavily-searchFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What does tavily-search do?
Tavily Search queries the entire web and returns ranked results with relevance scores and optional AI-generated answers in one call. Unlike single-URL fetching, it powers research workflows, competitive analysis, and "what's the latest" questions with configurable search depth, time ranges, and content extraction across multiple pages.
Can tavily-search extract content from multiple URLs?
Yes. Tavily Search supports batch extraction of full content from multiple URLs, enabling workflows that need to gather and process information across several web pages in a single operation rather than fetching them one at a time.
How do I search the web for latest AI news using tavily-search?
Tavily Search lets you query for the latest AI news by specifying your topic and configurable time ranges. The skill returns ranked results with relevance scores and can optionally generate AI-powered answers, helping you stay current on breaking developments.
Does tavily-search support region-specific or domain-filtered searches?
Yes. Tavily Search offers research capabilities with region-specific and domain-filtered search options, allowing you to narrow results by geography or restrict searches to particular websites when you need targeted information.
What is tavily-search licensed under?
Tavily Search is licensed under the MIT license, making it freely available for use, modification, and distribution in both open-source and commercial projects.
Can other skills use tavily-search for web search?
Yes. Tavily Search is designed to power other skills with web search and content retrieval capabilities, enabling downstream applications to access ranked web results and extracted content as part of their workflows.
SKILL.md
rendered from the published skill — quoted content, verbatim
Tavily Search
Why? WebFetch can only grab a single known URL. Tavily searches the entire web, returns ranked results with relevance scores, and can generate AI-powered answers -- all in one API call. Essential for answering "what's the latest on X?" or powering research workflows.
Quick Start
"Search the web for latest AI agent frameworks"
"What's the latest news about OpenAI?"
"Extract the main content from these 5 URLs"
Setup
Requires TAVILY_API_KEY environment variable.
# Check if set
echo $TAVILY_API_KEY
# If not, set it (get key from https://app.tavily.com)
export TAVILY_API_KEY=tvly-your-key-here
Free tier: 1,000 API credits/month. Basic search = 1 credit. Advanced search = 2 credits.
API Reference
Search
POST https://api.tavily.com/search
```bash curl -s -X POST https://api.tavily.com/search \
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 1 file
backend/skills/s_tavily-search/SKILL.md