Performs web search and URL content extraction using the Tavily API.
npx skills add https://github.com/JEROME-PRAKASH-L/openclaw --skill tavily-jerome-prakash-l
Please help me install this Agent Skill. Skill: tavily Source: https://github.com/JEROME-PRAKASH-L/openclaw/tree/main/extensions/tavily/skills/tavily Command: npx skills add https://github.com/JEROME-PRAKASH-L/openclaw --skill tavily-jerome-prakash-l
web_search or fine-grained searches with tavily_search using depth, topic, domain, and time-range filters. - Content Extraction: Pull clean markdown from up to 20 URLs per request with tavily_extract, including JavaScript-rendered pages and query-focused chunking. - Use Case: Research a breaking news topic by running tavily_search with the news topic and a week time range, then extract full article content from the top URLs for a summarized briefing. ## Quick Start Use the tavily skill to search for the latest news on renewable energy policy and extract the content of the top three result URLs.High-intent search queries and answers about installing and using this skill.
Use web_search for straightforward queries with just a query string and result count. For more control, use tavily_search with parameters like search_depth, topic, time_range, and domain filters.
Use tavily_extract with an array of up to 20 URLs. Start with basic extract depth and switch to advanced for JavaScript-rendered pages, tables, or dynamic content.
web_search handles basic queries with no special options, while tavily_search adds depth control, topic selection (general, news, finance), domain filters, time ranges, and optional AI-generated answer summaries.
Use basic depth for general-purpose queries since it is faster with high relevance. Use advanced depth when you need the highest relevance for precision tasks, specific facts, or detailed research, accepting slower response times.
Each tavily_extract request accepts a maximum of 20 URLs, so larger lists must be batched into multiple calls. Queries for tavily_search should stay under 400 characters for best results.
danny0926Define research scope with hypotheses, bias checks, and prior art references.
thirteen37Execute search queries, fetch article content, and synthesize findings into structured summaries.
moonshineTPVerify paper citations by cross-referencing title, author, venue, year, and URL.
roach88Crawl static and JavaScript-rendered websites and extract structured data.