Menu
AI-powered web search and content extraction
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Deep research with structured reports and charts. ONLY use when the user explicitly requests research/analysis, or needs data visualization with charts, or quantitative/comparative analysis across multiple sources. Do NOT use for simple questions or quick lookups.
Search the web and fetch content from URLs for current information, news, and research topics.
Web browser automation for tasks requiring UI interaction, login-protected pages, or human-like browsing when APIs are insufficient.
Autonomous coding agent. Delegate any task that involves understanding, writing, or running code โ from a GitHub issue, a bug report, or a user request. It explores, implements, and verifies on its own.
Create hand-drawn style diagrams and flowcharts using Excalidraw
Create, modify, and manage Excel spreadsheets.
| name | tavily-search |
| description | AI-powered web search and content extraction |
tavily_search(query, search_depth?, topic?): AI-powered web search that returns relevant, summarized results.
query (string, required): Search querysearch_depth (string, optional, default: "basic"): "basic" for quick lookups, "advanced" for comprehensive researchtopic (string, optional, default: "general"): "general", "news", or "research"tavily_extract(urls, extract_depth?): Extract clean, readable content from one or more web URLs.
urls (string, required): Comma-separated URLs to extract content fromextract_depth (string, optional, default: "basic"): "basic" or "advanced"tavily_search for research queries that benefit from AI-curated results.search_depth to "advanced" for comprehensive research, "basic" for quick lookups.topic to "news" for recent events, "research" for academic/technical topics.tavily_extract to get full page content from specific URLs found in search results.When presenting information from search results, wrap every specific claim in <cite> tags:
<cite source="SOURCE_TITLE" url="URL">claim text</cite>
Rules:
source attribute should contain the title or name of the source.url attribute should contain the source URL when available.