Advanced web search, content extraction, and site mapping through Tavily via SandBase. Use when asked for web research, URL content extraction, full article reading, news search, or site structure discovery.
npx skills add https://github.com/sandbaseai/sandbase-skills --skill tavily-deep-research
Advanced web search and content extraction through SandBase's Tavily integration. Search the web with depth control, extract clean content from URLs, and discover site structures. Read the API map before selecting a capability.
For every selected tool, call sandbase_describe_tool first and use only arguments in its current input schema. Then call sandbase_call_tool with the exact tool_name.
Use tavily_search with parameters:
search_depth: "basic" for quick validation, "advanced" for thorough researchtopic: "general", "news", or "finance" to focus resultsdays: limit to recent results (e.g., 7 for past week)max_results: 5-20 depending on coverage needsinclude_domains / exclude_domains: filter by sourceUse tavily_extract to get clean, readable content from specific URLs.
Use tavily_map to discover all pages on a website.
Return: search results with source URLs, extracted content summaries, site maps when relevant, and confidence indicators.
Take sandbaseai/tavily-deep-research from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.