web-search-tavily
Web-search-tavily delivers AI-driven search and research through multiple specialized endpoints: execute targeted queries with configurable depth and relevance tuning, extract and parse content from specific URLs, crawl entire websites as graphs, or launch comprehensive research tasks that synthesize multiple sources into detailed reports. Choose between fast, balanced, or advanced search modes depending on your latency and precision needs.
Web-search-tavily performs comprehensive web searches with AI-powered relevance ranking and multi-source research synthesis.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-23
Web-search-tavily performs comprehensive web searches with AI-powered relevance ranking and multi-source research synthesis. Web-search-tavily delivers AI-driven search and research through multiple specialized endpoints: execute targeted queries with configurable depth and relevance tuning, extract and parse content from specific URLs, crawl entire websites as graphs, or launch comprehensive research tasks that synthesize multiple sources into detailed reports. Choose between fast, balanced, or advanced search modes depending on your latency and precision needs.
Use it when
- Web-search-tavily supports multiple research workflows.
- Yes.
Verify before relying
Read SKILL.md below before installing (2 files). Open directory: indexed for reading, not audited.
Install
gooseworks-ai/goose-skills/web-search-tavily · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What is web-search-tavily and what can it do?
Web-search-tavily delivers AI-driven search and research through multiple specialized endpoints: execute targeted queries with configurable depth and relevance tuning, extract and parse content from specific URLs, crawl entire websites as graphs, or launch comprehensive research tasks that synthesize multiple sources into detailed reports. Choose between fast, balanced, or advanced search modes depending on your latency and precision needs.
How do I use tavily for research tasks?
Web-search-tavily supports multiple research workflows. You can perform comprehensive web searches with AI-powered relevance ranking, extract and parse content from multiple URLs at scale, crawl and map website structures for documentation or discovery, or conduct automated multi-source research with structured output. Each approach integrates into agent workflows for seamless automation.
Can web-search-tavily extract webpage content?
Yes. Web-search-tavily includes content extraction capabilities that let you parse and extract data from specific URLs at scale. Combined with its crawling features, you can map entire website structures and extract content systematically across multiple pages and sources for comprehensive research and documentation purposes.
What search modes does web-search-tavily offer?
Web-search-tavily provides three configurable search modes: fast mode for quick results with lower latency, balanced mode for standard research needs, and advanced mode for precision-focused queries. You can tune relevance and depth settings based on your specific requirements, whether you need rapid answers or exhaustive multi-source synthesis.
How does web-search-tavily integrate into agent workflows?
Web-search-tavily's AI search capabilities integrate directly into agent workflows, enabling automated research pipelines. Agents can execute targeted queries, extract structured data from URLs, crawl website graphs, and synthesize findings across sources—all with configurable depth and relevance tuning for autonomous research and discovery tasks.
What license does web-search-tavily use?
Web-search-tavily is released under the MIT license, allowing free use, modification, and distribution in both open-source and commercial projects with minimal restrictions.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Tavily - AI Search & Research API
Setup
Read your credentials from ~/.gooseworks/credentials.json:
export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])")
export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))")
If ~/.gooseworks/credentials.json does not exist, tell the user to run: npx gooseworks login
All endpoints use Bearer auth: -H "Authorization: Bearer $GOOSEWORKS_API_KEY"
Comprehensive web search, crawling, content extraction, and deep research.
Capabilities
- Tavily Search: Execute a search query using Tavily Search
- Get Research Task Status: Retrieve the status and results of a research task using its request ID (free)
- Create Research Task: Tavily Research performs comprehensive research on a given topic by conducting multiple searches, analyzing sources, and generating a detailed research report
- Tavily Extract: Extract
(truncated - see the full file via the links below)
File tree — 2 files
skills/research-tools/capabilities/web-search-tavily/SKILL.md
skills/research-tools/capabilities/web-search-tavily/skill.meta.json
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Perform comprehensive web searches with AI-powered relevance ranking”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Tavily wraps the Tavily REST API to enable web search, content extraction, site discovery, and crawling directly from your agent. It returns structured results with titles, URLs, and summaries designed for downstream LLM use, and supports optional research workflows with citations when deeper investigation is needed.
web-scraping-olostep provides API endpoints to scrape pages, crawl websites, and extract structured answers from web content. Use it to initiate scrapes with custom formatting, perform AI-driven searches across multiple pages, map site URLs, or batch-process large crawls with filtering and depth controls.
SEO Analyzer maps site structure, extracts page content, and identifies backlink opportunities to evaluate SEO performance. It examines keywords, content quality, and competitor positioning across your website. Use it to prioritize optimization efforts and track ranking improvements over time.
Tavily is an AI-optimized search engine built for language model applications that need current web data. It provides web search, URL content extraction, site crawling, and autonomous research capabilities—all designed to return results formatted for LLM consumption rather than human browsing.
Web-scraping lets you pull structured data from any URL using plain English descriptions of what you need. Choose from AI-powered extraction with natural language prompts, high-volume batch processing, or schema-based data structuring—then combine methods for comprehensive site crawling and automation.
web-search-exa provides neural search powered by embeddings to discover relevant web content, extract full page text, and synthesize findings. Query the web intelligently across multiple search modes, filter by domain or date, and get LLM-generated answers informed by live search results.
More skills extract-webpage-data (MIT) · tavily-search (MIT) · Tavily Crawl (unlicensed) · tavily-web (MIT) · Tavily Search (unlicensed) · tiktok-search (MIT) · Tavily Extract (unlicensed) · Web Search Plus (MIT)