tavily-web
Tavily Web integrates the Tavily API to handle multiple research workflows: search the web for current information, extract and summarize content from specific URLs, crawl sites to discover page structure, and generate structured research output. Route requests to the appropriate endpoint based on user intent—search for latest sources, extract for URL content, crawl for site traversal, map for page discovery, or research for schema-driven results.
Tavily Web searches the internet for current information and extracts content from URLs using the Tavily API.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-04-21
Tavily Web searches the internet for current information and extracts content from URLs using the Tavily API. Tavily Web integrates the Tavily API to handle multiple research workflows: search the web for current information, extract and summarize content from specific URLs, crawl sites to discover page structure, and generate structured research output. Route requests to the appropriate endpoint based on user intent—search for latest sources, extract for URL content, crawl for site traversal, map for page discovery, or research for schema-driven results.
Use it when
- Yes, Tavily Web can extract and summarize content from specific URLs.
- Tavily Web can crawl and map website structure to discover pages matching your criteria.
Verify before relying
Read SKILL.md below before installing (5 files). Open directory: indexed for reading, not audited.
Install
BenedictKing/tavily-web/tavily-web · repository language: JavaScript
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
How to search the web using tavily api?
Tavily Web uses the Tavily API to search the web and discover relevant sources. The skill routes your search query to Tavily's search endpoint, which returns the latest information and sources matching your request. This is ideal when you need current web results and want to identify authoritative pages on your topic.
Can Tavily Web extract content from url?
Yes, Tavily Web can extract and summarize content from specific URLs. Use the extract intent to pull text, structured data, and key information from a webpage. The skill processes the URL and returns a summary of the page content, making it easy to gather information without manually reading full pages.
What does Tavily Web crawl website mapping do?
Tavily Web can crawl and map website structure to discover pages matching your criteria. This crawl capability lets you traverse site hierarchies, identify linked pages, and understand how content is organized. It's useful for comprehensive site research and finding all relevant pages within a domain.
Does Tavily Web generate structured research output?
Tavily Web supports generating structured research output with custom schema. The research intent allows you to define how results should be formatted and organized, enabling you to get data in a consistent, machine-readable structure tailored to your specific needs.
What are the main use cases for Tavily Web?
Tavily Web handles five primary workflows: searching for latest information and sources, extracting and summarizing URL content, crawling sites to map structure, generating structured research output, and traversing websites to scrape page content. Route your request based on whether you need web search, URL extraction, site mapping, schema-driven results, or page traversal.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Tavily Web Skill
Trigger Conditions & Endpoint Selection
Choose Tavily endpoint based on user intent:
- search: Need to "search web / latest info / find sources / find links"
- extract: Given URL(s), need to extract/summarize content
- crawl: Need to traverse site following instructions and scrape page content
- map: Need to discover site page list/structure (without full content or metadata only)
- research: Need structured research output following given
output_schema
Recommended Architecture (Main Skill + Sub-skill)
This skill uses a two-phase architecture:
- Main skill (current context): Understand user question → Choose endpoint → Assemble JSON payload
- Sub-skill (fork context): Only responsible
(truncated - see the full file via the links below)
File tree — 5 files
.claude/skills/tavily-web/.env.example
.claude/skills/tavily-web/.gitignore
.claude/skills/tavily-web/SKILL.md
.claude/skills/tavily-web/tavily-api.cjs
.claude/skills/tavily-web/tavily-fetcher.md
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 › “Search the web for latest information and discover relevant sources”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
This skill leverages the Firecrawl API to pull content from web pages in multiple formats—markdown, HTML, JSON, screenshots, and PDFs. It supports single-page scraping, full-site crawling with depth and path controls, batch processing of multiple URLs, and browser automation through actions like clicks and scrolls. Use it whenever you need to gather web data, extract structured information with custom schemas, or interact with dynamic pages.
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.
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.
Tavily Crawl downloads website content across multiple pages and saves it as markdown files for agent workflows, knowledge base backup, or offline study. Configure crawl depth, path filters, and semantic instructions to target specific sections. Supports both full-page archival and context-optimized chunking for LLM integration.
Exa Search performs semantic web search and content discovery through embeddings, supporting multiple query types including similarity matching, category-specific searches, and structured research output. Route queries to the appropriate endpoint—search for general topics, findsimilar for related pages, contents for full text extraction, answer for direct responses, or research for formatted findings.
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.
More skills tavily-research (MIT) · Tavily (NOASSERTION) · tavily-best-practices (MIT) · tavily-best-practices (MIT)