skills.rest
AmirulAndalib
AmirulAndalibCOMMUNITY
Explore all skills by this author →
GitHub

tavily

Performs web search and URL content extraction using the Tavily API.

Updated Jun 19, 2026
Search Tags:#markdown#research#web search#content extraction#tavily#url scraping#news search
One-click install
npx skills add https://github.com/AmirulAndalib/Vilvona-AI --skill tavily-amirulandalib
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: tavily
Source: https://github.com/AmirulAndalib/Vilvona-AI/tree/main/extensions/tavily/skills/tavily
Command: npx skills add https://github.com/AmirulAndalib/Vilvona-AI --skill tavily-amirulandalib

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Finding current information on the web and pulling clean content out of specific pages requires juggling search queries, result filtering, and page scraping. This Skill provides a structured way to run web searches with fine-grained controls and extract readable markdown content from URLs, including JavaScript-rendered pages. ## Core Features & Use Cases - Web Search with Controls: Run searches with depth levels (basic or advanced), topic filters (general, news, finance), time ranges, domain allow/block lists, and optional AI-generated answer summaries. - URL Content Extraction: Extract clean markdown from up to 20 URLs per request, with query-based chunk reranking to return only relevant sections and an advanced mode for JS-heavy pages and tables. - Escalation Workflow: Follow a simple-to-advanced pattern: quick lookup with web_search, controlled search with tavily_search, then full content retrieval with tavily_extract. - Use Case: Research a breaking news topic by running tavily_search with topic set to news and a week time range, then feed the top URLs into tavily_extract with a query to pull only the relevant passages. ## 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.

Frequently Asked Questions about tavily

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I search the web with Tavily?▼

Use web_search for straightforward queries with just a query string and result count. Use tavily_search when you need control over search depth, topic, time range, domain filters, or an AI-generated answer summary.

How do I extract content from a URL with Tavily?▼

Call tavily_extract with an array of up to 20 URLs. It returns clean markdown and handles JavaScript-rendered pages. Add a query parameter with chunks_per_source to get only the sections relevant to your topic.

What is the difference between basic and advanced search depth in Tavily?▼

Basic depth is faster and suited for general-purpose queries, while advanced depth is slower but delivers the highest relevance. Use advanced for precision tasks, specific facts, and detailed research.

Can Tavily extract content from JavaScript-rendered pages?▼

Yes, tavily_extract handles JavaScript-rendered pages. Start with basic extract depth, and switch to advanced for JS-heavy single-page apps, dynamic content, tables, or embedded elements if content is missing.

What are the limits of Tavily search queries and extraction?▼

Search queries should stay under 400 characters, and tavily_search returns 1-20 results per call. tavily_extract accepts a maximum of 20 URLs per request, so batch larger lists into multiple calls.

Related Skills

Explore More Education & Research Skills→
remiverdiesenremiverdiesen
6

issue-creation

Drafts GitHub bug/feature issues after clarifying questions, research, duplicate/dependency checks, and user approval.

Community
Advanced
ARAVINDAN20ARAVINDAN20
4

parallel-web

Search the web and extract URL content via Parallel Web Systems APIs.

Community
Advanced
ibleaiblea
4

integrity

Cross-reference external files, reports, links, and search results to verify factual accuracy.

Community
Intermediate
sanjanbsanjanb
1

setup-browser-cookies

Import cookies from a real Chromium browser into a headless Playwright browse session.

Community
Intermediate