skills.rest
flemx
flemxCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

tavily-cli

Performs web search, content extraction, crawling, and research via the Tavily CLI.

Updated Jul 16, 2026
Search Tags:#cli#web search#web crawling#content extraction#deep research#tavily#url discovery
One-click install
npx skills add https://github.com/flemx/salesforce-langgraph-agent --skill tavily-cli-flemx
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: tavily-cli
Source: https://github.com/flemx/salesforce-langgraph-agent/tree/main/.agents/skills/tavily-cli
Command: npx skills add https://github.com/flemx/salesforce-langgraph-agent --skill tavily-cli-flemx

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires tavily-cli.

What problem does it solve? Agents lack native access to live web data, making it hard to search the internet, pull content from URLs, crawl documentation sites, or produce cited research. This Skill bridges that gap by exposing the Tavily CLI's LLM-optimized web capabilities through simple terminal commands. ## Core Features & Use Cases - Web Search: Run tvly search to find pages, answer questions, and discover sources on any topic, with JSON output for agentic workflows. - Content Extraction & Crawling: Use tvly extract for single URLs, tvly map to discover URLs on a domain, and tvly crawl to bulk-download entire site sections like documentation. - Deep Research: Use tvly research for multi-source synthesis with citations. - Use Case: A user asks to gather all pages from a vendor's docs site and summarize them. The agent runs tvly crawl "https://docs.example.com" --output-dir ./docs/, then reads the saved Markdown files to produce the summary. ## Quick Start Ask the agent to search the web for a topic or extract the content of a specific URL, for example: "Search the web for the latest LangGraph release notes and summarize the top results."

Frequently Asked Questions about tavily-cli

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

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

Run tvly search followed by your quoted query, for example tvly search "react hooks" --json. The command returns LLM-optimized results, and you can save them to a file with the -o flag.

How to extract text content from a webpage URL?▼

Use tvly extract with the quoted URL, such as tvly extract "https://example.com/docs" -o docs.md. Always quote URLs because shells interpret ? and & as special characters.

What is the difference between tvly map, crawl, and extract?▼

tvly extract pulls content from one known URL, tvly map discovers URLs across a domain to locate the right page, and tvly crawl bulk-downloads many pages from an entire site section such as all of /docs/.

Does Tavily CLI require an API key?▼

Yes, Tavily CLI requires authentication via a Tavily API key from tavily.com. Authenticate with tvly login --api-key tvly-YOUR_KEY, set the TAVILY_API_KEY environment variable, or use browser-based OAuth via tvly login.

Why does tvly return exit code 3 or 4?▼

Exit code 3 indicates an authentication error, meaning the API key is missing or invalid. Exit code 4 indicates a Tavily API error, while exit code 2 signals bad input and 0 means success.

Related Skills

Explore More Education & Research Skills→
HuynhSang2005HuynhSang2005

tavily-extract

Extract clean markdown or text from URLs using the Tavily CLI.

Community
Intermediate
stevessrstevessr

crawl

Crawl websites and save pages as markdown files using the Tavily API.

Community
Intermediate
huangkikihuangkiki
1.1k

daily-papers

Automate discovery, analysis, and organization of academic papers with Claude Code and Obsidian.

Community
Advanced
caoqiubozhangchenqin2caoqiubozhangchenqin2

web-browsing

Fetch and parse web pages using requests and BeautifulSoup.

Community
Intermediate