Skip to main content
skill CX Codex

tavily-usage — Claude Code skill: what it does, how to install

Guides coding agents to run web searches and extract page content via Tavily MCP tools. Requires a Tavily API key.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add fcakyon/claude-codex-settings --skill tavily-usage -a claude-code
Open on GitHub

What tavily-usage does

The skill orchestrates two MCP tools: mcp__tavily__tavily_search for keyword discovery and mcp__tavily__tavily-extract for page inspection. The agent queries the web, collects relevant links, and extracts deep content from target pages.

It includes a tavily_extract_to_advanced.py hook. This script switches extraction calls into advanced mode when higher precision is needed. You must configure the TAVILY_API_KEY environment variable in your shell beforehand.

Search calls consume fewer credits than deep extraction. Following this workflow prevents running expensive extraction calls on irrelevant URLs.

What it helps with

  • run keyword searches across the web for recent documentation
  • extract structured page contents from specific links
  • cut API costs by filtering candidate links before deep extraction

Example prompts for the agent

  • Search the web for recent changes in this package
  • Extract page content from this specific link
  • Use Tavily search to find articles on this error

How to install tavily-usage

1Skills CLI (Vercel)

npx skills add fcakyon/claude-codex-settings --skill tavily-usage -a claude-code

2Manually: put the files in place

~/.claude/skills/tavily-usage/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/tavily-usage/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about tavily-usage

How to install tavily-usage in Claude Code?

Run npx skills add fcakyon/claude-codex-settings --skill tavily-usage -a claude-code. This copies the skill files directly into your configuration directory.

What does tavily-usage do?

It provides an integration workflow for web search and scraping through Tavily MCP tools. The model first queries keywords and then extracts detailed content only from relevant URLs.

What prerequisites does tavily-usage require?

You need a working TAVILY_API_KEY exported in your environment. The MCP server relies on this key to authenticate requests.

Source text

SKILL.md · Apache-2.0
---
name: tavily-usage
description: This skill should be used when user asks to "search the web", "fetch content from URL", "extract page content", "use Tavily search", "scrape this website", "get information from this link", or "web search for X".
---

# Tavily Search and Extract

Use Tavily MCP tools for web search and content retrieval operations.

## Tool Selection

### Tavily Search (`mcp__tavily__tavily_search`)

Use for:

- Keyword-based searches across the web
- Finding relevant pages and content
- Quick answer gathering
- Multiple result discovery

**Best for**: Initial research, finding sources, broad queries

### Tavily Extract (`mcp__tavily__tavily-extract`)

Use for:

- Getting detailed content from specific URLs
- Deep analysis of page content
- Structured data extraction
- Following up on search results

**Best for**: In-depth analysis, specific URL content, detailed information

## Hook Behavior

`tavily_extract_to_advanced.py` hook automatically upgrades extract calls to advanced mode for better accuracy when needed.

## Integration Pattern

1. Use `mcp__tavily__tavily_search` for discovery phase
2. Analyze results to find relevant URLs
3. Use `mcp__tavily__tavily-extract` for detailed content on specific URLs
4. Process extracted content for user needs

## Environment Variables

Tavily MCP requires:

- `TAVILY_API_KEY` - API key from Tavily (tvly-...)

Configure in shell before using the plugin.

## Cost Considerations

- Search is cheaper than extract
- Use search to filter relevant URLs first
- Only extract URLs that are likely relevant
- Cache results when possible

© fcakyon · Apache-2.0 · fcakyon/claude-codex-settings

Similar skills

All skills for Agent setup: memory, context, orchestration →

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor