playbooks

home / skills / fcakyon / claude-codex-settings / tavily-usage

tavily-usage skill

/plugins/tavily-tools/skills/tavily-usage

This skill helps you search the web and extract detailed page content using Tavily tools for initial discovery and in-depth analysis.

npx playbooks add skill fcakyon/claude-codex-settings --skill tavily-usage

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
1.6 KB
---
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

Overview

This skill provides a clear, battle-tested pattern for using Tavily MCP tools to search the web and extract page content. It guides selection between lightweight keyword search and deeper URL extraction, helping get accurate source material while controlling cost. The skill is designed for Python-based agents and integrates an automatic hook that upgrades extraction to advanced mode when needed.

How this skill works

Start with the Tavily search tool to run keyword queries and retrieve multiple candidate pages. Inspect those search results and pick likely targets, then call the Tavily extract tool to pull full page content or structured data from specific URLs. An extraction hook will automatically enable advanced extraction for better accuracy on complex pages. Cache and post-process extracted content to satisfy user requests (summaries, analysis, or data transforms).

When to use it

  • User asks to search the web or fetch content from a URL
  • You need to discover sources for research or quick answers
  • You want structured data or full-text from specific webpages
  • When cost matters and you want to minimize heavy extractions
  • When you need reliable, repeatable web content retrieval in an agent workflow

Best practices

  • Use Tavily search for broad discovery and to narrow down relevant URLs before extracting
  • Only call extract on URLs that passed initial relevance checks to control cost
  • Enable the extraction hook to upgrade to advanced mode for pages with dynamic or complex structure
  • Cache search and extraction results when possible to avoid repeated API calls
  • Post-process extracted content (cleaning, dedupe, summarization) before delivering to users

Example use cases

  • Find authoritative articles and extract key sections for a research summary
  • Search for product pages and extract structured specs for a comparison table
  • Fetch blog posts or documentation pages and produce a concise summary
  • Scrape public data tables from a URL and convert into CSV or JSON
  • Follow up on a broad query by extracting the best candidate pages for detailed analysis

FAQ

What environment setup is required?

Set TAVILY_API_KEY in your shell to an active Tavily API key before using the tools.

When should I prefer search over extract?

Use search for discovery and broad queries; reserve extract for specific URLs you’ve verified as relevant to reduce cost and improve speed.