tavily-usage
npx machina-cli add skill fcakyon/claude-codex-settings/tavily-usage --openclawTavily 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
- Use
mcp__tavily__tavily_searchfor discovery phase - Analyze results to find relevant URLs
- Use
mcp__tavily__tavily-extractfor detailed content on specific URLs - 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
Source
git clone https://github.com/fcakyon/claude-codex-settings/blob/main/plugins/tavily-tools/skills/tavily-usage/SKILL.mdView on GitHub Overview
Tavily provides two MCP tools for web search and content retrieval: Tavily Search for discovering pages and Tavily Extract for pulling detailed content from URLs. This workflow helps you quickly map sources, fetch targeted content, and build reliable web-sourcing outputs.
How This Skill Works
Use Tavily Search (mcp__tavily__tavily_search) to discover relevant pages based on keywords. Analyze the results to pick promising URLs, then apply Tavily Extract (mcp__tavily__tavily-extract) to fetch and analyze detailed content from those pages. The tavily_extract_to_advanced.py hook upgrades extract calls to advanced mode for higher accuracy when needed.
When to Use It
- You need to perform a keyword-based web search to identify sources for a topic.
- You want to fetch content from a specific URL for analysis.
- You need to extract structured data or metadata from pages.
- You want to follow up search results with in-depth content extraction.
- You're validating information across multiple pages and need consolidated sources.
Quick Start
- Step 1: Use Tavily Search (mcp__tavily__tavily_search) to discover relevant pages.
- Step 2: Review results and select promising URLs.
- Step 3: Use Tavily Extract (mcp__tavily__tavily-extract) to fetch detailed content from the chosen URLs and process it for your needs.
Best Practices
- Start with Tavily Search to map the landscape before diving into pages.
- Analyze search results to select the most relevant URLs.
- Use Tavily Extract only on URLs likely to contain the needed details.
- Leverage advanced mode for high-precision extraction when needed.
- Cache or store extracted content to minimize repeated requests and costs.
Example Use Cases
- Research a topic by performing a broad web search and listing sources.
- Retrieve the full article text from a URL for summarization.
- Extract product specifications from a retailer page.
- Pull contact information or metadata from a corporate page.
- Cross-check facts by comparing content from multiple pages.
