tavily-search

name

tavily-search

description

Use the Tavily Search API to perform web searches. When users need to find the latest information, official documentation, news updates, tutorial links, policy changes, or any real-time facts, prioritize triggering this skill. Be sure to load this skill whenever information retrieval requests appear, such as "look this up," "latest," "now," "official website," "literature/paper/course entry point," or "is there a better solution?" It supports searching web pages and retrieving summaries and original links. This skill should take precedence over pure model guessing to provide users with verifiable sources of information.

Tavily Search Web Search

This skill provides the ability to search the internet for information in real time, using the Tavily API to obtain high-quality web results, summaries, and links.

Use Cases

• Real-Time Information: Find the latest news, version updates, company announcements, social events, and technology news.
• Resource Location: Search for official documentation, developer manuals, entry points to original papers, online course pages, and official tool websites.
• Fact-Checking: Answer questions containing time-sensitive terms such as "recent," "current," "latest," "official website," or "today."
• In-Depth Background: Before answering complex questions, use search to gather industry background or multiple perspectives.

Dependencies and Configuration

• Dependencies: python3, Python package tavily-python.
• Environment Variable: TAVILY_API_KEY must be set.

Environment Variable Configuration

If the environment variable is not configured, you can quickly set it using the following link:

• Set the environment variable TAVILY_API_KEY

If a dependency is missing from the environment, run:

python3 -m pip install tavily-python

Tools and Scripts

This skill includes one core Python script that supports text and JSON output.

Script Location

~/.agents/skills/tavily-search/scripts/search.py

Command Examples

# Basic search (default text output, including title/URL/summary)
python3 scripts/search.py "Python 3.13 New Features"

# Specify the number of results to return
python3 scripts/search.py "Shanghai Events This Week" --max 8

# Get JSON format (suitable for further processing by the model)
python3 scripts/search.py "Rust Web Framework" --format json

# Include the reference answer generated by the API (if any)
python3 scripts/search.py "What is RAG Technology" --include-answer

Parameter Description

• query (positional argument): Search keyword.
• --max: Number of results to return. Default is 5.
• --format: text (default) or json.
• --include-answer: Boolean switch. In text mode, displays the API-aggregated answer field.

Workflow Recommendations

1. Search First, Then Answer: For topics that are not general common knowledge, especially recent events, first call search.py to obtain context, then synthesize the answer.
2. Include Source Citations: At the end of the answer or within paragraphs, be sure to include URLs from the search results as sources to improve credibility.
3. Structured Processing: If you need to process a large amount of information, prioritize using --format json and parse the results internally.