tavily-search
Use Tavily Search API for optimized, real-time web search results for RAG. Requires TAVILY_API_KEY.
Best use case
tavily-search is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Use Tavily Search API for optimized, real-time web search results for RAG. Requires TAVILY_API_KEY.
Teams using tavily-search should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/tavily-search/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How tavily-search Compares
| Feature / Agent | tavily-search | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Use Tavily Search API for optimized, real-time web search results for RAG. Requires TAVILY_API_KEY.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Tavily Search Skill
This skill utilizes the Tavily Search API, providing clean, real-time web search results optimized for LLMs and RAG pipelines.
## Setup
1. **Dependencies:** Requires `tavily-python`.
```bash
pip install tavily-python python-dotenv
```
2. **API Key Configuration:** Requires `TAVILY_API_KEY`.
```bash
# If the script fails due to a missing key, run the following:
echo "It seems the Tavily API key is not set up."
read -p "Enter your Tavily API key: " TAVILY_KEY
echo "TAVILY_API_KEY=$TAVILY_KEY" >> .env
if [ -f .gitignore ] && ! grep -q ".env" .gitignore; then echo ".env" >> .gitignore; fi
echo "API key saved to .env."
```
## Usage
Use the `scripts/tavily_search.py` script.
### Command
```bash
python3 scripts/tavily_search.py --query "<query>" [--max-results <N>] [--search-depth <basic|advanced>]
```
### Parameters
* `--query` (Required): The search query.
* `--search-depth` (Optional): Default `basic`. Use `advanced` for intensive research (higher quality, slower).
* `--max-results` (Optional): Default 10.
### Example
```bash
python3 scripts/tavily_search.py --query "autonomous research agents comparison" --search-depth advanced
```
## Output
The script outputs JSON containing a synthesized `answer` (if requested by the script) and a list of `results` (URL, title, content snippets).Related Skills
openai-deep-research
Use OpenAI's Deep Research API (o3 / o4 models) to automate multi-step, citation-backed research workflows.
langchain-deep-research
Run LangChain Open Deep Research agent for iterative web research and comprehensive reports. Requires LLM API keys and search API (e.g., OPENAI_API_KEY, TAVILY_API_KEY).
gpt-researcher
Run the GPT Researcher autonomous agent to generate comprehensive deep research reports. Requires LLM and Search API keys (e.g., OPENAI_API_KEY, TAVILY_API_KEY).
exa-research
Use Exa AI for neural search, content retrieval, and automated deep research. Requires EXA_API_KEY.
xai-grok
Use xAI Grok API with Agent Tools for real-time web and X (Twitter) search and synthesis. Requires XAI_API_KEY.
stanford-storm
Run Stanford STORM (knowledge-storm) to generate comprehensive, Wikipedia-style articles with citations. Requires LLM and Search API keys (Bing or You.com).
smolagents
Use Hugging Face Smolagents framework for code-based agentic research with tool support. Supports multiple LLM providers and web search.
perplexity-sonar
Use Perplexity Sonar API for real-time, citation-backed answers. Ideal for up-to-date information and quick synthesis. Requires PERPLEXITY_API_KEY
jina-ai
Use Jina AI APIs for converting URLs to LLM-friendly Markdown (Reader) and searching the web (Search).
search-first
Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Systematizes the "search for existing solutions before implementing" approach. Use when starting new features or adding functionality.
market-research
Conduct market research, competitive analysis, investor due diligence, and industry intelligence with source attribution and decision-oriented summaries. Use when the user wants market sizing, competitor comparisons, fund research, technology scans, or research that informs business decisions.
exa-search
Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.