Programmatic web search with context isolation. Use this skill for any research task where you need to search the web, filter results, and extract specific information — without polluting your context window with raw HTML and boilerplate. This is the default skill for web research. Triggered by "search for", "look up", "find", "research", "what's the latest on", or any query that requires current web information. Also use when asked to "search and filter", "find the important parts", or "extract
The 'tavily-dynamic-search' skill allows users to search the web using Tavily's LLM-optimized search API. It simplifies the process of retrieving relevant web content without the need for coding, making it accessible to non-technical users. The search results are optimized for large language models (LLMs), ensuring that the content snippets, scores, and metadata are tailored to improve understanding and utility. This skill is ideal for anyone looking to quickly find web content on any topic, leveraging advanced search capabilities to get precise and relevant results.
Main features of the 'tavily-dynamic-search' skill include OAuth authentication for seamless integration, and the ability to customize search queries with parameters like time range, result count, domain filters, and more. The skill supports both basic and advanced search modes, offering flexibility for different search needs. It also allows users to include additional content like images or full page content in the search results, which can enhance the usefulness of the gathered information.
This skill is targeted at users who need quick, relevant web search results without coding, such as researchers, content creators, and developers. It’s perfect for people who want to integrate web search into their workflow or applications without dealing with the complexity of API integration. Additionally, its flexibility makes it suitable for various fields, including machine learning, software development, and academic research.
You can authenticate using OAuth, which will automatically open your browser for authentication if no existing tokens are found. Alternatively, you can use an API key by adding it to your settings.json file.
You can customize several parameters including 'query', 'max_results', 'search_depth', 'time_range', 'include_domains', and 'exclude_domains'. Additional options like 'include_images' and 'include_raw_content' are also available.
'search_depth' controls the level of detail and processing for your search. The available options are 'ultra-fast', 'fast', 'basic', and 'advanced', each offering different balances of speed, relevance, and content richness.
You can include up to 300 domains and exclude up to 150 domains in your search query.
Yes, an internet connection is required to access the Tavily search API and retrieve web results.
Quick Setup:
.claude/skills/Repository
tavily-ai/skills