tavily-best-practices
This skill provides documentation and implementation patterns for the Tavily search API. It guides developers on using search, extraction, crawling, and research methods within agentic workflows and RAG systems.
Is tavily-best-practices safe to install?
Safe to install: our audit of tavily-best-practices's source files found 2 shell commands, 0 external URLs, no file writes (low risk). Every command and URL listed appears verbatim in the skill's source. The skill provides documentation and code snippets for API integration. It does not execute network requests or file operations itself, but it instructs users to install packages and implement code that interacts with the Tavily API.
How we audit skills: our security review methodology.
Who is this skill for?
Developers building AI agents or RAG systems who need to integrate real-time web search and content extraction capabilities.
What can you do with it?
- Performing web searches with advanced depth settings
- Extracting content from specific URLs
- Crawling entire websites for data collection
- Discovering URLs from a site using map functionality
- Generating AI-powered research reports
How good is this skill?
Quality score: 5/10. The skill provides clear, structured documentation for the Tavily API. It includes code examples for all primary methods and references specific documentation files for deeper technical details.
What does the skill file contain?
# Tavily Tavily is a search API designed for LLMs, enabling AI applications to access real-time web data. ## Installation **Python:** ```bash pip install tavily-python ``` **JavaScript:** ```bash npm install @tavily/core ``` See **[references/sdk.md](references/sdk.md)** for complete SDK reference. ## Client Initialization ```python from tavily import TavilyClient # Uses TAVILY_API_KEY env var (recommended) client = TavilyClient() #With project tracking (for usage organization) client = TavilyClient(project_id="your-project-id") # Async client for parallel queries from tavily import ...
Frequently asked questions
What methods does the Tavily client support?
The client supports search, extract, crawl, map, and research methods.
How do I handle research tasks that take time to complete?
The research method returns a request_id, which you use to poll the get_research endpoint until the status reaches completed or failed.
Does the skill support asynchronous operations?
Yes, the skill documentation references an AsyncTavilyClient for parallel queries.
Related skills
azure-ai
429.4KDevelopers and AI agents requiring integration with Azure AI services for search, transcription, and synthesis tasks
The azure-ai skill provides tools for interacting with Azure AI services, including AI Search, Speech, OpenAI, and Document Intelligence. It supports search operations, speech-to-text, text-to-speech, and OCR through an MCP server interface.
microsoft-foundry
429.2KDevelopers building, deploying, and managing AI agents on Azure AI Foundry
The Microsoft Foundry skill provides a framework for the end-to-end lifecycle of AI agents, including scaffolding, deployment, evaluation, fine-tuning, and troubleshooting within Azure AI Foundry.
find-skills
225.2KUsers and AI agents seeking to discover, evaluate, and install third-party agent skills from public registries
The find-skills skill searches multiple agent skill registries (skills.sh, clawhub.ai, and GitHub) in parallel to help users discover, vet, and install relevant agent capabilities. It provides a comparative report based on native popularity metrics, performs a heuristic security scan on top candidates, and flags skills already present on the user's system.
just-scrape
212.9KDevelopers and data analysts who need to automate web data collection, structured extraction, and site monitoring tasks
The just-scrape skill provides a command-line interface for searching, scraping, crawling, and monitoring web pages using ScrapeGraph AI. It supports structured data extraction, recurring page monitoring, and history inspection.