What problem does it solve? Applications often need access to real-time information beyond an AI model's knowledge cutoff, such as current news, recent research, or up-to-date facts. This Skill provides the patterns and code to integrate web search into backend applications using the z-ai-web-dev-sdk. ## Core Features & Use Cases - Web Search via SDK or CLI: Invoke the web_search function with a query, result count, and recency filter, either from JavaScript/TypeScript code or the z-ai command line. - Result Processing Patterns: Includes ready-made examples for filtering by domain, sorting by date, caching results, rate limiting, and validating result quality. - Use Case: Build a research assistant that searches for a topic, groups results by domain, sorts them by publication date, and feeds the top snippets into a chat completion for an AI-generated summary with cited sources. ## Quick Start Ask the AI to search the web for the latest news on a topic and return the top five results with titles, URLs, and snippets.