What problem does it solve? It gives you live web search results from a self-hosted SearXNG instance, so you can find current information, news, and documentation that is not in the model's training data without relying on a commercial search API. ## Core Features & Use Cases - Categorized Search: Query across categories like general, news, images, videos, it, science, and social media, combinable with commas. - Filtering Options: Narrow results by time range (day, week, month, year), language, safe search level, and maximum result count. - Flexible Output: Get results as structured JSON or a readable numbered text list. - Use Case: Ask for the latest AI announcements from the past week, and the skill runs a news-category search with a week time filter against your local SearXNG server and returns titles, URLs, and snippets. ## Quick Start Ask the assistant to search the web for a topic, for example: search for recent news about transformer architecture from the past week.