web-search

Search the web and return structured result items with URLs and snippets.

Updated Dec 26, 2025
One-click install
npx skills add https://github.com/yutaoshao/agent-skills --skill web-search-yutaoshao
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: web-search
Source: https://github.com/yutaoshao/agent-skills/tree/main/glm-skills/web-search
Command: npx skills add https://github.com/yutaoshao/agent-skills --skill web-search-yutaoshao

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires z-ai-web-dev-sdk, and includes scripts (resource) components.

What problem does it solve?

Web applications often require up-to-date information from the internet and a consistent, structured format for search results. This skill provides a backend web search capability using the z-ai-web-dev-sdk, returning results with url, name, snippet, host_name, date, and favicon for easy consumption.

Core Features & Use Cases

  • Real-time web search queries to fetch fresh information.
  • Standardized result structure including url, name, snippet, host_name, date, and favicon.
  • Use cases: research assistants, news aggregation, competitive analysis, and content discovery.

Quick Start

Provide a simple user instruction to perform a web search and return the top results in a structured format.

Frequently Asked Questions about web-search

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I fetch real-time web search results in a structured format for my backend application?

To fetch real-time web search results, you can use a backend SDK to query the web and return a list of structured objects containing url, name, snippet, host_name, date, and favicon for easy application consumption.

What is the best way to aggregate current information for research assistants using z-ai-web-dev-sdk?

Aggregating current information is best handled by passing a query, num, and recency_days argument to the SDK to retrieve fresh, structured search results suitable for research assistants and competitive analysis.

Can I limit web search results to a specific recency using the backend SDK?

Yes, you can limit web search results to a specific recency by providing the recency_days argument, ensuring the returned structured SearchFunctionResultItem objects only contain current information published within that timeframe.

How do I get standardized metadata like host_name and favicon from web search queries?

You get standardized metadata by executing web search queries through the backend SDK, which automatically parses and returns structured result items including host_name, date, and favicon alongside the url and snippet.

Does the web-search approach work for news aggregation and content discovery?

Yes, the web-search approach works for news aggregation and content discovery by leveraging real-time web information retrieval to return current, structured results across multiple sources for immediate application use.