web-search

Search queries via the z-ai-web-dev-sdk and return SearchFunctionResultItem objects.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/favouritehu/call_tracking --skill web-search-favouritehu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: web-search
Source: https://github.com/favouritehu/call_tracking/tree/main/skills/web-search
Command: npx skills add https://github.com/favouritehu/call_tracking --skill web-search-favouritehu

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill enables developers to build applications that can perform fast, reliable web searches and retrieve current information from internet sources, reducing manual lookup time.

Core Features & Use Cases

  • Backend web search: Use the z-ai-web-dev-sdk to perform programmatic queries and fetch structured results.
  • Real-time information retrieval: Ideal for news, research, and content discovery across topics.
  • Use Case: Build an internal search tool that aggregates the latest articles about a topic and returns titles, URLs, and snippets for user review.

Quick Start

  • CLI example: z-ai function -n web_search -a '{"query": "artificial intelligence"}'
  • SDK example: const zai = await ZAI.create(); const results = await zai.functions.invoke('web_search', { query: 'machine learning', num: 5 });

Frequently Asked Questions about web-search

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

FAQPage Schema
How do I retrieve real-time web search information in a TypeScript backend?

Real-time web search information is retrieved by using the z-ai-web-dev-sdk to execute programmatic queries and fetch structured SearchFunctionResultItem objects. This backend integration supports configurable parameters like query strings and result limits.

What's the best way to get structured web search results for an application?

The best way to get structured web search results is configuring the z-ai-web-dev-sdk backend invocation to return titles, URLs, and snippets. This approach enforces structured SearchFunctionResultItem objects for reliable content discovery.

Can I use z-ai-web-dev-sdk for automated research workflows and content discovery?

Yes, z-ai-web-dev-sdk supports automated research workflows and content discovery by returning structured SearchFunctionResultItem objects. Backend integration allows aggregating articles and fetching real-time information across topics.

How to perform a web search using z-ai-web-dev-sdk?

Perform a web search by initializing the z-ai-web-dev-sdk instance and invoking the search function with a JSON payload containing the query and number of results. This backend SDK execution returns structured SearchFunctionResultItem objects.

Does web search return formatted data or raw HTML when fetching real-time information?

Web search returns structured SearchFunctionResultItem objects rather than raw HTML when fetching real-time information. This structured data provides titles, URLs, and snippets directly through the z-ai-web-dev-sdk backend integration.

Why use a backend SDK for real-time information retrieval instead of direct API calls?

Using a backend SDK for real-time information retrieval enforces structured result formats and reduces manual lookup time. The z-ai-web-dev-sdk integration provides reliable SearchFunctionResultItem objects suitable for automated research workflows.