Agent Skills › zzatpku/AgentFactory › google_search

google_search

GitHub

通过 Serper API 执行 Google 搜索，返回标题、URL 和简短摘要。用于快速检索网络信息，建议结合 read_url_jina 获取完整内容以补充细节。

skills/tools/google_search/SKILL.md zzatpku/AgentFactory

Trigger Scenarios

需要查询互联网上的最新信息或事实寻找特定主题的网页链接和简介作为前置步骤为读取完整页面做准备

Install

npx skills add zzatpku/AgentFactory --skill google_search -g -y

More Options

Non-standard path

npx skills add https://github.com/zzatpku/AgentFactory/tree/master/skills/tools/google_search -g -y

Use without installing

npx skills use zzatpku/AgentFactory@google_search

指定 Agent (Claude Code)

npx skills add zzatpku/AgentFactory --skill google_search -a claude-code -g -y

安装 repo 全部 skill

npx skills add zzatpku/AgentFactory --all -g -y

预览 repo 内 skill

npx skills add zzatpku/AgentFactory --list

SKILL.md

Frontmatter

{
    "name": "google_search",
    "description": "Search the internet via Google (Serper API). Returns only titles, URLs, and short snippets. Use read_url_jina to get full page content."
}

Search Tool

search_serper: High-quality search using Google via Serper API. Returns web page title, url and a short snippet.

Usage

from tools import search_serper

results = search_serper(query, topk=10)

Parameters

Parameter	Type	Default	Description
query	str	required	The search query string
topk	int	10	Number of top results to return

Returns

Returns a list of dictionaries directly:

[
    {
        "title": "web page title",
        "link": "web page url",
        "snippet": "brief snippet, NOT the full content...",
    },
    ...
]

Or on error:

[{"error": "error message"}]

Note: The snippet field is a very short excerpt, NOT the full page content. It may miss critical information. Always use read_url_jina to retrieve the full page content for any relevant result.

Example

from tools import search_serper

# Search for information about a topic
results = search_serper("capital of France", topk=3)

# Process results
for doc in results:
    if "error" in doc:
        print(f"Error: {doc['error']}")
        break
    print(f"Doc title: {doc['title']}")
    print(f"url: {doc['link']}")
    print(f"snippet: {doc['snippet']}...")
    print("---")

Tips

Use specific, descriptive queries for better results
Start with topk around 10 and adjust if needed
Check the score to gauge relevance
The snippet field is a brief excerpt, NOT the full content - it may miss critical information
Always use read_url_jina to get the full page content for any relevant result - do NOT rely solely on the snippet from search
Check for errors in the first result