multi-search▌
nex-zmh/agent-websearch-skill · updated Apr 8, 2026
Intelligent multi-engine search with automatic network detection and fallback prioritization.
- ›Supports four search engines with two priority modes: quality-first (Tavily > DuckDuckGo > Bing API > Bing scraper) or balanced/free-first (DuckDuckGo > Tavily > Bing API > Bing scraper)
- ›Includes automatic quota management for API-based engines, 5-minute network detection caching, and forced re-detection after network changes
- ›Provides web content fetching and batch enrichment of search resul
Multi-Search Skill - 智能多引擎搜索
本技能整合多个搜索引擎,自动检测网络环境,智能选择最佳可用引擎。
引擎优先级
质量优先模式 (prefer_quality=True)
- Tavily API (1000次/月) - 质量最高,需 API Key
- DuckDuckGo (无限免费) - 无需 API Key
- Bing Web Search API (1000次/月) - 需 API Key
- Bing 爬虫 (无限免费) - 最终回退
平衡模式 (prefer_quality=False, 默认)
- DuckDuckGo (无限免费) - 优先免费引擎
- Tavily API (1000次/月) - 如果配置了 API Key
- Bing Web Search API (1000次/月)
- Bing 爬虫 (无限免费)
核心能力
- 智能网络检测与引擎切换
- 自动配额管理(Tavily/Bing API)
- 支持网页内容抓取
- 5分钟网络检测缓存
使用方式
基本搜索
from multi_search import search
# 平衡模式 - 优先免费引擎
results = search("Python tutorial", max_results=5)
# 质量优先模式 - 优先使用 Tavily
results = search("AI research", max_results=5, prefer_quality=True)
# 强制重新检测网络(切换 VPN 后使用)
results = search("OpenClaw skills", max_results=5, force_network_check=True)
搜索技能(自动质量优先)
from multi_search import search_skills
results = search_skills("OpenClaw AI agent automation", max_results=10)
查看系统状态
from multi_search import get_status
status = get_status() # 使用缓存
status = get_status(force_network_check=True) # 强制重新检测
抓取网页详细内容
from multi_search import search, fetch_web_content, fetch_search_results_content
# 搜索并抓取第一个结果的详细内容
results = search("OpenClaw new features", max_results=3)
if results:
content = fetch_web_content(results[0]['href'], max_length=3000)
# content['title'], content['content'], content['success']
# 批量抓取所有搜索结果的详细内容
enriched_results = fetch_search_results_content(results, max_length=2000)
for r in enriched_results:
if r.get('full_content'):
# 使用 summarize 技能总结内容
pass
与 Summarize 技能结合使用
OpenClaw 工作流:
1. 使用 multi-search 搜索关键词
2. 选择感兴趣的搜索结果
3. 使用 fetch_web_content() 抓取网页内容
4. 使用 summarize 技能总结网页内容
5. 将摘要呈现给用户
返回结果格式
[
{
'title': '结果标题',
'href': 'https://example.com',
'body': '结果摘要...',
'source': 'duckduckgo' # 或 'tavily', 'bing_api', 'bing_scraper'
}
]
参数说明
query: 搜索关键词max_results: 最大结果数(默认5)prefer_quality: 是否优先质量(默认False)force_network_check: 是否强制重新检测网络(默认False)
注意事项
- DuckDuckGo: 免费无限,但某些网络环境无法访问
- Tavily: 质量高,需要 API key,1000次/月
- Bing API: 官方稳定,需要 Azure 账号,1000次/月
- Bing 爬虫: 免费无限,但可能受反爬影响
Ratings
4.5★★★★★10 reviews- ★★★★★Shikha Mishra· Oct 10, 2024
multi-search is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
- ★★★★★Piyush G· Sep 9, 2024
Keeps context tight: multi-search is the kind of skill you can hand to a new teammate without a long onboarding doc.
- ★★★★★Chaitanya Patil· Aug 8, 2024
Registry listing for multi-search matched our evaluation — installs cleanly and behaves as described in the markdown.
- ★★★★★Sakshi Patil· Jul 7, 2024
multi-search reduced setup friction for our internal harness; good balance of opinion and flexibility.
- ★★★★★Ganesh Mohane· Jun 6, 2024
I recommend multi-search for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
- ★★★★★Oshnikdeep· May 5, 2024
Useful defaults in multi-search — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
- ★★★★★Dhruvi Jain· Apr 4, 2024
multi-search has been reliable in day-to-day use. Documentation quality is above average for community skills.
- ★★★★★Rahul Santra· Mar 3, 2024
Solid pick for teams standardizing on skills: multi-search is focused, and the summary matches what you get after install.
- ★★★★★Pratham Ware· Feb 2, 2024
We added multi-search from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
- ★★★★★Yash Thakker· Jan 1, 2024
multi-search fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.