multi-search-engine

Queries 17 search engines via URL templates without API keys.

89|5|Updated Mar 25, 2026
One-click install
npx skills add https://github.com/CUHK-AIM-Group/NeuroDiscovery --skill multi-search-engine-cuhk-aim-group
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: multi-search-engine
Source: https://github.com/CUHK-AIM-Group/NeuroDiscovery/tree/main/skills/multi-search-engine
Command: npx skills add https://github.com/CUHK-AIM-Group/NeuroDiscovery --skill multi-search-engine-cuhk-aim-group

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? It removes the need for paid search APIs or API keys when gathering web information, letting you query 17 search engines (8 Chinese and 9 international) directly through URL-based web fetching. ## Core Features & Use Cases - Multi-Engine Coverage: Query Baidu, Bing, Google, DuckDuckGo, Sogou, WeChat, Brave, Qwant, WolframAlpha, and more through simple URL templates. - Advanced Search Syntax: Use operators like site:, filetype:, exact-match quotes, exclusions, and time filters (past hour/day/week/month/year) to narrow results. - Privacy & Knowledge Queries: Route sensitive searches through DuckDuckGo, Startpage, or Brave, and run calculations or conversions through WolframAlpha. - Use Case: A researcher needs recent Chinese-language discussions on a topic plus international academic sources; they query WeChat and Toutiao for domestic content, then Google with a past-week time filter for global coverage. ## Quick Start Use the multi-search-engine skill to search Google for recent papers on graph neural networks from the past month.

Frequently Asked Questions about multi-search-engine

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

FAQPage Schema
How do I search multiple search engines without an API key?▼

Construct search URLs directly using each engine's query template, such as https://www.google.com/search?q={keyword} or https://www.baidu.com/s?wd={keyword}, then fetch the results page. This skill provides templates for 17 engines requiring no authentication.

How to search within a specific website using Google?▼

Use the site: operator in your query, for example site:github.com python, appended to the Google search URL. You can combine it with filetype:pdf, exact-match quotes, and exclusion operators for more precise results.

Which search engines protect user privacy?▼

DuckDuckGo performs no tracking, Startpage delivers Google results with privacy, Brave uses an independent index, and Qwant complies with EU GDPR. All four are included among the 17 supported engines.

How do I filter Google search results by time period?▼

Append a tbs parameter to the Google search URL: tbs=qdr:h for past hour, qdr:d for past day, qdr:w for past week, qdr:m for past month, or qdr:y for past year.

Can I search Chinese platforms like WeChat and Baidu?▼

Yes, the skill includes 8 domestic engines: Baidu, Bing CN, 360, Sogou, WeChat article search via wx.sogou.com, Toutiao, and Jisilu. Each has a documented URL template for direct querying.

What are the limitations of URL-based web search scraping?▼

Results depend on the HTML returned by each engine, which may include rate limiting, CAPTCHAs, or layout changes that break parsing. There is no structured API response, so extraction reliability varies by engine.