multi-search

Query web, social, code, community, and video platforms simultaneously and output Markdown results.

3|Updated May 10, 2026
One-click install
npx skills add https://github.com/inorilzy/multi-search-skill --skill multi-search-inorilzy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: multi-search
Source: https://github.com/inorilzy/multi-search-skill/tree/main/skills/multi-search
Command: npx skills add https://github.com/inorilzy/multi-search-skill --skill multi-search-inorilzy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires mcp, beautifulsoup4, twikit-ng, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill solves the challenge of gathering information from multiple sources simultaneously, enabling quick and comprehensive data retrieval.

Core Features & Use Cases

  • Multi-Source Search: Integrates Web search, code repositories, community discussions, video platforms, and Twitter/X to provide a broad perspective.
  • Markdown Output: Presents search results and extracted page content in a Markdown format suitable for agents to read.
  • Custom Routes: Allows selection of specific sources like 'web', 'social', 'dev', 'cn-community', 'video', or 'all' for targeted search.
  • Speed Cues: Offers a 'fast' route for quick searches with inline body content and a 'default' route for more in-depth results.
  • Query Expansion: Provides additional query variants for ambiguous or broad requests to refine search results.

Quick Start

Trigger the 'multi-search' skill by saying "search for [your query]".

Frequently Asked Questions about multi-search

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

FAQPage Schema
How do I retrieve information from web, social, and code platforms simultaneously?

Multi-source search unifies information retrieval by simultaneously querying web, social, code, community, and video platforms, outputting comprehensive Markdown results. You can trigger it by saying "search for [your query]" to gather broad perspectives instantly.

Can I target specific platforms like Twitter or code repositories for search?

Yes, you can specify custom source routes like 'web', 'social', 'dev', 'cn-community', 'video', or 'all' for targeted search. This route selection allows you to narrow multi-source information retrieval to specific platforms relevant to your query.

What's the best way to get quick search results with inline page content?

Use the 'fast' route for quick searches that return inline body content directly. This contrasts with the 'default' route, which performs more in-depth multi-source information retrieval and extracts comprehensive page content for detailed analysis.

Does multi-source search work with ambiguous or broad search queries?

Yes, it supports query expansion by providing additional query variants for ambiguous or broad requests. This mechanism refines multi-source search results, ensuring the information retrieval process yields more accurate and targeted data across web and social platforms.

How is extracted web page content formatted for agents to read?

Extracted page content and search results are presented in Markdown format, making it suitable for agents to read and process. This structured output ensures that multi-source information retrieval data is easily parsed by automated workflows.