enterprise-search-strategy

Decompose natural language queries into source-specific syntax for enterprise search.

114|13|Updated Jan 17, 2026
One-click install
npx skills add https://github.com/frumu-ai/tandem --skill enterprise-search-strategy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: enterprise-search-strategy
Source: https://github.com/frumu-ai/tandem/tree/main/src-tauri/resources/skill-templates/enterprise-search-strategy
Command: npx skills add https://github.com/frumu-ai/tandem --skill enterprise-search-strategy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill tackles the challenge of finding specific information scattered across various internal tools and communication channels by intelligently breaking down complex questions into targeted searches.

Core Features & Use Cases

  • Query Decomposition: Analyzes natural language questions to identify intent, keywords, and constraints.
  • Source-Specific Query Generation: Translates decomposed queries into syntax suitable for different platforms like chat, knowledge bases, and project trackers.
  • Result Ranking & Synthesis: Ranks results by relevance and authority, then synthesizes them into a coherent answer.
  • Ambiguity & Fallback Handling: Manages unclear queries by asking clarifying questions and gracefully handles unavailable sources or empty results.
  • Use Case: Asking "What did we decide about the API migration timeline?" will trigger targeted searches across chat, knowledge base, and project trackers to find the most relevant decision and timeline information.

Quick Start

Use the enterprise-search-strategy skill to find out what was decided about the API migration timeline.

Frequently Asked Questions about enterprise-search-strategy

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

FAQPage Schema
How does multi-source enterprise search orchestration work?

Enterprise search orchestration works by decomposing natural language queries into source-specific syntax, then ranking and synthesizing results from chat, knowledge bases, and project trackers into a coherent answer.

What's the best way to find information scattered across internal communication channels and knowledge bases?

The best way to find scattered internal information is using query decomposition to translate natural language questions into targeted searches across multiple platforms, synthesizing ranked results to retrieve specific decisions or documentation.

Can I use natural language to search across project trackers and chat history simultaneously?

Yes, natural language search queries can target multiple sources simultaneously by analyzing intent and constraints, generating source-specific syntax for chat and project trackers, and synthesizing the retrieved results.

How do I handle enterprise search when my query is ambiguous or returns empty results?

To handle ambiguous enterprise search queries or empty results, the search orchestration mechanism asks clarifying questions to refine intent and gracefully executes fallbacks when targeted sources are unavailable or return no matches.

How are search results ranked when retrieving information from multiple internal tools?

Search results from multiple internal tools are ranked by evaluating relevance and source authority. The orchestration layer synthesizes these ranked results to provide a comprehensive answer to the original natural language query.