skills.rest
anthropics
anthropicsOFFICIAL
Explore all skills by this author →
WebsiteGitHub

search-strategy

Decompose natural language questions into source-specific queries across enterprise data sources.

23.4k|2.8k|Updated Jan 23, 2026
Search Tags:#knowledge management#information retrieval#search#enterprise search#query decomposition#multi-source search
One-click install
npx skills add https://github.com/anthropics/knowledge-work-plugins --skill search-strategy-anthropics
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: search-strategy
Source: https://github.com/anthropics/knowledge-work-plugins/tree/main/enterprise-search/skills/search-strategy
Command: npx skills add https://github.com/anthropics/knowledge-work-plugins --skill search-strategy-anthropics

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill tackles the challenge of finding information scattered across various enterprise data sources by intelligently breaking down complex natural language queries into targeted searches.

Core Features & Use Cases

  • Query Decomposition: Analyzes user questions to identify intent, keywords, entities, and constraints.
  • Multi-Source Search: Generates and executes optimized queries for different data sources (chat, knowledge base, project trackers, etc.).
  • Result Synthesis: Ranks, deduplicates, and synthesizes results from multiple sources into a coherent answer.
  • Use Case: When you ask "What was decided about the API migration timeline?", this skill will query chat logs for decisions, knowledge bases for documentation, and project trackers for status, then combine the findings into a single, comprehensive answer.

Quick Start

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

Frequently Asked Questions about search-strategy

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

FAQPage Schema
How do I search across multiple enterprise data sources using a single natural language query?▼

To search across multiple enterprise data sources, this skill decomposes a natural language query into source-specific queries for chat logs, knowledge bases, and project trackers, then synthesizes the combined results into one coherent answer.

What is query decomposition for enterprise search and how does it work?▼

Query decomposition for enterprise search analyzes user questions to identify intent, keywords, entities, and constraints, translating them into optimized targeted queries for different data sources like project trackers and knowledge bases.

Can I use multi-source search orchestration if one of my data sources is unavailable?▼

You can use multi-source search orchestration with unavailable data sources because the skill implements fallback strategies, ambiguity resolution, and relevance ranking to handle missing sources and deduplicate available results.

What's the best way to find decisions scattered across chat logs and project trackers?▼

The best way to find decisions scattered across chat logs and trackers is multi-source search orchestration, which queries chat for decisions, knowledge bases for documentation, and trackers for status, then synthesizes the findings.

How does information retrieval handle relevance ranking and deduplication from multiple knowledge bases?▼

Information retrieval handles relevance ranking and deduplication by evaluating results from multiple knowledge bases, applying ranking algorithms, removing duplicate entries, and synthesizing the remaining findings into a single comprehensive answer.

Related Skills

Explore More Software Engineering Skills→
ilove323ilove323

search-strategy

Decompose natural language queries into parallel, source-specific searches across connected data sources.

Community
Advanced
cnoe-iocnoe-io
392

documentation-search

Retrieve internal documentation using Retrieval-Augmented Generation across ADRs and runbooks.

Official
Intermediate
lilbom32lilbom32

source-management

Centralizes and prioritizes MCP sources for enterprise search.

Community
Intermediate
Eng0AIEng0AI
15

natural-language-postgres-presentation

Convert natural-language queries into SQL for PostgreSQL data retrieval.

Official
Advanced