skills.rest
chelleboyer
chelleboyerCOMMUNITY
Explore all skills by this author →
GitHub

search-strategy

Decompose natural language questions into parallel source-specific searches and synthesize ranked results.

Updated Jan 11, 2026
Search Tags:#search#enterprise#ranking#semantic-search#multisource#query-decomposition
One-click install
npx skills add https://github.com/chelleboyer/reachy_mini_retail_assistant --skill search-strategy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: search-strategy
Source: https://github.com/chelleboyer/reachy_mini_retail_assistant/tree/main/skills/enterprise-search/skills/search-strategy
Command: npx skills add https://github.com/chelleboyer/reachy_mini_retail_assistant --skill search-strategy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transforms a single natural language query into parallel, source-specific searches across connected knowledge sources, delivering ranked results with deduplication.

Core Features & Use Cases

  • Decomposes queries into per-source sub-queries and translates them into source-specific syntax (semantic vs keyword).
  • Executes searches in parallel across chat, wiki, project trackers, and document stores.
  • Ranks results by relevance and resolves ambiguity and fallback scenarios to synthesize a coherent answer.

Quick Start

Run a multi-source search plan for a question and synthesize the results into a single, ranked answer.

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 knowledge sources with a single natural language query?▼

Multi-source search decomposes a natural language query into parallel, source-specific sub-queries, translating them into appropriate syntax for each connected wiki, chat, or document store to return unified results.

What is the best way to handle ambiguity and deduplication when searching across enterprise wikis and project trackers?▼

Enterprise search orchestration handles ambiguity and deduplication by ranking results with relevance scoring across parallel queries, applying fallback scenarios, and synthesizing a coherent answer from overlapping sources.

How does query decomposition decide between semantic search and keyword search for different data sources?▼

Query decomposition selects semantic or keyword search per source by translating the original question into source-specific syntax, ensuring each connected knowledge store receives the optimal search type for its structure.

Can I execute parallel searches across chat assistants and document stores without writing individual API queries for each?▼

Yes, multi-source search orchestration automatically generates and executes parallel searches across chat assistants and document stores, eliminating the need to manually write individual API queries for each data source.

Does multi-source search work with enterprise knowledge contexts that use varied search syntax and storage formats?▼

Multi-source search works across diverse enterprise knowledge contexts by translating queries to source-specific syntax, selecting semantic or keyword search per source, and applying robust error handling for varied storage formats.

How are search results ranked and synthesized when querying multiple project trackers simultaneously?▼

Search results are ranked using relevance scoring and synthesized into a unified answer after parallel queries execute, resolving ambiguity and applying fallbacks to ensure coherent output across project trackers.

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
anthropicsanthropics
37

enterprise-search

Search enterprise knowledge indexes with permission-aware filtering and cursor pagination.

Official
Advanced
kousenkousen
10

osquery

Translate natural language questions into Osquery SQL queries and parse JSON results.

Community
Advanced
getty104getty104
11

web-search

Execute gemini-based web searches and present source-labeled answers in Markdown.

Community
Basic