skills.rest
kiryteo
kiryteoCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

search-strategy

Deconstruct natural language questions into parallel, source-specific search queries.

1|Updated Mar 9, 2026
Search Tags:#search#ambiguity#decomposition#ranking#semantic-search#multisource
One-click install
npx skills add https://github.com/kiryteo/opencode-setup --skill search-strategy-kiryteo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: search-strategy
Source: https://github.com/kiryteo/opencode-setup/tree/main/skills/search-strategy
Command: npx skills add https://github.com/kiryteo/opencode-setup --skill search-strategy-kiryteo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Deconstructs a single natural language question into parallel, source-specific searches and produces ranked, deduplicated results.

Core Features & Use Cases

  • Query Decomposition: Breaks a query into per-source components and generates targeted sub-queries.
  • Source Translation: Converts user intent into semantic or keyword queries for each connected source.
  • Result Synthesis: Ranks, deduplicates, and presents a unified answer from multiple sources.
  • Ambiguity Handling: Manages uncertainty with fallback strategies and optional clarifications.

Quick Start

Ask a complex question and let the skill decompose it into parallel, source-specific searches.

Frequently Asked Questions about search-strategy

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

FAQPage Schema
How do I search multiple data sources from a single natural language question?▼

Multi-source search from a single question is handled by decomposing the query into parallel, source-specific sub-queries. The skill translates user intent into targeted semantic or keyword searches for each connected source.

What is the best way to deduplicate and rank results from parallel semantic searches?▼

Deduplicating and ranking results from parallel semantic searches requires synthesizing the outputs into a unified answer. The skill applies ranking algorithms to merge multiple source results and remove duplicates.

How does query decomposition handle ambiguity in exploratory search requests?▼

Query decomposition handles ambiguity by applying fallback strategies and optional clarifications. When exploratory search intent is uncertain, the skill manages uncertainty through robust translation and targeted sub-queries.

Can I use semantic and keyword search translation across different connected sources?▼

Semantic and keyword search translation can be applied across different connected sources. The skill converts user intent into the specific query format required by each source, whether it requires semantic matching or keyword extraction.

When do I need to decompose a natural language question into per-source search queries?▼

Decomposing a natural language question into per-source search queries is needed for exploratory, factual, and status-type inquiries. This approach generates targeted sub-queries to gather comprehensive results from multiple sources.

Related Skills

Explore More Software Engineering Skills→
kousenkousen
10

osquery

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

Community
Advanced
L-LesterYuL-LesterYu
51

brave-web-search-zh

Searches the web via the Brave Search API and returns ranked results or AI-generated summaries.

Community
Intermediate
giosuetedeschi-specgiosuetedeschi-spec

rag-engineer

Design and optimize Retrieval-Augmented Generation pipelines for improved context retrieval.

Community
Advanced
botlearn-aibotlearn-ai
9

google-search

Construct advanced search queries with Boolean operators and credibility-based ranking.

Official
Intermediate