external-context

Decompose queries into facets and synthesize cited documentation from parallel web agents.

Updated Apr 17, 2026
One-click install
npx skills add https://github.com/dropsyoon/oh-my-claudecode --skill external-context-dropsyoon
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: external-context
Source: https://github.com/dropsyoon/oh-my-claudecode/tree/main/skills/external-context
Command: npx skills add https://github.com/dropsyoon/oh-my-claudecode --skill external-context-dropsyoon

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you quickly gather high-quality external documentation and supporting sources for a question, so you can make better decisions without manually searching across the web.

Core Features & Use Cases

  • Facet-based web research: Breaks a query into 2-5 independent facets (e.g., official docs, comparisons, best practices) to cover different angles efficiently.
  • Parallel document-specialist agents: Runs multiple document-focused agents concurrently and synthesizes the results with citations.
  • Actionable structured output: Produces a clear set of key findings plus facet-level detailed results and a consolidated sources list.

Quick Start

Use /oh-my-claudecode:external-context with your topic or question to receive synthesized, cited external context in a single response.

Frequently Asked Questions about external-context

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

FAQPage Schema
How do I get cited web search results for multi-faceted research questions?

Cited web search results are produced by decomposing a query into 2-5 independent search facets, running parallel document-specialist agents, and synthesizing findings with a consolidated sources list.

What is query decomposition for external research and when should I use it?

Query decomposition for external research breaks a question into independent facets like official references and best practices, used for documentation lookup and comparison questions requiring multiple perspectives.

How to synthesize information from parallel web searches into a single document?

Synthesize information from parallel web searches by running 2-5 document-specialist agents concurrently, collecting key findings per facet, and returning a consolidated document with cited URLs.

Can I use multi-agent web search for official documentation lookup and best practices comparison?

Multi-agent web search supports documentation lookup and best practices comparison by assigning parallel agents to cover different perspectives, then synthesizing results with citations.

What is the maximum number of search facets supported for parallel document retrieval?

Parallel document retrieval supports a maximum of 5 search facets, allowing up to five concurrent document-specialist agents to fetch and synthesize web context.

What are the limitations of multi-agent query decomposition for web research?

Multi-agent query decomposition is limited to 2-5 facets per query, meaning extremely broad research topics may need separate queries to avoid exceeding the five parallel agent limit.