External Context

Yeachan-Heo/oh-my-claudecode/skills/external-context

by Yeachan-Heo454bae017356ed1d056182cd929b6eb6cf6143adNo licenseListed Oct 9, 2026Updated Oct 9, 2026

Invoke parallel document-specialist agents for external web searches and documentation lookup

Instructions onlyResearch & Analysis AI & Agents

AI-generated overview

Decomposes a query into facets and runs parallel document-specialist agents to gather external web documentation and references.

What it does: This skill takes a topic or question, breaks it into two to five independent search facets, and dispatches parallel document-specialist agents that use web search and fetch tools to find official documentation and examples. It then synthesizes the agents' findings into a structured report with key findings, per-facet detail, and a cited source list. It is an instructions-only skill with no bundled scripts.
When to use it: Use it when you need external documentation, references, or current web context for a technical question, such as best practices, library comparisons, or framework conventions. It is meant for explicit invocation rather than automatic triggering.
Requirements: An agent runtime that supports the Task tool with a document-specialist subagent type, plus web search and web fetch capabilities and network access. No scripts or credentials are bundled.

External Context Skill

Fetch external documentation, references, and context for a query. Decomposes into 2-5 facets and spawns parallel document-specialist Claude agents.

Usage

Examples

/oh-my-claudecode:external-context What are the best practices for JWT token rotation in Node.js?/oh-my-claudecode:external-context Compare Prisma vs Drizzle ORM for PostgreSQL/oh-my-claudecode:external-context Latest React Server Components patterns and conventions

/oh-my-claudecode:external-context What are the best practices for JWT token rotation in Node.js?/oh-my-claudecode:external-context Compare Prisma vs Drizzle ORM for PostgreSQL/oh-my-claudecode:external-context Latest React Server Components patterns and conventions

Protocol

Step 1: Facet Decomposition

Given a query, decompose into 2-5 independent search facets:

markdown

## Search Decomposition
**Query:** <original query>
### Facet 1: <facet-name>- **Search focus:** What to search for- **Sources:** Official docs, GitHub, blogs, etc.
### Facet 2: <facet-name>...

## Search Decomposition
**Query:** <original query>
### Facet 1: <facet-name>- **Search focus:** What to search for- **Sources:** Official docs, GitHub, blogs, etc.
### Facet 2: <facet-name>...

Step 2: Parallel Agent Invocation

Fire independent facets in parallel via Task tool:

Task(subagent_type="oh-my-claudecode:document-specialist", model="sonnet", prompt="Search for: <facet 1 description>. Use WebSearch and WebFetch to find official documentation and examples. Cite all sources with URLs.")
Task(subagent_type="oh-my-claudecode:document-specialist", model="sonnet", prompt="Search for: <facet 2 description>. Use WebSearch and WebFetch to find official documentation and examples. Cite all sources with URLs.")

Task(subagent_type="oh-my-claudecode:document-specialist", model="sonnet", prompt="Search for: <facet 1 description>. Use WebSearch and WebFetch to find official documentation and examples. Cite all sources with URLs.")
Task(subagent_type="oh-my-claudecode:document-specialist", model="sonnet", prompt="Search for: <facet 2 description>. Use WebSearch and WebFetch to find official documentation and examples. Cite all sources with URLs.")

Maximum 5 parallel document-specialist agents.

Step 3: Synthesis Output Format

Present synthesized results in this format:

markdown

## External Context: <query>
### Key Findings1. **<finding>** - Source: [title](url)2. **<finding>** - Source: [title](url)
### Detailed Results
#### Facet 1: <name><aggregated findings with citations>
#### Facet 2: <name><aggregated findings with citations>
### Sources- [Source 1](url)- [Source 2](url)

## External Context: <query>
### Key Findings1. **<finding>** - Source: [title](url)2. **<finding>** - Source: [title](url)
### Detailed Results
#### Facet 1: <name><aggregated findings with citations>
#### Facet 2: <name><aggregated findings with citations>
### Sources- [Source 1](url)- [Source 2](url)

Configuration

Maximum 5 parallel document-specialist agents
No magic keyword trigger - explicit invocation only

Source and attribution

Source:Yeachan-Heo/oh-my-claudecodeinskills/external-contextat commit454bae0

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal

External Context

External Context Skill

Usage

Examples

Protocol

Step 1: Facet Decomposition

Step 2: Parallel Agent Invocation

Step 3: Synthesis Output Format

Configuration

Source and attribution

More from Yeachan-Heo/oh-my-claudecode

Wiki

Visual Verdict

Team

Verify

Skill

Release

More in Research & Analysis

Sector Overview

Sector Overview

Idea Generation

Competitive Analysis

Equity Research

Sector Overview