Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

external-context — Claude Code skill: parallel documentation search

This skill breaks down your query into multiple search facets and spawns parallel document-specialist agents to search documentation and web simultaneously. Useful for gathering context on a topic or comparing approaches.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add Yeachan-Heo/oh-my-claudecode --skill external-context -a claude-code
Open on GitHub

What external-context does

external-context decomposes your question into 2–5 independent search facets. For each facet, it spawns a specialist agent that searches official docs, GitHub, and technical blogs. Results are synthesized into a single response with citations and links.

Invoke it with /oh-my-claudecode:external-context <topic or question>. Under the hood, it uses WebSearch and WebFetch to find and load pages. Maximum 5 parallel agents run at once — this is a design limit.

What it helps with

  • gather context on a topic from multiple sources without manual searches
  • compare approaches: ORMs, architecture patterns, or frameworks
  • find current code examples and industry best practices
  • learn what official docs and the community recommend

Example prompts for the agent

  • /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

How to install external-context

1Skills CLI (Vercel)

npx skills add Yeachan-Heo/oh-my-claudecode --skill external-context -a claude-code

2Manually: put the files in place

~/.claude/skills/external-context/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/external-context/

From the same set26

The whole set →
ai-slop-cleaner Yeachan-Heo Cleans bloated AI-generated code by deleting dead logic and duplicate abstractions. It keeps current behavior locked under regression tests. Claude Code CX Codex Cursor +1 1,500installs ralplan Yeachan-Heo A skill that runs iterative planning with three agents (Planner, Architect, Critic) until consensus. Blocks vague requests before execution, never runs changes without your approval. Claude Code CX Codex Cursor +1 1,200installs hud Yeachan-Heo The hud skill configures a HUD display in Claude Code's statusline, showing git branch, context usage, running subagents, and other metrics. Track session state and keep tabs on complex work without losing context. Claude Code CX Codex Cursor +1 1,100installs deepinit Yeachan-Heo Walks a repository and writes an AGENTS.md per directory: what sits there, how the parts connect, what an agent should know before editing. Claude Code CX Codex Cursor +1 1,000installs autopilot Yeachan-Heo A skill that takes a task description and runs the full development cycle: requirements analysis, design, implementation, testing, and validation—all hands-off. Use it when you want to describe what you need and get working code back. Claude Code CX Codex Cursor +1 999installs deep-interview Yeachan-Heo A skill that runs a Socratic interview on your idea, scores ambiguity across weighted dimensions, and blocks coding until the score falls under the threshold. Claude Code CX Codex Cursor +1 998installs omc-setup Yeachan-Heo Canonical setup and repair wizard for oh-my-claudecode. It configures CLAUDE.md files, HUD statusline, and agent team defaults. Claude Code CX Codex Cursor +1 987installs ralph Yeachan-Heo A persistence loop that works through tasks in prd.json until all stories pass and get reviewer verification. Useful for multi-step jobs that need guaranteed completion. Claude Code CX Codex Cursor +1 971installs

Similar

validate-skills Callstack Checks skills in skills/ against the agentskills.io specification and Claude Code practices. Use it when authoring or reviewing a skill collection. Claude Code CX Codex Cursor +1 7,200installs image-to-ui UIZZE Turn a screenshot, mockup, or sketch into working interface code. The skill views the image, reproduces it exactly in code, then renders and compares to fix any mismatches. Claude Code CX Codex Cursor +1 63,500installs mmx-cli MiniMax-AI Teaches your agent to use the MiniMax CLI directly from the terminal. Helps generate text, images, video, speech, and music inside coding workflows. Claude Code CX Codex Cursor +1 1,600installs deep-research ruvnet Orchestrates multi-phase research using web search, codebase analysis, and memory storage. It generates structured findings with evidence ratings for complex topics. Claude Code CX Codex Cursor +1 893installs events-system phaserjs Guides Phaser 4 event work, from listeners and custom signals to communication between scenes. Use it when editing code with on, emit, or EventEmitter. Claude Code CX Codex Cursor +1 778installs api-docs ruvnet Skill that turns TypeScript and JavaScript source into documentation: it finds public exports, reads existing JSDoc, writes the missing comments and emits OpenAPI 3.0 for HTTP endpoints. Claude Code CX Codex Cursor +1 891installs setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. Claude Code 1,052,851installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. Claude Code 711,230installs

Questions about external-context

How do I install external-context in Claude Code?

Run npx skills add Yeachan-Heo/oh-my-claudecode --skill external-context -a claude-code. The skill installs to ~/.claude/skills/external-context/SKILL.md.

What does external-context do?

It takes your question or topic, breaks it into multiple search facets, and launches parallel agents to search documentation and web pages. Results are combined with citations and source links.

How many agents run at the same time?

Up to 5 specialist agents in parallel. Each searches its own facet of the topic independently.

Source text

SKILL.md · MIT 
---
name: external-context
description: Invoke parallel document-specialist agents for external web searches and documentation lookup
argument-hint: <search query or topic>
level: 4
---

# 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

```
/oh-my-claudecode:external-context <topic or question>
```

### 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
```

## 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>
...
```

### 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.")
```

Maximum 5 parallel document-specialist agents.

### Step 3: Synthesis Output Format

Present synthesized results in this format:

```markdown
## External Context: <query>

### Key Findings
1. **<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

© Yeachan-Heo · MIT · Yeachan-Heo/oh-my-claudecode

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor