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:

## 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:

## 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

Files1

1 files · 1.0 KB

Select a file to preview

Overall Score

76/100

Grade

B

Good

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

82

Quality

72

Clarity

83

Completeness

64

Summary

This skill decomposes arbitrary search queries into 2-5 research facets and spawns parallel document-specialist Claude agents to fetch external documentation and references. Results are synthesized and presented with full source citations. It acts as a research coordinator for knowledge gathering across the web.

Detected Capabilities

web search via subagentparallel task invocationexternal document fetchurl citation and aggregationfacet-based query decomposition

Trigger Keywords

Phrases that agents use to match this skill to user intent.

research best practicescompare frameworksgather documentationweb search synthesisfind latest patterns

Use Cases

Gather best practices and patterns for a technology (JWT rotation, async patterns, security)
Compare two competing tools or frameworks with recent examples and trade-offs
Find latest conventions and updates for a rapidly-evolving domain (React, Node.js, Python)
Research emerging libraries and gather cross-source recommendations
Synthesize multiple expert perspectives on a technical problem by pulling from diverse sources

Quality Notes

Well-structured protocol with clear three-step decomposition-invocation-synthesis flow
Excellent examples demonstrate common research scenarios (JWT rotation, ORM comparison, React patterns)
Source citation requirement ensures traceability and verification
Parallel agent model (max 5) shows thoughtful scaling constraints
Clear output format makes synthesis predictable and parseable
No guardrails documented for malicious or abusive search queries (e.g., doxing, harassment)
Missing guidance on query filtering, content validation, or handling of low-quality sources
No documented error handling for subagent failures or timeouts
Facet decomposition strategy is intuitive but lacks examples of decomposition for edge cases (overly broad queries, ambiguous topics)
Missing documented cost/latency implications of spawning up to 5 parallel agents

Model: claude-haiku-4-5-20251001Analyzed: Sep 9, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

external-context