When you need to research something technical and don't want to tab-switch through a dozen Stack Overflow posts and docs sites, this skill decomposes your query into 2-5 focused facets and fires off parallel document-specialist agents to hunt them down. Each agent uses WebSearch and WebFetch to pull official docs, examples, and references, then everything gets synthesized into a single report with proper citations. It's genuinely useful for comparative questions like "Prisma vs Drizzle ORM" or diving into best practices that span multiple sources. The parallel execution means you're not waiting for sequential searches, and the structured output keeps things readable instead of dumping raw search results on you.

skills.sh installs
839
GitHub stars
40.7K
last updated
Aug 21, 2026

Install

$ npx -y skills add yeachan-heo/oh-my-claudecode --skill external-context --agent claude-code

Installs into .claude/skills of the current project.

Files

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.")

Sponsors

Details

Repository
github.com/yeachan-heo/oh-my-claudecode
Categories
Documentation, Automation & Workflows
First seen
Jun 3, 2026

More from yeachan-heo/oh-my-claudecode

All 37
1basicmachines-co avatarmemory-notesbasicmachines-co/basic-memory-skillsHow to write well-structured Basic Memory notes: frontmatter, observations with semantic categories, relations with wiki-links, and best practices for building 833skills.sh installs
2hugorcd avatarcreate-evlog-adapterhugorcd/evlogCreate a new built-in evlog adapter to send wide events to an external observability platform. Use when adding a new drain adapter (e.g., for Elasticsearch, Hon811skills.sh installs
3softaworks avatarperplexitysoftaworks/agent-toolkitWeb search and research using Perplexity AI. Use when user says "search", "find", "look up", "ask", "research", or "what's the latest" for generic queries. NOT 802skills.sh installs
4diodeinc avatarreference-designdiodeinc/pcbGrow a component package into a high-quality, sourceable reusable design in Zener. Use when translating a datasheet, application note, or eval design into circu799skills.sh installs
5lulu-eva avatarevalulu-eva/eva-skillEva-skill 2.2.8 的极薄路由入口。仅在用户调用 /eva、点名 Eva 子入口,提出 Eva 的思考、人群识别、短视频或非虚构文章、发布前审核、学习、Brief、复盘、Lens、Memory、Link、新手教程,或在 Eva 上下文中询问“下一步怎么走、先用哪个功能、入口排序、给我一个工作流”时使用;也处799skills.sh installs
6subframeapp avatardesignsubframeapp/subframeDesign and edit anything in Subframe — pages, components, snippets, design documents, the theme. Also handles deletion of those resources except theme. Always l793skills.sh installs