external-context
Invoke parallel document-specialist agents for external web searches and documentation lookup
Before you install
- Last update
- Files in folder
- 1
- Scripts
- No script files found
- SKILL.md size
- 2.1 KB (about 545 tokens of context each time it loads)
- License
- MIT
- Source on GitHub
- Yeachan-Heo/oh-my-claudecode
Skills are plain text instructions the agent follows, sometimes with scripts. Check the source, prefer repositories with many installs and stars, and read any script it ships.
Install
npx skills add Yeachan-Heo/oh-my-claudecode@external-contextRuns in a terminal with Node.js 18 or newer. Add -y to skip the prompts and -g to install for every project instead of this one.
Install for your agent
npx skills add Yeachan-Heo/oh-my-claudecode@external-context --agent claude-code -y- Project install writes to
.claude/skills/external-context- Global install writes to
~/.claude/skills/external-context
Start a new session afterwards so the agent picks the skill up. In Claude Code you can also call it directly with /external-context.
What it does
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 Protocol Step 1: Facet Decomposition Given a query, decompose into 2-5 independent search facets: Step 2: Parallel Agent Invocation Fire independent facets in parallel via Task tool: Maximum 5 parallel document-specialist agents. Step 3: Synthesis Output Format Present synthesized results in this format: Configuration - Maximum 5 parallel document-specialist agents - No magic keyword trigger - explicit…
Excerpt from the skill's own SKILL.md. Read the full file on GitHub before installing: skills run with your agent's permissions.
Categories
Related skills
- ai-slop-cleaner
Yeachan-Heo/oh-my-claudecode
Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode
- ralplan
Yeachan-Heo/oh-my-claudecode
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution
- hud
Yeachan-Heo/oh-my-claudecode
Configure HUD display options (layout, presets, display elements)
- deepinit
Yeachan-Heo/oh-my-claudecode
Deep codebase initialization with hierarchical AGENTS.md documentation
- autopilot
Yeachan-Heo/oh-my-claudecode
Full autonomous execution from idea to working code
- deep-interview
Yeachan-Heo/oh-my-claudecode
Socratic deep interview with mathematical ambiguity gating before explicit execution approval