external-context
Invoke parallel document-specialist agents for external web searches and documentation lookup
Skill by leejaedus
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/leejaedus-external-context
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
external-context- Description
- Invoke parallel document-specialist agents for external web searches and documentation lookup
- License
- MIT
- Instructions
- 85 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# External Context Skill Invoke parallel document-specialist agents to search the web for external documentation, references, and context. ## Overview External Context decomposes a query into parallel web search facets, each handled by an independent document-specialist agent: 1. **Decomposition** - Break query into 2-5 independent search facets 2. **Parallel Search** - Spawn document-specialist agents for each facet 3. **Synthesis** - Aggregate findings into structured context ## 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 ### 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> ... ``` ### 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.") ``` ### Synthesis After all agents complete, synthesize findings: ```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 - Each agent uses WebSearch and WebFetch tools - No magic keyword trigger - explicit invocation only
From leejaedus/pepcode, MIT.
More from leejaedus/pepcode
- 0.404score
agent-audit
leejaedus
Analyze agent usage patterns and recommend cleanup of unused agents
SkillDFreshness: DClaude Code +9 - 0.404score
cancel
leejaedus
Cancel any active PEP mode (autopilot, ralph, ultrawork, ecomode, ultraqa, swarm, ultrapilot, pipeline, team)
SkillDFreshness: DClaude Code +9 - 0.404score
distill
leejaedus
Distill session patterns into CLAUDE.md rules and project documentation
SkillDFreshness: DClaude Code +9 - 0.401score
doctor
leejaedus
Diagnose and fix pepcode installation issues
SkillDFreshness: DClaude Code +9 - 0.401score
frontend-ui-ux
leejaedus
Designer-developer for UI/UX work
SkillDFreshness: DClaude Code +9 - 0.401score
ecomode
leejaedus
Token-efficient model routing modifier
SkillDFreshness: DClaude Code +9 - 0.401score
code-review
leejaedus
Run a comprehensive code review
SkillDFreshness: DClaude Code +9 - 0.401score
analyze
leejaedus
Deep analysis and investigation
SkillDFreshness: DClaude Code +9 - 0.398score
help
leejaedus
Guide on using pepcode plugin
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Feb 15, 2026 (8 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/leejaedus/pepcode
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from leejaedus
- 0.404score
distill
leejaedus
Distill session patterns into CLAUDE.md rules and project documentation
SkillDFreshness: DClaude Code +9 - 0.404score
cancel
leejaedus
Cancel any active PEP mode (autopilot, ralph, ultrawork, ecomode, ultraqa, swarm, ultrapilot, pipeline, team)
SkillDFreshness: DClaude Code +9 - 0.404score
agent-audit
leejaedus
Analyze agent usage patterns and recommend cleanup of unused agents
SkillDFreshness: DClaude Code +9 - 0.401score
code-review
leejaedus
Run a comprehensive code review
SkillDFreshness: DClaude Code +9 - 0.401score
frontend-ui-ux
leejaedus
Designer-developer for UI/UX work
SkillDFreshness: DClaude Code +9 - 0.401score
ecomode
leejaedus
Token-efficient model routing modifier
SkillDFreshness: DClaude Code +9
Cite this page
external-context skill. Agent Mart. https://agentmart.dev/skills/leejaedus-external-context (last updated 2026-10-24)