Research External

This is a structured research assistant that pulls documentation and best practices from external sources, not your codebase. You invoke it with a focus mode: library for API docs via nia-docs, best-practices for current recommendations via Perplexity, or general for multi-source sweeps. It walks you through questions if you don't pass arguments, asks how deep you want to go, then writes findings to a markdown file or preps a handoff for implementation. The workflow is methodical, chains multiple MCP tools depending on your focus, and explicitly targets 2024-2025 timeframes for best practices. Useful when you need to get up to speed on a package, compare alternatives, or gather context before coding. It's thorough but not chatty, just structured research output.

skills.sh installs: 503
GitHub stars: 3.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add parcadei/continuous-claude-v3 --skill research-external --agent claude-code

Installs into .claude/skills of the current project.

Files

External Research Workflow

Research external sources (documentation, web, APIs) for libraries, best practices, and general topics.

Note: The current year is 2025. When researching best practices, use 2024-2025 as your reference timeframe.

Invocation

/research-external <focus> [options]

Question Flow (No Arguments)

If the user types just /research-external with no or partial arguments, guide them through this question flow. Use AskUserQuestion for each phase.

Phase 1: Research Type

question: "What kind of information do you need?"
header: "Type"
options:
  - label: "How to use a library/package"
    description: "API docs, examples, patterns"
  - label: "Best practices for a task"
    description: "Recommended approaches, comparisons"
  - label: "General topic research"
    description: "Comprehensive multi-source search"
  - label: "Compare options/alternatives"
    description: "Which tool/library/approach is best"

Mapping: