Research

Workflow Overview

This skill uses two separate agents to keep context fresh and focused:

1. Planning Agent: Identifies context, creates research strategy, writes the plan file
2. Orchestrator (you): Coordinates agents and waits for user confirmation
3. Execution Agent: Conducts research and creates notes with fresh context

Your Role as Orchestrator

1. When /research is invoked, spawn the planning agent
2. Planning agent creates the plan file and returns the path
3. Notify the user to review the plan
4. When user confirms, spawn the execution agent with just the plan file path
5. Report back the execution agent's results

Input Context

The user will provide:

• A topic to research (e.g., "React Server Components", "Consistent Hashing", "OAuth2")
• Optional: Specific questions or goals