research

# Research Skill

Discovery-driven, exhaustive research using parallel LLM agents for comprehensive, current information gathering.

## Core Principles

**CRITICAL:** These principles define how research works.

### 1. Discovery-Driven, Not List-Driven
- Find the BEST sources, not just known sources
- Don't limit to predefined source lists
- The internet is huge - explore it
- Value is in finding what user doesn't already know

### 2. Context-Aware
- Load user's domain context from preferences
- Research is RELEVANT to their specific situation
- But context doesn't limit WHERE you search

### 3. Exhaustive
- No time limits - can take 30 minutes to 3 hours
- Don't stop at first page of results
- Keep going until topic is exhausted
- Follow promising links deeper

### 4. Multimedia
- Not just text articles
- Videos (YouTube), TikTok, podcasts
- Real user experiences from forums

### 5. Highly Cited
- Every claim must have a citation
- Multiple sources for important claims
- Note when sources conflict

### 6. Clarifying Questions First
Before diving into research, ask deep, thought-provoking questions to understand:
- What's the actual goal? (not just the surface request)
- What constraints exist? (budget, time, preferences)
- What would success look like?
- What have they already tried or considered?
- Are there hidden requirements?

Example: "Research Japan ski trip" should prompt:
- "What skill level are you and Carrie? Blue runs, black diamonds?"
- "Is après-ski culture important, or pure skiing focus?"
- "Do you need English-friendly areas, or comfortable with Japanese-only?"
- "Any specific dates that are fixed vs flexible?"
- "Besides skiing, anything else you want to do (onsen, food tours)?"

## Domain Context Loading

Research automatically loads relevant context from preferences based on detected domain.

### How It Works
1. Detect domain from query (travel, shopping, work, etc.)
2. Load `research_domains.[domain]` from preferences
3. Load referenced context