deep-research

The saved excerpt is a snapshot from review. The external source remains the complete and most current version.

---
name: deep-research
description: |
  Conduct exhaustive, citation-rich research on any topic using all available tools: web search, browser automation, documentation APIs, and codebase exploration. Use when asked to "research X", "find out about Y", "investigate Z", "deep dive into...", "what's the current state of...", "compare options for...", "fact-check this...", or any request requiring comprehensive, accurate information from multiple sources. Prioritizes accuracy over speed, cross-references claims across sources, identifies conflicts, and provides full citations. Outputs structured findings with confidence levels and source quality assessments.
---

# Deep Research

Systematic methodology for conducting exhaustive, accurate research using all available tools. Prioritizes correctness over speed.

## Core Principles

1. **Multiple sources required** — Never rely on a single source for important claims
2. **Cross-reference everything** — Verify facts appear consistently across independent sources
3. **Citation mandatory** — Every claim must have a source; no unsourced assertions
4. **Acknowledge uncertainty** — When sources conflict or are weak, say so explicitly
5. **Prefer primary sources** — Official docs > blog posts > forum answers > AI-generated content

## Available Research Tools

Use these tools in combination based on the research topic:

| Tool | Best For | Limitations |
|------|----------|-------------|
| **WebSearch** | Current events, recent information, broad topic discovery | Results may be outdated, SEO-influenced |
| **WebFetch** | Reading specific URLs, extracting detailed content | Requires known URL |
| **Playwright browser** | Interactive sites, paywalled content (if logged in), complex navigation | Slower, requires more tokens |
| **Context7/MCP docs** | Library/framework documentation | Only indexed libraries |
| **OpenAI docs MCP** | OpenAI API specifics | OpenAI only |
| **Grep/Glob/Read** | Codebase research, finding implementations | Local files only |

## Research Workflow

### Phase 1: Scope Definition

Before researching, clarify:

1. **Core question** — What specific question(s) need answering?
2. **Required depth** — Surface overview or exhaustive deep-dive?
3. **Recency requirements** — Is timeliness critical? (API versions, current events, etc.)
4. **Authoritative sources** — What would count as a definitive answer?

Ask clarifying questions if scope is ambiguous. Use AskUserQuestion for structured choices when multiple research directions are possible.

### Phase 2: Source Discovery

Cast a wide net to find relevant sources:

```
1. WebSearch with multiple query variations
   - Try 3-5 different phrasings of the core question
   - Include technical terms AND plain language
   - Search for "[topic] official documentation"
   - Search for "[topic] research paper" or "[topic] study"

2. Identify authoritative sources from results
   - Official documentation sites
   - Academic papers / research institutions
   - Industry standards bodies
   - Recognized experts in the field

3. Check specialized tools
   - Context7 for library/framework docs
   - OpenAI docs MCP for OpenAI-specific topics
   - GitHub/codebase for implementation details
```

**Source discovery heuristics:**
- Government and academic domains (.gov, .edu, .ac.uk) tend toward accuracy
- Official project documentation is authoritative for that project
- Wikipedia is a starting point, not an endpoint — follow its citations
- Stack Overflow answers need verification; check votes and dates
- Be skeptical of content farms and SEO-optimized listicles

### Phase 3: Deep Reading

For each promising source:

1. **Fetch full content** — Use WebFetch or browser to get complete text
2. **Extract key claims** — Note specific facts, figures, dates, quotes
3. **Note source metadata** — Author, date, organization, potential biases
4. **Identify citations** — What sources does this source cite?
5. **Flag conflicts** — Does this contradict