Deep Research Skill

Overview

This skill provides a systematic methodology for conducting thorough web research. Load this skill BEFORE starting any content generation task to ensure you gather sufficient information from multiple angles, depths, and sources.

When to Use This Skill

Always load this skill when:

Research Questions

• User asks "what is X", "explain X", "research X", "investigate X"
• User wants to understand a concept, technology, or topic in depth
• The question requires current, comprehensive information from multiple sources
• A single web search would be insufficient to answer properly

Content Generation (Pre-research)

• Creating presentations (PPT/slides)
• Creating frontend designs or UI mockups
• Writing articles, reports, or documentation
• Producing videos or multimedia content
• Any content that requires real-world information, examples, or current data

Core Principle

Never generate content based solely on general knowledge. The quality of your output directly depends on the quality and quantity of research conducted beforehand. A single search query is NEVER enough.

Research Methodology

Phase 1: Broad Exploration

Start with broad searches to understand the landscape:

1. Initial Survey: Search for the main topic to understand the overall context
2. Identify Dimensions: From initial results, identify key subtopics, themes, angles, or aspects that need deeper exploration
3. Map the Territory: Note different perspectives, stakeholders, or viewpoints that exist

Example:

Topic: "AI in healthcare"
Initial searches:
- "AI healthcare applications 2024"
- "artificial intelligence medical diagnosis"
- "healthcare AI market trends"

Identified dimensions:
- Diagnostic AI (radiology, pathology)
- Treatment recommendation systems
- Administrative automation
- Patient monitoring
- Regulatory landscape
- Ethical considerations

Phase 2: Deep Dive

For each important dimension identified, conduct targeted research:

1. Specific Queries: Search with precise keywords for each subtopic
2. Multiple Phrasings: Try different keyword combinations and phrasings
3. Fetch Full Content: Use web_fetch to read important sources in full, not just snippets
4. Follow References: When sources mention other important resources, search for those too

Example:

Dimension: "Diagnostic AI in radiology"
Targeted searches:
- "AI radiology FDA approved systems"
- "chest X-ray AI detection accuracy"
- "radiology AI clinical trials results"

Then fetch and read:
- Key research papers or summaries
- Industry reports
- Real-world case studies

Phase 3: Diversity & Validation

Ensure comprehensive coverage by seeking diverse information types:

Phase 4: Synthesis Check

Before proceeding to content generation, verify:

• Have I searched from at least 3-5 different angles?
• Have I fetched and read the most important sources in full?
• Do I have concrete data, examples, and expert perspectives?
• Have I explored both positive aspects and challenges/limitations?
• Is my information current and from authoritative sources?

If any answer is NO, continue researching before generating content.

Search Strategy Tips

Effective Query Patterns

# Be specific with context
❌ "AI trends"
✅ "enterprise AI adoption trends 2024"

# Include authoritative source hints
"[topic] research paper"
"[topic] McKinsey report"
"[topic] industry analysis"

# Search for specific content types
"[topic] case study"
"[topic] statistics"
"[topic] expert interview"

# Use temporal qualifiers — always use the ACTUAL current year from <current_date>
"[topic] 2026"   # ← replace with real current year, never hardcode a past year
"[topic] latest"
"[topic] recent developments"

Temporal Awareness

Always check <current_date> in your context before forming ANY search query.

<current_date> gives you the full date: year, month, day, and weekday (e.g. 2026-02-28, Saturday). Use the right level of precision depending on what the user is asking:

Rules:

• When the user asks about "today" or "just released", use month + day + year in your search queries to get same-day results
• Never drop to year-only when day-level precision is needed — "tech news 2026" will NOT surface today's news
• Try multiple phrasings: numeric form (2026-02-28), written form (February 28 2026), and relative terms (today, this week) across different queries

❌ User asks "what's new in tech today" → searching "new technology 2026" → misses today's news ✅ User asks "what's new in tech today" → searching "new technology February 28 2026" + "tech news today Feb 28" → gets today's results

When to Use web_fetch

Use web_fetch to read full content when:

• A search result looks highly relevant and authoritative
• You need detailed information beyond the snippet
• The source contains data, case studies, or expert analysis
• You want to understand the full context of a finding

Iterative Refinement

Research is iterative. After initial searches:

1. Review what you've learned
2. Identify gaps in your understanding
3. Formulate new, more targeted queries
4. Repeat until you have comprehensive coverage

Quality Bar

Your research is sufficient when you can confidently answer:

• What are the key facts and data points?
• What are 2-3 concrete real-world examples?
• What do experts say about this topic?
• What are the current trends and future directions?
• What are the challenges or limitations?
• What makes this topic relevant or important now?

Common Mistakes to Avoid

• ❌ Stopping after 1-2 searches
• ❌ Relying on search snippets without reading full sources
• ❌ Searching only one aspect of a multi-faceted topic
• ❌ Ignoring contradicting viewpoints or challenges
• ❌ Using outdated information when current data exists
• ❌ Starting content generation before research is complete

Output

After completing research, you should have:

1. A comprehensive understanding of the topic from multiple angles
2. Specific facts, data points, and statistics
3. Real-world examples and case studies
4. Expert perspectives and authoritative sources
5. Current trends and relevant context

Only then proceed to content generation, using the gathered information to create high-quality, well-informed content.