deep-researcher
The deep-researcher skill conducts systematic, multi-stage investigations on complex topics by defining research parameters, performing exploratory searches, diving deep into key areas, cross-referencing findings across sources, and synthesizing results into structured reports. Use this skill when you need comprehensive, well-validated information on unfamiliar subjects that require multiple perspectives, historical context, and current developments organized into actionable insights.
git clone --depth 1 https://github.com/lofcz/LLMTornado /tmp/deep-researcher && cp -r /tmp/deep-researcher/src/LlmTornado.Tests/Static/Files/Skills/deep-researcher ~/.claude/skills/deep-researcherSKILL.md
## Deep Research Workflow Copy this checklist and track your progress: ``` Deep Research Progress: - [ ] Step 1: Define research scope and objectives - [ ] Step 2: Conduct initial exploratory research - [ ] Step 3: Deep dive into key areas - [ ] Step 4: Cross-reference and validate findings - [ ] Step 5: Synthesize and analyze information - [ ] Step 6: Generate structured research report ``` ## **Step 1: Define research scope and objectives** Clearly establish the research parameters: - **Main research question**: What is the primary question or topic to investigate? - **Scope boundaries**: What aspects should be included or excluded? - **Depth requirements**: How detailed should the research be? - **Expected deliverables**: What format and structure for the final output? - **Key areas of focus**: What specific subtopics or angles to explore? Document these parameters before proceeding to ensure focused and efficient research. ## **Step 2: Conduct initial exploratory research** Begin with broad reconnaissance to map the landscape: - **Search for overview information**: Use search tools to find general information, definitions, and context - **Identify key sources**: Look for authoritative sources, recent publications, and expert opinions - **Note initial findings**: Create a preliminary list of important concepts, terms, and themes - **Discover related topics**: Identify adjacent areas that may be relevant - **Assess information gaps**: Note what information is readily available vs. what needs deeper investigation Create an initial research map with main themes and subtopics identified. ## **Step 3: Deep dive into key areas** For each identified key area, conduct detailed investigation: - **Targeted searches**: Use specific queries for each subtopic - **Multiple perspectives**: Seek diverse viewpoints and approaches - **Technical details**: Gather specific data, statistics, methodologies, or technical specifications - **Historical context**: Understand the evolution and background - **Current state**: Identify latest developments and trends - **Future outlook**: Look for predictions, projections, or emerging patterns Document findings systematically, noting sources and credibility indicators. ## **Step 4: Cross-reference and validate findings** Ensure accuracy and reliability: - **Verify key facts**: Cross-check important information across multiple sources - **Identify contradictions**: Note where sources disagree and investigate why - **Assess source credibility**: Evaluate the authority and reliability of information sources - **Check recency**: Ensure information is current and relevant - **Look for consensus**: Identify where experts or multiple sources agree - **Flag uncertainties**: Mark areas where information is unclear or disputed Create a validated knowledge base with confidence levels for different findings. ## **Step 5: Synthesize and analyze information** Transform collected data into insights: - **Identify patterns**: Look for common themes, trends, or relationships - **Draw connections**: Link concepts across different sources and subtopics - **Generate insights**: Develop original observations based on the research - **Compare and contrast**: Analyze similarities and differences between approaches or perspectives - **Evaluate implications**: Consider the significance and consequences of findings - **Address the research question**: Directly answer the original question with evidence Build a coherent narrative that goes beyond mere compilation of facts. ## **Step 6: Generate structured research report** Create a comprehensive, well-organized final report: ### Report Structure: 1. **Executive Summary** - Brief overview of research question - Key findings (3-5 main points) - Main conclusions 2. **Introduction** - Research scope and objectives - Methodology overview - Key areas explored 3. **Main Body** (organized by themes/topics) - Detailed findings for each key area - Supporting evidence and examples - Multiple perspectives where relevant - Data and statistics 4. **Analysis & Synthesis** - Patterns and connections identified - Cross-cutting themes - Insights and interpretations - Implications of findings 5. **Conclusions** - Direct answers to research questions - Summary of most significant findings - Limitations of the research 6. **Sources & References** - List of key sources consulted - Credibility assessment where relevant ### Report Quality Standards: - **Clarity**: Use clear, precise language - **Structure**: Logical organization with clear headings - **Evidence-based**: Support claims with specific references - **Balanced**: Present multiple viewpoints fairly - **Depth**: Go beyond surface-level information - **Actionable**: Provide insights that can inform decisions or understanding ## Best Practices ### Research Strategies: - **Iterative approach**: Refine research questions as understanding deepens - **Breadth before depth**: Start broad, then narrow focus to important areas - **Follow the thread**: Let interesting findings guide additional research paths - **Document as you go**: Keep organized notes throughout the process - **Question assumptions**: Challenge initial hypotheses with evidence ### Information Quality: - **Prefer primary sources**: When possible, go to original sources rather than summaries - **Recent is better**: Prioritize current information, especially for fast-moving topics - **Multiple sources**: Don't rely on a single source for important facts - **Expert opinion**: Seek out recognized authorities in the field - **Data over anecdotes**: Prefer statistical evidence to individual stories ### Analysis Techniques: - **SWOT analysis**: Strengths, Weaknesses, Opportunities, Threats - **Compare/Contrast**: Systematic comparison of different approaches or perspectives - **Timeline analysis**: Understanding historical development and trends - **Stakeholder analy
A step-by-step guide to synthesizing research from multiple sources into a coherent summary.
Generates a structured skill template based on provided specifications.
This skill provides a comprehensive context extraction system for large codebases. It intelligently analyzes code structure, dependencies, and relationships to extract relevant context for understanding, debugging, or modifying code.
Compiles comprehensive company product context from PDF documents, web research, and industry knowledge
Generates comprehensive code tutorials on LlmTornado API formatted for Medium publication with examples, explanations, and best practices.
Extracts text and tables from PDF files, fills forms, and merges documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction.
Generates Anthropic Skills with complete workflow including GitHub PR creation and local download verification.
Generates complete Anthropic SKILL packages with proper structure, documentation, and automated download verification.