Research Workflow

Research Workflow

A structured methodology for conducting comprehensive research. This skill guides you through planning, executing, analyzing, and synthesizing research on any topic.

When to Use This Skill

Use this skill when:

• The user needs comprehensive research on a topic
• Multiple search queries are needed to fully answer a question
• Source credibility and synthesis matter
• A research report or documented findings are expected
• Keywords mentioned: research, investigate, deep dive, comprehensive analysis

Do NOT use this skill when:

• A single quick search will suffice (use web-search instead)
• The user just wants a simple fact lookup
• No synthesis or analysis is needed
• Time is extremely limited

Prerequisites

Before using this skill, ensure:

• Web search capability is available (web-search skill, WebSearch tool, or similar)
• Sufficient time for multi-phase research process
• Clear understanding of the research question or topic

Research Phases Overview

┌─────────────────────────────────────────────────────────────┐
│                    RESEARCH WORKFLOW                        │
├─────────────────────────────────────────────────────────────┤
│                                                             │
│  1. PLANNING          2. EXECUTION                          │
│  ┌──────────────┐    ┌──────────────┐                       │
│  │ Define       │    │ Run searches │                       │
│  │ questions    │───>│ Evaluate     │                       │
│  │ Plan queries │    │ sources      │                       │
│  └──────────────┘    └──────────────┘                       │
│         │                   │                               │
│         v                   v                               │
│  3. ANALYSIS          4. SYNTHESIS                          │
│  ┌──────────────┐    ┌──────────────┐                       │
│  │ Organize     │    │ Create       │                       │
│  │ findings     │───>│ coherent     │                       │
│  │ Find patterns│    │ output       │                       │
│  └──────────────┘    └──────────────┘                       │
│                                                             │
└─────────────────────────────────────────────────────────────┘

Phase 1: Planning

Before any searches, establish a clear research plan.

Step 1: Define the Research Question

Convert the topic into specific, answerable questions.

Example:

• Topic: "AI in healthcare"
• Questions:

1. What are the current applications of AI in healthcare? 2. What are the main benefits and challenges? 3. What regulations govern AI in healthcare? 4. What are the latest developments (last 6 months)?

Step 2: Identify Sub-Topics

Break down the main topic into searchable components:

• Core concepts and definitions
• Current state and applications
• Benefits and advantages
• Challenges and limitations
• Recent developments
• Future trends

Step 3: Plan Search Strategy

Create a search plan with query progression:

1. Broad queries first: Get overall landscape

• "[topic] overview"
• "[topic] introduction guide"

2. Specific queries next: Dive into details

• "[topic] specific aspect"
• "[topic] case study"

3. Verification queries last: Confirm findings

• "[topic] criticism challenges"
• "[topic] latest news [year]"

Use the template at assets/research-plan-template.md to document your plan.

Phase 2: Execution

Execute your search plan systematically.

Step 1: Run Searches

Execute queries in order, using appropriate search parameters:

# Broad overview
web-search "AI in healthcare overview 2024"

# Specific deep dive
web-search "AI diagnostic imaging applications" --depth advanced

# Current news
web-search "AI healthcare regulations 2024" --topic news --time month

Step 2: Document Each Search

For each search, record:

• Query used
• Number of results reviewed
• Key findings (2-3 bullet points)
• Notable sources
• New questions raised

Step 3: Evaluate Sources

Use the checklist at assets/source-evaluation-checklist.md to assess:

Credibility Indicators:

• Author/organization expertise
• Publication reputation
• Date of publication
• Citations and references

Quality Signals:

• Evidence-based claims
• Multiple perspectives
• Clear methodology

Step 4: Iterate as Needed

Research is not linear. Based on findings:

• Add new queries for gaps discovered
• Verify surprising claims
• Explore unexpected connections

Phase 3: Analysis

Organize and analyze your collected findings.

Step 1: Group Findings by Theme

Organize results into categories:

• Core concepts
• Current state
• Benefits/opportunities
• Challenges/risks
• Recent developments
• Expert opinions

Step 2: Identify Patterns

Look for:

• Consensus: Where do multiple sources agree?
• Conflicts: Where do sources disagree?
• Gaps: What questions remain unanswered?
• Trends: What direction is the field moving?

Step 3: Assess Confidence

For each finding, determine confidence level:

• High: Multiple authoritative sources agree
• Medium: Some evidence, limited sources
• Low: Single source or conflicting information

Step 4: Note Limitations

Document:

• What couldn't be found
• Areas needing more research
• Potential biases in sources

Phase 4: Synthesis

Create coherent, useful output from your analysis.

Step 1: Structure the Output

Choose appropriate format based on use case:

• Executive summary: Quick overview for decisions
• Full report: Comprehensive documentation
• Action items: Practical next steps

Use the template at assets/research-report-template.md.

Step 2: Write the Synthesis

Key principles:

• Lead with most important findings
• Connect related concepts
• Note confidence levels
• Acknowledge limitations
• Cite sources

Step 3: Include Actionable Elements

End with practical outputs:

• Key takeaways (3-5 points)
• Recommendations
• Further research suggestions
• Decision points

Complete Example

Scenario: Research "Best practices for API versioning"

Phase 1 - Planning:

Research Question: What are the best practices for API versioning?

Sub-questions:
1. What versioning strategies exist?
2. What are pros/cons of each?
3. What do major companies use?
4. What do experts recommend?

Search Plan:
- "API versioning strategies comparison"
- "REST API versioning best practices 2024"
- "API versioning header vs URL vs query parameter"
- "large companies API versioning approach"

Phase 2 - Execution:

Query 1: "API versioning strategies comparison"
- Found: URL versioning, header versioning, query parameter
- Key insight: URL versioning most common, header more "RESTful"
- Sources: REST API tutorial, Martin Fowler blog

Query 2: "REST API versioning best practices 2024"
- Found: Semantic versioning principles apply
- Key insight: Version only when breaking changes
- Sources: API design guides, Stack Overflow discussions

Phase 3 - Analysis:

Consensus Points:
- Version only for breaking changes
- Be consistent within an API
- Document version lifecycle

Conflicts:
- URL vs header placement (no clear winner)
- When to deprecate old versions

Gaps:
- Limited data on performance impact
- Few studies on developer experience

Phase 4 - Synthesis:

Key Findings:
1. Three main strategies exist (URL, header, query param)
2. URL versioning is most common and discoverable
3. Header versioning is considered more "pure" REST
4. Version only on breaking changes
5. Major companies split between approaches

Recommendations:
- Use URL versioning for public APIs (discoverability)
- Consider header versioning for internal APIs
- Document deprecation timeline clearly
- Use semantic versioning principles

Quality Checklist

Before completing research, verify:

• [ ] Clear research questions were defined
• [ ] Multiple queries were executed (minimum 3-5)
• [ ] Sources were evaluated for credibility
• [ ] Findings are organized by theme
• [ ] Consensus and conflicts are noted
• [ ] Confidence levels are indicated
• [ ] Limitations are acknowledged
• [ ] Output is actionable

Reference Materials

For detailed guidance, see:

• Research Methodology - In-depth methodology background
• Output Formats - Detailed format specifications

Templates

• Research Plan Template
• Research Report Template
• Source Evaluation Checklist

Limitations

This workflow has the following limitations:

• Quality depends on available web search capability
• Cannot access paywalled or restricted content
• Time-intensive for comprehensive research
• Synthesis quality depends on agent capabilities
• May miss very recent developments not yet indexed

Related Skills

• web-search: For executing individual web searches (used within this workflow)

Research Plan: [Topic]

Research Question

[Clear statement of what you want to discover]

Sub-Questions

1. [Specific question that contributes to the main question] 2. [Another specific question] 3. [Another specific question] 4. [Another specific question]

Scope

In Scope

• [What will be covered]
• [What will be covered]

Out of Scope

• [What will NOT be covered]
• [What will NOT be covered]

Search Strategy

Broad Queries (Start Here)

• "[topic] overview"
• "[topic] introduction guide"
• "[topic] current state [year]"

Specific Queries (Dive Deeper)

• "[topic] [specific aspect 1]"
• "[topic] [specific aspect 2]"
• "[topic] case study examples"

Verification Queries (Confirm Findings)

• "[topic] criticism challenges"
• "[topic] latest news [year]"
• "[topic] expert opinions"

Search Parameters

• Depth: [ ] Basic [ ] Advanced
• Topic type: [ ] General [ ] News [ ] Finance
• Time range: [ ] Any [ ] Day [ ] Week [ ] Month [ ] Year
• Domain filters: [Domains to include/exclude if any]

Success Criteria

Research is complete when:

• [ ] All sub-questions have answers
• [ ] Multiple sources confirm key findings
• [ ] Gaps and uncertainties are identified
• [ ] Output can be synthesized

Time Allocation

• Planning: [X] minutes (this phase)
• Execution: [X] minutes (searching)
• Analysis: [X] minutes (organizing)
• Synthesis: [X] minutes (output creation)
• Total: [X] minutes

Notes

[Space for additional notes, constraints, or context]

Research Report: [Topic]

Executive Summary

[2-3 paragraphs summarizing the most important findings and recommendations. Write this last after completing the full report.]

Research Question

[The primary question or topic this research addresses]

Methodology

• Queries executed: [Number]
• Sources reviewed: [Number]
• Time period: [When research was conducted]
• Search tools used: [Tools/skills used]
• Time range filter: [If any time restrictions applied]

Key Findings

Finding 1: [Title]

Summary: [Brief explanation of the finding]

Evidence: [Supporting details from sources]

Sources: [List of sources supporting this finding]

Confidence: [High/Medium/Low] - [Brief rationale]

Finding 2: [Title]

Summary: [Brief explanation of the finding]

Evidence: [Supporting details from sources]

Sources: [List of sources supporting this finding]

Confidence: [High/Medium/Low] - [Brief rationale]

Finding 3: [Title]

[Repeat structure as needed]

Source Analysis

Source Consensus

Strong Agreement On:

• [Topic where multiple sources agree]
• [Topic where multiple sources agree]

Divergent Views On:

• [Topic where sources disagree]
• [Topic where sources disagree]

Analysis

Patterns Observed

[Trends, relationships, or recurring themes across sources]

Implications

[What these findings mean for the original question]

Limitations

• [What this research couldn't determine]
• [Potential biases in sources]
• [Gaps in available information]

Recommendations

Based on this research:

1. [Recommendation Title] [Specific action and rationale]

2. [Recommendation Title] [Specific action and rationale]

3. [Recommendation Title] [Specific action and rationale]

Open Questions

Research that may be needed:

• [Question that remains unanswered]
• [Area requiring deeper investigation]
• [Emerging topic to monitor]

Appendix: Search Log

Source Evaluation Checklist

Use this checklist to assess the credibility and quality of sources during research.

Quick Assessment

For each source, answer these questions:

Authority

• [ ] Author or organization is identified
• [ ] Author has relevant expertise or credentials
• [ ] Organization is reputable in this field
• [ ] Contact information or about page is available

Accuracy

• [ ] Information can be verified elsewhere
• [ ] Claims are specific and testable
• [ ] Data sources are cited
• [ ] No obvious factual errors

Currency

• [ ] Publication date is provided
• [ ] Information is recent enough for the topic
• [ ] Updates or revisions are noted
• [ ] Links and references are still active

Purpose

• [ ] Purpose of the content is clear
• [ ] Commercial interests are disclosed
• [ ] Sponsorship or funding is transparent
• [ ] Content is not purely promotional

Objectivity

• [ ] Multiple perspectives are considered
• [ ] Counterarguments are addressed
• [ ] Language is professional, not sensational
• [ ] Facts are separated from opinions

Credibility Rating

Based on the checklist above, rate the source:

High Credibility

All or most boxes checked:

• Academic journals, peer-reviewed research
• Official documentation
• Established news organizations
• Recognized industry experts
• Government or institutional reports

Medium Credibility

Some boxes checked:

• Industry blogs with author credentials
• Trade publications
• Company documentation (for their own products)
• Well-researched opinion pieces
• Conference presentations

Low Credibility

Few boxes checked:

• Anonymous sources
• Outdated information
• Promotional content
• Unverified claims
• Sources with clear bias

Red Flags

Be cautious of sources that:

• [ ] Have no author attribution
• [ ] Make extraordinary claims without evidence
• [ ] Use emotional or sensational language
• [ ] Have obvious spelling/grammar errors
• [ ] Only cite themselves
• [ ] Are promoting a product/service
• [ ] Have a clear political/ideological agenda
• [ ] Lack publication dates
• [ ] Use clickbait titles

Source Type Guidelines

Academic/Research

• Look for peer review status
• Check citation count
• Verify institutional affiliation
• Note methodology transparency

News/Journalism

• Check publication reputation
• Look for multiple sources in article
• Distinguish news from opinion
• Check for corrections/retractions

Industry/Technical

• Verify author's role and experience
• Check for conflicts of interest
• Look for practical examples
• Note recency for fast-moving fields

Official/Government

• Confirm it's the official source
• Note any political context
• Check update frequency
• Look for underlying data

User-Generated (Forums, Q&A)

• Check answer votes/acceptance
• Verify against other sources
• Note answer recency
• Consider author reputation

Recording Your Assessment

For each key source, note:

Source: [Name/URL]
Type: [Academic/News/Industry/Official/User]
Credibility: [High/Medium/Low]
Strengths: [What makes it reliable]
Weaknesses: [Any concerns]
Use for: [What aspects of research]

Research Methodology

Detailed background on the research methodology used in this workflow.

Why Structured Research?

Unstructured research often leads to:

• Incomplete coverage of the topic
• Confirmation bias (finding what you expect)
• Poor source evaluation
• Unfocused or rambling outputs

Structured research addresses these issues through systematic phases.

The Four-Phase Model

Phase 1: Planning

Purpose: Define scope and strategy before searching

Key Activities:

• Transform vague topics into specific questions
• Identify knowledge gaps to fill
• Plan query sequence from broad to specific
• Set success criteria

Common Mistakes to Avoid:

• Skipping directly to searching
• Asking only one question
• Not planning for verification queries

Phase 2: Execution

Purpose: Gather information systematically

Key Activities:

• Execute queries in planned order
• Document findings immediately
• Evaluate source credibility
• Identify emerging questions

Search Strategy Patterns:

1. Funnel Pattern: Start broad, narrow down

• Overview → Specifics → Details

2. Multi-perspective Pattern: Cover different viewpoints

• Proponents → Critics → Neutral analysis

3. Temporal Pattern: Track evolution

• Historical → Current → Future trends

4. Geographic Pattern: Consider different contexts

• Global → Regional → Local

Phase 3: Analysis

Purpose: Make sense of gathered information

Key Activities:

• Categorize findings by theme
• Identify patterns and relationships
• Assess evidence strength
• Note gaps and conflicts

Analysis Frameworks:

1. SWOT for Topics:

• Strengths/Benefits
• Weaknesses/Challenges
• Opportunities/Trends
• Threats/Risks

2. 5 Whys for Understanding:

• Keep asking "why" to get to root causes

3. Compare/Contrast for Options:

• Side-by-side evaluation of alternatives

Phase 4: Synthesis

Purpose: Create useful, coherent output

Key Activities:

• Select appropriate output format
• Structure information logically
• Write clear, actionable content
• Include proper attribution

Synthesis Principles:

• Lead with conclusions
• Support with evidence
• Acknowledge uncertainty
• Enable action

Source Evaluation Framework

Primary vs. Secondary Sources

Primary Sources (prefer these):

• Original research papers
• Official documentation
• First-hand accounts
• Direct data

Secondary Sources (use carefully):

• News articles
• Blog posts
• Aggregated analyses
• Textbooks

Credibility Assessment

CRAAP Test:

• Currency: Is it recent enough?
• Relevance: Does it address your question?
• Authority: Is the source qualified?
• Accuracy: Is it supported by evidence?
• Purpose: What's the source's motivation?

Bias Detection

Look for:

• Funding sources
• Organizational affiliations
• Commercial interests
• Political leanings
• Omission of counterarguments

Confidence Levels

High Confidence

• Multiple authoritative sources agree
• Evidence is verifiable
• Claims are specific and falsifiable
• Recent and well-cited

Medium Confidence

• Some evidence exists
• Limited number of sources
• Evidence is indirect
• Some conflicting information

Low Confidence

• Single source only
• Evidence is anecdotal
• Significant conflicts exist
• Information is dated

Adapting to Research Types

Factual Research

Focus on: Accuracy, recency, authoritative sources Example: "What is the population of Tokyo?"

Exploratory Research

Focus on: Breadth, multiple perspectives, emerging patterns Example: "What are the impacts of remote work?"

Comparative Research

Focus on: Consistent criteria, fair representation, trade-offs Example: "React vs Vue for new projects?"

Decision Support Research

Focus on: Actionability, risk assessment, recommendations Example: "Should we migrate to microservices?"

Time Management

Quick Research (15-30 min)

• 1-2 focused questions
• 3-5 queries
• Brief synthesis
• Key takeaways only

Standard Research (1-2 hours)

• 3-5 questions
• 10-15 queries
• Full analysis
• Structured report

Deep Research (4+ hours)

• Comprehensive question set
• 20+ queries
• Detailed analysis
• Extensive documentation

Common Pitfalls

1. Premature Synthesis: Drawing conclusions too early 2. Source Homogeneity: Using only similar sources 3. Recency Bias: Ignoring historical context 4. Complexity Avoidance: Oversimplifying nuanced topics 5. Confirmation Seeking: Only finding supporting evidence

Output Formats

Detailed specifications for research output formats.

Choosing the Right Format

Executive Summary Format

When to use: Stakeholders need quick overview for decisions

Structure:

## Executive Summary: [Topic]

**Key Finding**: [One sentence main conclusion]

**Supporting Points**:
- [Point 1]
- [Point 2]
- [Point 3]

**Recommendation**: [What to do next]

**Confidence**: [High/Medium/Low]

Example:

## Executive Summary: API Rate Limiting Approaches

**Key Finding**: Token bucket algorithm is the industry standard
for its balance of simplicity and fairness.

**Supporting Points**:
- Used by major providers (Stripe, GitHub, AWS)
- Handles burst traffic gracefully
- Easy to implement and explain to users

**Recommendation**: Implement token bucket with per-user quotas

**Confidence**: High (strong consensus across sources)

Key Findings Format

When to use: Quick communication of research results

Structure:

## Key Findings: [Topic]

### Summary
[2-3 sentence overview]

### Findings

1. **[Finding Title]**
   [Brief explanation]
   *Source: [Attribution]*

2. **[Finding Title]**
   [Brief explanation]
   *Source: [Attribution]*

### Gaps/Uncertainties
- [What couldn't be determined]

Full Report Format

When to use: Comprehensive documentation needed

Structure:

# Research Report: [Topic]

## Executive Summary
[Condensed version for quick reading]

## Research Question
[What you set out to discover]

## Methodology
- Queries executed: [count]
- Sources reviewed: [count]
- Time period: [dates]
- Search tools used: [tools]

## Findings

### [Theme 1]
[Detailed findings with evidence]

**Source Analysis**:
| Source | Type | Credibility | Key Contribution |
|--------|------|-------------|------------------|
| [Name] | [Type] | [Level] | [What it added] |

### [Theme 2]
[Repeat structure]

## Analysis

### Consensus Points
[Where sources agree]

### Conflicts
[Where sources disagree]

### Patterns
[Trends or relationships observed]

## Limitations
[What this research couldn't cover]

## Recommendations
1. [Recommendation with rationale]
2. [Recommendation with rationale]

## Further Research
[Questions that remain unanswered]

## Sources
[Complete list of sources consulted]

Comparison Table Format

When to use: Evaluating multiple options

Structure:

## Comparison: [Options Being Compared]

### Quick Summary
[1 paragraph overview of conclusion]

### Comparison Matrix

| Criteria | [Option A] | [Option B] | [Option C] |
|----------|------------|------------|------------|
| [Criterion 1] | [Rating/Value] | [Rating/Value] | [Rating/Value] |
| [Criterion 2] | [Rating/Value] | [Rating/Value] | [Rating/Value] |
| [Criterion 3] | [Rating/Value] | [Rating/Value] | [Rating/Value] |

### Detailed Analysis

#### [Option A]
**Pros**: [List]
**Cons**: [List]
**Best for**: [Use case]

#### [Option B]
[Repeat structure]

### Recommendation
[Which option and why, with caveats]

Action Plan Format

When to use: Research needs to lead to implementation

Structure:

## Action Plan: [Topic/Goal]

### Background
[Brief context from research]

### Objective
[What this plan aims to achieve]

### Recommended Actions

#### Phase 1: [Name] (Immediate)
- [ ] Action item 1
- [ ] Action item 2
- [ ] Action item 3

**Dependencies**: [What's needed]
**Risks**: [What could go wrong]

#### Phase 2: [Name] (Short-term)
[Repeat structure]

### Success Metrics
- [How to measure success]

### Resources Required
- [What's needed to execute]

### Decision Points
- [When to reassess]

Markdown Formatting Tips

Headers

Use consistent hierarchy:

• # for report title (once)
• ## for major sections
• ### for subsections
• #### sparingly for details

Emphasis

• Bold for key terms and findings
• Italic for sources and asides
• Code for technical terms

Lists

• Use bullet points for unordered items
• Use numbered lists for sequences/priorities
• Use task lists - [ ] for action items

Tables

• Keep columns under 50 characters
• Align numbers right when possible
• Use for comparisons and structured data

Quotes

Use blockquotes for:

• Direct quotes from sources
• Key statistics
• Important callouts

> "85% of developers prefer URL-based API versioning"
> — Developer Survey 2024

Quality Checklist for Outputs

Before delivering any output:

• [ ] Format matches the purpose
• [ ] Structure is consistent throughout
• [ ] Key findings are prominent
• [ ] Evidence is cited
• [ ] Confidence levels are indicated
• [ ] Limitations are acknowledged
• [ ] Next steps are clear
• [ ] Formatting is clean and readable