Supported formats:
- Interview transcripts (.txt, .md, .docx)
- Survey exports (.csv, .xlsx)
- Support ticket exports (.csv, .json)
- User feedback logs (.json, .csv)

## Analysis Framework

### Step 1: Initial Coding
For each transcript:
1. Read through completely for context
2. Highlight significant statements
3. Apply initial codes (open coding)
4. Note participant metadata

### Step 2: Pattern Recognition
Across transcripts:
1. Group similar codes
2. Identify recurring themes
3. Note frequency of mentions
4. Track contradicting evidence

### Step 3: Insight Generation
For each theme:
1. Define the insight clearly
2. List supporting evidence (3+ quotes)
3. Assess confidence level
4. Note actionable implications

{
  "transcript_id": "INT-001",
  "participant": {
    "id": "P001",
    "segment": "power_user",
    "tenure": "2_years"
  },
  "findings": [
    {
      "code": "onboarding_friction",
      "theme": "First-time experience",
      "quote": "I had no idea where to start...",
      "timestamp": "00:12:34",
      "sentiment": "negative",
      "intensity": "high"
    }
  ],
  "summary": {
    "key_pain_points": [],
    "unmet_needs": [],
    "positive_experiences": [],
    "feature_requests": []
  }
}

## Affinity Diagram Process

### 1. Capture Observations
- One observation per note
- Include source attribution
- Maintain original language

### 2. Group Bottom-Up
- Cluster similar observations
- Name each cluster
- Create hierarchy of clusters

### 3. Output Format

# Theme: [Theme Name]
## Subtheme: [Subtheme Name]
- Observation 1 (P001, INT-001)
- Observation 2 (P003, INT-003)
- Observation 3 (P007, INT-007)

### Evidence Strength
- Strong: 5+ supporting observations
- Moderate: 3-4 supporting observations
- Emerging: 2 supporting observations

## Insight Template

### Insight ID: INS-001
**Statement**: [Clear, actionable insight statement]

**Theme**: [Parent theme]
**Confidence**: [High/Medium/Low]
**Evidence Count**: [Number of supporting data points]

### Supporting Evidence
| Source | Quote | Participant |
|--------|-------|-------------|
| INT-001 | "..." | P001 |
| INT-003 | "..." | P003 |
| SUR-045 | "..." | R045 |

### Implications
- Product: [Product implications]
- Design: [Design implications]
- Engineering: [Technical considerations]

### Recommendations
1. [Specific recommendation]
2. [Specific recommendation]

### Contradicting Evidence
- [Note any contradicting findings]

const researchSynthesisTask = defineTask({
  name: 'research-synthesis',
  description: 'Synthesize user research into actionable insights',

  inputs: {
    transcriptPaths: { type: 'array', required: true },
    researchQuestion: { type: 'string', required: true },
    outputFormat: { type: 'string', default: 'markdown' },
    minEvidenceThreshold: { type: 'number', default: 3 }
  },

  outputs: {
    themes: { type: 'array' },
    insights: { type: 'array' },
    personas: { type: 'array' },
    recommendations: { type: 'array' }
  },

  async run(inputs, taskCtx) {
    return {
      kind: 'skill',
      title: 'Synthesize user research findings',
      skill: {
        name: 'user-research-synthesis',
        context: {
          operation: 'full_synthesis',
          transcriptPaths: inputs.transcriptPaths,
          researchQuestion: inputs.researchQuestion,
          outputFormat: inputs.outputFormat,
          minEvidenceThreshold: inputs.minEvidenceThreshold
        }
      },
      io: {
        inputJsonPath: `tasks/${taskCtx.effectId}/input.json`,
        outputJsonPath: `tasks/${taskCtx.effectId}/result.json`
      }
    };
  }
});

## JTBD Statement Format

When [situation/context],
I want to [motivation/goal],
So I can [expected outcome].

### Extraction Process
1. Identify triggering situations in transcripts
2. Extract stated and unstated motivations
3. Map to desired outcomes
4. Categorize: Functional, Emotional, Social jobs

# Research Synthesis Report

## Executive Summary
[2-3 sentence overview]

## Research Methodology
- **Method**: [Interviews/Surveys/etc.]
- **Participants**: [N participants]
- **Duration**: [Date range]
- **Research Questions**: [Key questions]

## Key Themes
### Theme 1: [Name]
[Description and evidence]

### Theme 2: [Name]
[Description and evidence]

## Top Insights
1. **Insight**: [Statement]
   - Evidence: [Count]
   - Confidence: [Level]
   - Recommendation: [Action]

## Persona Implications
[How findings affect personas]

## Recommended Actions
1. [Action item]
2. [Action item]

## Appendix
- Full coding scheme
- Participant demographics
- Raw data references