# Research Evidence Brief

> Turn research inputs into concise evidence, patterns, confidence levels, and product decisions.

- Skill: `danielpradilla/research-evidence-brief` (Agent Skill)
- Install (CLI): `npx skillmds add danielpradilla/research-evidence-brief`
- Raw SKILL.md: https://api.skillmd.com/api/skills/danielpradilla/research-evidence-brief/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Research & Search
- Author: danielpradilla (https://skillmd.com/u/danielpradilla)
- Updated: 2026-08-19
- Page: https://skillmd.com/skills/danielpradilla/research-evidence-brief

---


# Research Evidence Brief

Use this workflow to analyze user research data and transform it into actionable insights following a structured methodology.

## Required Inputs

Ask the user for these if not provided:
- **Research data** (transcripts, notes, survey results, or summary bullets)
- **Research method** (interviews, surveys, usability tests, etc.)
- **Number of participants** and their profiles (role, context)
- **Research questions** the study aimed to answer

## Synthesis Framework

### 1. Data Collection Overview
- **Research Type**: Interviews, surveys, usability tests, etc.
- **Participant Profile**: Demographics, segments, sample size
- **Research Questions**: What we sought to learn
- **Methodology**: How data was collected

### 2. Key Themes Identification

Organize findings into themes using this structure:

**Theme Name**
- **Description**: What this theme represents
- **Prevalence**: How many participants mentioned this (e.g., "8 out of 12 participants")
- **Supporting Quotes**: 2-3 representative quotes
- **Implication**: What this means for our product

Aim for 4-8 major themes per research effort.

### 3. Pain Points Analysis

For each identified pain point:
- **Pain Point**: Clear description
- **Severity**: High/Medium/Low (based on impact and frequency)
- **Current Workaround**: How users deal with it today
- **Evidence**: Specific examples from research

### 4. Feature Requests

Categorize requests:
- **Must-Have**: Critical needs blocking user success
- **High Value**: Would significantly improve experience
- **Nice-to-Have**: Incremental improvements

For each request:
- **Request**: What users asked for
- **Frequency**: How often it came up
- **User Quote**: Representative example
- **Underlying Need**: Why they want this (dig deeper than surface request)

### 5. User Workflow Insights

Document actual workflows observed:
- **Current State**: How users accomplish tasks today
- **Pain Points**: Where they struggle
- **Ideal State**: What they wish they could do
- **Opportunities**: Where we can add value

### 6. Segmentation Insights

If research reveals distinct user segments:
- **Segment Name**: Descriptive label
- **Characteristics**: What defines this segment
- **Unique Needs**: How their needs differ
- **Size/Importance**: Relative weight for prioritization

### 7. Competitive Insights

If users mentioned competitors or alternatives:
- **Competitor/Alternative**: What they use
- **Why They Use It**: What it does well
- **Gaps**: What it doesn't do
- **Switching Barriers**: Why they don't switch fully

### 8. Recommendations

Prioritized recommendations based on insights:

**High Priority**
- Recommendation with supporting evidence
- Expected impact

**Medium Priority**
- Recommendation with supporting evidence
- Expected impact

**Low Priority / Future Consideration**
- Recommendation with supporting evidence
- Expected impact

### 9. Open Questions

Research gaps identified:
- What we still need to understand
- Suggested follow-up research
- Uncertainties requiring validation

## Analysis Guidelines

**When synthesizing interviews:**
- Look for patterns across multiple participants
- Note both what users say AND what they do
- Pay attention to emotional reactions
- Identify jobs-to-be-done, not just feature requests

**When analyzing quotes:**
- Use verbatim quotes in "quotation marks"
- Attribute quotes: [Participant ID, Role, Context]
- Select quotes that illustrate patterns, not outliers
- Include both positive and negative feedback

**When identifying themes:**
- Use descriptive names, not generic labels
- Provide evidence for each theme
- Quantify when possible ("7 out of 10 users...")
- Connect themes to business objectives

## Quality Standards

**Good Synthesis:**
- Identifies patterns, not just individual responses
- Connects insights to product decisions
- Includes supporting evidence for each claim
- Separates observations from interpretations
- Prioritizes findings by impact

**Poor Synthesis:**
- Lists every individual comment
- Lacks evidence or examples
- Makes unsupported leaps
- Focuses on solutions before understanding problems
- Ignores contradictory data