agentleFS
aroyburman-codesaroyburman-codes/pm-skills/skills/user-research-synthesis/SKILL.md

user-research-synthesis

Skill25 starsChanged 9 months agoMITView on GitHub

Synthesize user interviews, survey results, feedback, and support tickets into structured insights. Identifies themes, pain points, and opportunities. Generates research reports ready for stakeholders.

14 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use mvp-scoping, competitive-analysis and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • shawnpangSkill

    mvp-scoping

    When the user needs to decide what to build, cut, and defer for a first release or minimum viable version of a product or feature.

    Also in 3 projects that use this

  • AnthropicSkill

    competitive-analysis

    Framework for building competitive landscape decks — market positioning, competitor deep-dives, comparative analysis, strategic synthesis. Use when the user asks for a competitive landscape, competitor analysis, peer comparison, market positioning assessment, strategic review, or investment memo deck. Also triggers on "who are the competitors to X", "benchmark X against peers", "build a market map", or any request to systematically evaluate competitive dynamics across an industry.

    Also in 4 projects that use this

  • silvainfmSkill

    launch-strategy

    When the user wants to plan a product launch, feature announcement, or release strategy. Also use when the user mentions 'launch,' 'Product Hunt,' 'feature release,' 'announcement,' 'go-to-market,' 'beta launch,' 'early access,' 'waitlist,' or 'product update.' This skill covers phased launches, channel strategy, and ongoing launch momentum.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 14 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Timeframe: When was this data collected?

    line 24
  2. Distinctive:

    Look for contradictions — users who say opposite things often reveal a segmentation opportunity

    line 84

“Common” is measured: kept by at least 6 in 10 of the 14 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

User Research Synthesis Skill

Turn raw user research data (interviews, surveys, feedback, support tickets) into structured, actionable insights.

When to Use

  • User has interview notes and needs to synthesize findings
  • User has survey results to analyze
  • User wants to identify patterns across user feedback
  • User says /user-research-synthesis followed by research data
  • Any time qualitative or quantitative user data needs structure

Framework: Research Synthesis (5 Steps)

Step 1: Organize Raw Data

  • Source type: Interviews / Surveys / Support tickets / App reviews / Usage data
  • Sample size: How many data points?
  • User segments: Who was included? Any notable gaps?
  • Timeframe: When was this data collected?

Step 2: Code & Theme

Identify recurring themes across the data:

ThemeFrequencySentimentExample Quote
[Theme 1]X of Y participantsPositive/Negative/Mixed"..."
[Theme 2]X of Y participants"..."

Group themes into categories:

  • Pain Points: What's frustrating or broken
  • Unmet Needs: What users want but don't have
  • Bright Spots: What's working well (don't break these)
  • Surprises: Unexpected findings

Step 3: Prioritize Insights

For each insight, assess:

  • Prevalence: How many users mentioned this? (1 = rare, 5 = universal)
  • Severity: How painful is this? (1 = minor annoyance, 5 = deal-breaker)
  • Actionability: Can we do something about this? (1 = hard, 5 = clear path)

Priority Score = Prevalence x Severity x Actionability

Step 4: Generate Recommendations

For the top 3-5 insights:

  • Insight: Clear statement of what we learned
  • Evidence: Supporting data points and quotes
  • Implication: What this means for the product
  • Recommendation: Specific next step (build, test, investigate further)
  • Confidence: High / Medium / Low (based on data quality)

Step 5: Research Report

Executive Summary (2-3 sentences): What we studied, what we found, what we should do.

Key Findings (3-5 bullet points): The most important insights with supporting data.

Detailed Findings: Each theme with quotes, data, and implications.

Recommendations: Prioritized action items.

Methodology & Limitations: How research was done, sample biases, confidence level.

Input Formats Supported

  • Raw interview notes: Paste them in, the skill will code and theme them
  • Survey results: Paste summary stats or raw responses
  • Support tickets: Paste representative tickets for pattern analysis
  • App store reviews: Paste reviews for sentiment and theme analysis
  • Mixed: Combine multiple sources for triangulated insights

Output Format

Generate a clean research report in markdown. Use tables for theme coding. Include direct quotes as evidence. Be specific about confidence levels and limitations.

Tips for Better Synthesis

  • Look for contradictions — users who say opposite things often reveal a segmentation opportunity
  • Pay attention to workarounds — what users hack together reveals unmet needs
  • Note what users do vs. what they say — behavioral data trumps stated preferences
  • Flag sample bias — if you only talked to power users, say so

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.