user-research-synthesis
Skill4 starsChanged 3 months agoMITView on GitHub
Turn raw user data into ranked design insights. Use when synthesize interviews, user feedback, what did users say, research findings, analyze survey, or interview notes.
14 other projects use a version of this.
Adopted by
Most recently taken up by
- insight68/Skillstheir own version, first seen Nov 8, 2026
- RBraga01/builder-producttheir own version, first seen Nov 1, 2026
- codeApe-7/ai-agent-workflowGrouptheir own version, first seen Nov 1, 2026
- Maudeunfledged834/startup-founder-skillstheir own version, first seen Oct 25, 2026
- MaxMiksa/Autonomous-Companytheir own version, first seen Oct 15, 2026
- akachandan1/proofstacktheir own version, first seen Oct 11, 2026
Used with
Projects with it also use competitive-analysis and launch-strategy.
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.
AnthropicSkillcompetitive-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
silvainfmSkilllaunch-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
Other versions14 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 14
- MaxMiksa/Auto-Company★ 3.2ksame name
- MaxMiksa/Autonomous-Company★ 3.2ksame name
- shawnpang/startup-founder-skills★ 331same name
- nicepkg/auto-company★ 188same name
- NikitaDmitrieff/auto-co-meta★ 43same name
- aroyburman-codes/pm-skills★ 25same name
- codeApe-7/ai-agent-workflowGroup★ 18same name
- Maudeunfledged834/startup-founder-skills★ 8same name
- insight68/Skills★ 5same name
- RBraga01/builder-product★ 2same name
4 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository46 other files it gives its agents.
- accessibility-reviewSkill
- accessibility-runtime-auditSkill
- adaptive-component-behaviorSkill
- ai-feature-ux-patternsSkill
- behavioral-pricing-psychologySkill
- business-model-readingSkill
- business-model-thinkingSkill
- cognitive-load-heatmap-predictionSkill
- component-style-guideSkill
- cross-functional-reviewSkill
- dark-mode-theming-systemSkill
- dashboard-layout-patternsSkill
- dashboard-scaffolding-contractSkill
- design-drift-detectorSkill
- design-system-builderSkill
- design-to-code-handoffSkill
- design-tokensSkill
- error-boundary-resilience-designSkill
- flow-based-functional-testingSkill
- growth-impact-reviewSkill
- i18n-localization-strategySkill
- information-architectureSkill
- interactive-element-auditSkill
- kinematic-motion-choreographySkill
- micro-interaction-motion-designSkill
- module-registry-syncSkill
- mvp-scopingSkill
- perceived-performance-loadingSkill
- prd-traceability-matrixSkill
- product-discoverySkill
- product-strategySkill
- project-health-diagnosticsSkill
- qa-feedback-loop-orchestratorSkill
- responsive-breakpoint-strategySkill
- responsive-qa-auditSkill
- route-integrity-checkerSkill
- security-privacy-reviewSkill
- stakeholder-requirement-mappingSkill
- touch-gesture-interactionSkill
- typography-systemSkill
- usability-heuristics-checkSkill
- user-flow-mappingSkill
- ux-chaos-monkeySkill
- visual-hierarchy-reviewSkill
- visual-responsive-regression-testingSkill
- visual-style-extractorSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 14 edited versions we read keep these.
1
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
- Distinctive: line 14
Never analyze qualitative complaints in a vacuum.
“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.
Files
Synthesis is the translation of raw user noise into ranked, actionable product decisions. Summarizing repeats what people said; synthesis uncovers the underlying behavioral patterns that dictate what you must build.
1. Collect & classify data by type
Separate input signals into two complementary streams:
- Qualitative Data: User interview transcripts, open-ended support tickets, usability test session notes, observational recordings.
- Quantitative Telemetry: Funnel drop-off percentages, feature click rates, search query logs, NPS scores, time-on-task metrics.
2. Triangulate qualitative insights with quantitative baselines
Never analyze qualitative complaints in a vacuum. Pair the "What" with the "Why":
- Example: "Users abandon at Checkout Step 2" (Quantitative: 42% drop-off) + "I didn't trust that my credit card info was secure without a lock badge" (Qualitative: 7/10 users) = Single High-Confidence Insight.
3. Extract atomic observations
Break transcripts and notes into atomic observations (1 observation = 1 discrete action, quote, or blocker).
- Valid atomic observation: "User #4 clicked the disabled 'Next' button 5 times because the required checkbox was scrolled out of view."
- Invalid vague summary: "User was confused by the form."
4. Affinity clustering & thematic grouping
Group atomic observations into emerging behavioral themes (e.g. Mental Model Mismatch, Discoverability Gap, Trust Deficit, Operational Friction).
5. Weigh by Frequency × Severity Matrix
Plot themes on a 2×2 grid:
- Frequency: Isolated (1 user) ↔ Pervasive (≥ 70% of sample).
- Severity: Annoyance (cosmetic) ↔ Task Blocker (churn risk / fatal drop-off). Themes in Pervasive + Task Blocker are critical release-blocking priorities.
6. Derive actionable Insight Statements
Formulate structured insight statements:
"[Target Segment] experiences [struggle/behavior] because [underlying root cause], which means we should [specific design/architectural remediation]."
Completion Criteria
- Raw input parsed into discrete atomic observations (not premature conclusions)
- Qualitative feedback triangulated with quantitative telemetry where available
- Frequency × Severity matrix calculated for all identified clusters
- Insight statements follow the
[Segment] + [Behavior] + [Root Cause] + [Remediation]formula - Prioritized design recommendations ranked by impact and implementation effort
Output Format
A research_synthesis_report.md artifact containing the raw observation catalog, thematic clusters, Frequency × Severity matrix, and ranked actionable design recommendations.
Anti-patterns
- Treating one vocal enterprise customer's feature demand as a universal product pattern.
- Reporting raw transcript quotes without extracting the underlying root need.
- Confusing feature requests ("they asked for an Excel export") with user needs ("reporting is fragmented across tools").
- Ignoring quantitative baseline data when qualitative feedback contradicts real telemetry behavior.
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
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.

