User Persona Intelligence Skill

User research often results in messy transcripts and fragmented feedback that fails to inform product decisions. This skill transforms raw qualitative data into evidence-linked persona profiles and prioritized product recommendations. It removes the guesswork by enforcing traceability and highlighting where data is thin.

What it does

• Data auditing analyzes raw inputs to identify sample size, selection bias, and critical information gaps.
• Evidence extraction captures pain points, behaviors, and motivations while maintaining strict links to source IDs or interview excerpts.
• Pattern identification groups observations into recurring themes without overstating the frequency of isolated comments.
• Need-based personas builds profiles centered on behaviors and goals rather than invented demographic fluff like age or income.
• Actionable translation converts insights into specific UX, onboarding, and messaging improvements backed by the supplied data.

How it works

1. Input raw data by providing interview transcripts, survey responses, product reviews, or support tickets.
2. Review data quality as the agent assesses the sample and flags ambiguities or missing context.
3. Analyze personas through the generated profiles that detail decision criteria, workarounds, and product expectations.
4. Implement recommendations based on the prioritized list of product and messaging opportunities.

Frameworks & tools

This skill is framework-agnostic and processes raw text, CSV exports, or Markdown notes. It applies Jobs-to-be-Done (JTBD) principles to segment users by intent and outcomes rather than superficial attributes.

Why this beats prompting it yourself

Generic prompts often hallucinate demographic details or invent "average" users that don't exist. This skill enforces strict evidence-linking, ensuring every persona attribute is tied to a specific source ID and labeled with a confidence score.

Use cases

• Feature prioritization by identifying which pain points are shared across multiple segments.
• Onboarding optimization based on documented user barriers and decision triggers.
• Messaging refinement using direct evidence of user motivations and objections.
• Research synthesis after a round of user interviews to find actionable patterns.

Known limitations

Does not perform statistical analysis or imply market-wide significance. Requires supplied research data to function; it will not invent market trends or external benchmarks.