persona-research

Research and maintain evidence-backed persona models with explicit source tracking and validation.

Updated Sep 6, 2026
One-click install
npx skills add https://github.com/rickvang/Persona-Library --skill persona-research-rickvang
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: persona-research
Source: https://github.com/rickvang/Persona-Library/tree/main/.agents/skills/persona-research
Command: npx skills add https://github.com/rickvang/Persona-Library --skill persona-research-rickvang

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Building personas often produces fictional biographies or unsupported claims. This Skill structures persona research so every claim is classified as observed evidence, synthesis, or hypothesis, with preserved source metadata and explicit uncertainty. ## Core Features & Use Cases - Evidence-graded research: Separates observed evidence, synthesis, and hypotheses, and preserves publisher, URL, dates, and population context for every source. - Structured persona modeling: Keeps workflows, activities, skills, and tool candidates distinct, with tiers, friction, success signals, and confidence levels. - Controlled updates: Classifies new sources as confirms, extends, qualifies, or contradicts, and requires explicit authorization before any live record change. - Use Case: A product manager researching a new user role can produce a record-shaped persona proposal with an evidence table, workflow map, tool hypotheses, and a validation plan—without mutating any library data. ## Quick Start Use $persona-research to research this role with explicit evidence and uncertainty.

Frequently Asked Questions about persona-research

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I research a persona with evidence-backed claims?▼

Define the role and decision the persona supports, gather primary and reputable sources, then classify every material claim as observed evidence, synthesis, or hypothesis. Preserve source metadata including publisher, URL, date checked, and population context for each claim.

How do I handle a new source that contradicts an existing persona?▼

Classify the source's relationship to each affected claim as confirms, extends, qualifies, or contradicts. Update only supported claims, preserve the old claim and revision rationale when a contradiction remains unresolved, and keep the conflict visible as an open question.

Can persona research update live library records automatically?▼

No. Research defaults to read-only and produces a brief or proposal. A live record change requires explicit authorization, a confirmed target, scoped impact review, validation, and a handoff to the persona-reconciliation adapter.

What is the difference between a workflow and an activity in persona modeling?▼

A workflow is a trigger-to-outcome path with steps, decisions, and handoffs. An activity is a recurring or interrupt-driven unit of work with its own cadence and friction that can belong to multiple workflows, and the two must remain separately inspectable.

When should a tool be linked to a persona?▼

Only when a material workflow or skill depends on execution capability. Tools named only by role inference stay labeled as representative hypotheses; canonical tool-record work routes to tool-record-maintenance rather than being created as a side effect.