Persona creation
Skill Dragoon0x/everything-design-taste/skills/persona-creation
A taste system for AI agents. 288 skills, 80 agents, 12 rules, and 8 hooks that turn generic AI output into work with genuine design quality. Anti-slop detection, typography craft, color systems, brand voice, product strategy, and 50+ specialized reviewers across UI, industry, platform, and content domains.
npx -y skills add Dragoon0x/everything-design-taste --skill persona-creationAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 6 stars6 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
User persona development, proto-personas, and avoiding persona fiction.
SKILL.md
1.2 KB, as published. Nobody here has run it
Persona Creation
Persona Types
Research-Based Personas
- Built from actual user research (interviews, surveys, analytics).
- Based on patterns across multiple users, not one person.
- Updated as you learn more.
Proto-Personas
- Hypothesis-based, created before research.
- Used to align the team on assumptions.
- Must be validated (or invalidated) through research.
Persona Components
- Name and photo (make them feel real, but don't use real people).
- Context (situation, not demographics).
- Goals (what they're trying to achieve).
- Pain points (what frustrates them today).
- Behaviors (how they currently solve the problem).
- Quote (something they might actually say).
Anti-Patterns
- Personas based on demographics alone ("Sarah, 34, marketing manager" tells you nothing about behavior).
- Personas nobody references after creation.
- Too many personas (3-5 maximum for a product).
- Fictional personas presented as research-backed.
- Personas that confirm what the team already believes.