Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From pm-copilot
Use this skill when the user asks to "create user personas", "develop personas", "write a persona", "define our users", "user profile", "who is our user", "help me define the target user", "create a user archetype", or wants to build or update structured user persona definitions grounded in research or known user characteristics.
npx claudepluginhub productfculty-aipm/pm-copilot-by-product-facultyHow this skill is triggered — by the user, by Claude, or both
Slash command
/pm-copilot:persona-developmentThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are building user personas grounded in real user behavior and JTBD thinking — not demographic templates. A persona is useful only if it changes what you build or how you communicate. If a persona doesn't make a decision obvious, it's not sharp enough.
Generates behavioral user personas from product descriptions, user data, or research notes. Outputs 2-4 ranked personas with goals, pain points, behaviors, and product implications to personas-[product].md.
Builds interactive user personas by researching audiences via web searches/fetches, profiling demographics/behaviors/motivations, and linking to product features/user stories.
Create refined user personas from research data with demographics, goals, frustrations, and behavioral patterns. Use when synthesizing user research into actionable persona profiles for design decisions.
Share bugs, ideas, or general feedback.
You are building user personas grounded in real user behavior and JTBD thinking — not demographic templates. A persona is useful only if it changes what you build or how you communicate. If a persona doesn't make a decision obvious, it's not sharp enough.
Frameworks: Bob Moesta / JTBD (demand-side thinking), Hilary Gridley (AI-embracer vs. skeptic segmentation), Lean Startup (build-measure-learn).
Read memory/user-profile.md for product context and any existing persona notes. Read context/product/personas.md if it exists — understand what's already there and whether it needs updating or creating from scratch.
If research data exists (interview notes, support tickets, survey responses), use it. If not, build a research-grounded hypothesis persona that can be validated.
A good persona answers these questions from the user's perspective:
Who are they? (Role, situation, context — not demographics) What are they trying to do? (The JTBD — what progress are they making?) What's stopping them? (Pain, friction, workaround) What does success look like for them? (Desired outcome — functional, emotional, social) How do they currently handle this? (Current hire — the status quo) What would make them switch? (Switch trigger) How do they feel about AI assistance? (Embracer, neutral, or skeptic)
Write each persona with a demand-side framing:
Triggering situation: "When [specific situation arises], this persona needs to [make progress]."
This is more actionable than "They are 32 years old and work at a startup." The triggering situation tells you when the persona needs the product, not just who they are.
Based on Hilary Gridley's segmentation: "The most meaningful segmentation for AI products is attitudinal: AI embracers vs. AI skeptics."
For each persona, identify their position:
AI Embracer:
AI Skeptic / Cautious:
AI Neutral:
For each persona, fill in:
Name: [Descriptive label — e.g. "The Founding PM" not "Sarah"] Triggering situation: [When they need this product] JTBD: [What progress they're trying to make — functional, emotional, social] Current hire: [What they use today; what's wrong with it] Switch trigger: [What would make them look for something different] Pains: [3 specific frustrations with the current solution] Gains: [3 specific outcomes a new solution would enable] AI stance: [Embracer / Neutral / Skeptic] Onboarding path: [How to onboard this persona given their AI stance] Representative quote: [A real or composite quote that captures their core frustration] What makes them a bad fit: [Who this product isn't for — prevents over-targeting]
Write one anti-persona: the user who looks like a fit but isn't. This prevents wasted sales and support effort, and helps the team say no to feature requests from this segment.
Produce:
Offer to save to context/product/personas.md and update memory/user-profile.md with any new persona insights.