agentleFS
JipletJiplet/transformation-os/skills/product/pm-proto-persona/SKILL.md

pm-proto-persona

Skill2 starsChanged 5 months agoMITView on GitHub

Create an initial hypothesis-driven user persona from available research, market data, and stakeholder knowledge. Use when the user asks to "create a persona", "define our target user", "build a proto-persona", or needs to align a team on who they're building for before extensive research is complete.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After you've done extensive user research (create a validated persona instead)

    line 29
  2. Distinctive:

    Creating 10 personas upfront: start with 1-2

    line 93
  3. Very specific:

    Fabricating quotes: use real quotes or mark as [PLACEHOLDER—NEEDS RESEARCH]

    line 94

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Purpose

Create an initial, assumption-based persona profile that synthesises available user research, market data, and stakeholder knowledge into a working hypothesis about your target user. Use this to align teams early in product development, guide initial design decisions, and identify gaps in understanding that require validation through research.

This is not a validated persona — it's a "proto" (prototype) persona that evolves as you learn more.

Key Concepts

Proto vs. Validated Persona

Proto-PersonaValidated Persona
Created in hours/daysCreated over weeks/months
Based on assumptions + limited researchBased on extensive user research
Used to align teams earlyUsed to guide detailed design
Evolves rapidlyStable over time

When to Use

  • Early-stage product development (before extensive user research)
  • Kicking off a new feature or pivot
  • Aligning stakeholders on target users
  • Identifying research gaps

When NOT to Use

  • After you've done extensive user research (create a validated persona instead)
  • As a substitute for quantitative data

Application

Step 1: Gather Available Context

Collect before creating:

  • User research: interview notes, survey results, support tickets
  • Analytics: usage data, demographics, behavioural patterns
  • Market data: industry reports, competitor user bases
  • Stakeholder insights from sales/support/CS teams

If missing context: Note gaps — don't fabricate.

Step 2: Build the Persona

### Name
- [Alliterative, memorable name — e.g., "Manager Mike", "Startup Sarah"]

### Bio & Demographics
- [Age range]
- [Geographic location]
- [Social status]
- [Online presence]
- [Leisure activities]
- [Career status — job title, industry, seniority]

### Quotes
- "[Quote revealing how they think or speak]"
- "[Quote revealing frustrations or motivations]"
- "[Quote revealing attitudes or beliefs]"

### Pains
- [Pain point 1 — be specific, not vague]
- [Pain point 2]
- [Pain point 3]

### What is This Person Trying to Accomplish?
- [Observable behaviour or outcome 1]
- [Observable behaviour or outcome 2]
- [Observable behaviour or outcome 3]

### Goals
- [Short-term goal]
- [Long-term / aspirational goal]
- [Personal goal if relevant]

### Attitudes & Influences
- **Decision-Making Authority:** [Yes/No + context]
- **Decision Influencers:** [Who influences them — peers, analysts, managers]
- **Beliefs & Attitudes:** [Beliefs that impact adoption of your product]

Step 3: Validate and Iterate

  • Share with the team: does this persona resonate?
  • Tag assumptions: add [ASSUMPTION—VALIDATE] where uncertain
  • Plan research: use proto-persona to guide who to interview next
  • Evolve as you learn; graduate to a validated persona when confidence is high

Common Pitfalls

  • Demographics without behaviour: "28, lives in NYC" → add behavioural context
  • Treating as fact: tag assumptions explicitly
  • Creating 10 personas upfront: start with 1-2
  • Fabricating quotes: use real quotes or mark as [PLACEHOLDER—NEEDS RESEARCH]
  • Never validating: plan research sprints to test key assumptions

Related Skills

  • pm-problem-statement — Persona informs the "I am" section
  • pm-user-story — Stories use "As a [persona]"
  • pm-storyboard — Persona is the main character

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.