agentleFS
patonkikhpatonkikh/APES/skills/product/persona-generator/skill.md

persona-generator

Skill3 starsChanged 4 months agoMITView on GitHub

Create evidence-based user personas focused on behaviors, goals, and pain points — not demographics alone. Use when working on product discovery, PRDs, user stories, OKRs, or backlog planning.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create evidence-based user personas focused on behaviors, goals, and pain points — not demographics alone.

    line 14
  2. Distinctive:

    Use empathy map before writing narrative profile.

    line 112

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Persona Generator

Purpose

Create evidence-based user personas focused on behaviors, goals, and pain points — not demographics alone.

Input: Target user segment, problem statement (optional), research data (optional)
Output: Persona document with empathy map, behavioral traits, and scenario triggers Examples: See examples.md for worked input/output.


Workflow

Step 1: Define persona scope

Confirm:

  • One persona per Skill execution (not persona sets)
  • Primary vs secondary persona (if multiple requested, pick primary first)
  • Segment boundaries (role, context, experience level)

Step 2: Gather behavioral evidence

Collect or request:

  • Observed behaviors (not just stated preferences)
  • Goals and motivations
  • Pain points and frustrations
  • Tools and workflows currently used
  • Decision-making triggers

Step 3: Build empathy map

Fill four quadrants:

SaysThinks
[Quotes or paraphrased statements][Unspoken concerns]
DoesFeels
[Observed actions][Emotional states]

Step 4: Define persona profile

Include:

  • Name (fictional label, not a real person claim)
  • Role and context
  • Goals (primary and secondary)
  • Pain points (ranked by severity)
  • Success definition (what "winning" looks like for them)
  • Anti-goals (what they actively avoid)

Step 5: Add scenario triggers

Describe 2–3 situations that activate the persona's need.

Step 6: Validate

Run Validation checklist.


Decision Rules

ConditionAction
Only demographics provided (age, gender)Request behavioral and goal data
Persona based on assumptions onlyMark all traits as "assumed"; list validation needed
Multiple segments in one requestAsk user to pick primary segment
Contradictory behaviors in inputSurface contradiction; ask for clarification
Research data conflicts with stated segmentFlag conflict; prioritize research data

Validation

  • Exactly one persona produced
  • Empathy map has content in all four quadrants
  • At least 3 pain points ranked by severity
  • Goals are behavioral, not feature wishes
  • Assumed traits clearly marked vs evidence-based
  • 2–3 scenario triggers defined
  • No stereotyping or unsupported demographic generalizations

Anti-patterns

  • Demographic persona — "35-year-old male, likes technology" without behaviors.
  • Ideal user fantasy — persona with no pain points or trade-offs.
  • Feature wishlist persona — goals listed as "wants feature X".
  • Multiple personas at once — dilutes focus and validation.
  • Presenting assumptions as facts — not marking unvalidated traits.

Best Practices

  • Base personas on observed behavior patterns, not market segments alone.
  • Use empathy map before writing narrative profile.
  • Include anti-goals to prevent scope creep in later Skills.
  • Reference problem statement if available from prior Skill.
  • Recommend 3–5 user interviews to validate assumed traits.

Output Structure

# Persona: [Name] — [Role]

## Profile
- **Segment:** [description]
- **Context:** [work/life situation]
- **Experience level:** [novice/intermediate/expert]

## Empathy Map
[Four quadrants table]

## Goals
| Priority | Goal |
|----------|------|

## Pain Points
| Severity | Pain Point | Evidence |
|----------|------------|----------|

## Success Definition
[What winning looks like]

## Anti-goals
- [What they avoid]

## Scenario Triggers
1. [Situation] → [need activated]

## Validation Status
| Trait | Status (evidence/assumed) |
|-------|---------------------------|

Next Skills

OutcomeRecommended Skill
Persona validated, need visionproduct/product-vision-builder
Need to re-validate ideaproduct/idea-validator
Ready for problem refinementproduct/problem-statement-builder
Ready for feature decisionsproduct/feature-prioritization

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.