agentleFS
miguelclavelmiguelclavel/ux-research-skills/skills/user-personas/SKILL.md

user-personas

Skill1 starsChanged 38 days agoMITView on GitHub

Create evidence based personas from real research: behaviours, goals, frustrations and context, each traced to its source, with an honest confidence level. Use when someone asks for personas, user archetypes, segments, or wants to check whether existing personas are backed by data.

9 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

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 1

    Distinctive

    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:

    Don't invent demographics, hobbies or quotes.

    line 29

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “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

User personas

A persona is a summary of evidence, not a character sketch. If it can't point to research, it's an assumption and should be labelled one.

Steps

  1. Gather the evidence: interviews, usability tests, surveys, analytics, support tickets. Note how many people each source covers.
  2. Find the behaviours that split people: how they decide, how much they know, how often they do the task, what they're trying to get done. Group people by those, not by age or job title.
  3. Build each persona from one group:
    • A name that describes the behaviour ("The cautious comparer"), not a stock photo and a fake biography
    • Goals and the job they're trying to get done
    • How they do it today, and their main frustrations, each with a short quote and its source
    • What would make them trust a product, and what would make them leave
    • Context: devices, time pressure, who else is involved
  4. Confidence. For each persona say how many participants it rests on and which parts are inferred. If there is no research yet, call them proto personas and list what would confirm them.
  5. How to use it: two or three design questions each persona should answer ("Would the cautious comparer trust this price?").

Output

One card per persona, a short "how we got here" note, and a list of what's still unknown.

Don't

  • Don't invent demographics, hobbies or quotes. Don't make more personas than the team will remember (three to five).

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.