agentleFS
miguelclavelmiguelclavel/ux-research-skills/skills/synthetic-users/SKILL.md

synthetic-users

Skill1 starsChanged 38 days agoMITView on GitHub

Use AI simulated users to pressure test assumptions, sharpen interview questions and anticipate objections, clearly labelled as hypotheses, never evidence. Use when someone asks about synthetic users, AI personas, simulated user interviews, or wants quick feedback on a concept before real research.

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Widen the frame: ask for perspectives the team hasn't considered (people using screen readers, people on slow connections, people new to …

    line 15
  2. Distinctive:

    Ground each synthetic user in real research: when you have it (a persona and quotes), and say when you don't.

    line 19
  3. Distinctive:

    Don't count synthetic answers as participants, put them in research reports as findings, quote them as users, or use them to decide whether …

    line 30

≈ “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

Synthetic users

Asking an AI to role play users is fast and tempting, and it can't replace people: it tells you what's typical in its training data, not what your users do. Used carefully, it's good for one thing: getting sharper before you talk to real people.

Good uses

  • Stress test assumptions: "What would make a cautious comparer not trust this price?" Then check the answers with real users.
  • Sharpen a guide: rehearse interview questions and spot leading or confusing ones.
  • Anticipate objections and edge cases to cover in a test.
  • Widen the frame: ask for perspectives the team hasn't considered (people using screen readers, people on slow connections, people new to the country), then recruit those people.

How

  1. Ground each synthetic user in real research when you have it (a persona and quotes), and say when you don't.
  2. Ask for reasoning, not verdicts: "What would you look for first, and why?" rather than "Would you buy this?"
  3. Generate several distinct perspectives, and ask each what would make them leave.
  4. Turn every output into a hypothesis with a plan to test it: "Hypothesis: people won't trust a price without seeing the insurer. Test: usability task 2."

Output

A list of hypotheses and better questions, each labelled "synthetic, not evidence", with how to validate it.

Don't

  • Don't count synthetic answers as participants, put them in research reports as findings, quote them as users, or use them to decide whether something ships.

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.