agentleFS
miguelclavelmiguelclavel/ux-research-skills/skills/interview-guide/SKILL.md

interview-guide

Skill1 starsChanged 36 days agoMITView on GitHub

Write a semi structured interview guide with behaviour based questions and follow up probes that do not lead the participant. Use when someone is preparing user interviews, customer conversations, discovery calls or switch interviews, or wants their questions reviewed for bias.

6 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. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 3

    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:

    No leading ("Wouldn't it be easier if..."), no yes or no, no hypotheticals ("Would you use...").

    line 21
  2. Distinctive:

    After each core question, a probe: "What happened next?", "Why was that?", "How did you decide?", "Can you show me?"

    line 22
  3. Distinctive:

    Don't pitch. Don't fill silences.

    line 30

“Common” is measured: kept by at least 6 in 10 of the 4 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

Interview guide

Good interviews ask about the past, not the future. People are bad at predicting what they'll do and good at telling you what they did.

Structure for a 30 to 45 minute session

  1. Intro (3 min). Who you are, the purpose in plain words, consent to record, "there are no wrong answers, we're testing ideas, not you".
  2. Warm up (5 min). Their context and role, not your product.
  3. The core (20 to 30 min). Walk through the last time they actually did the task: "Tell me about the last time you..." then let the story run. Questions follow the order things happened.
  4. Workarounds and costs (5 min). What they tried instead, what it cost in time, money or stress.
  5. Close (3 min). "What should I have asked?", thanks, next steps for the incentive.

Rules for every question

  • Open ended, about real past behaviour, one idea at a time.
  • No leading ("Wouldn't it be easier if..."), no yes or no, no hypotheticals ("Would you use...").
  • After each core question, a probe: "What happened next?", "Why was that?", "How did you decide?", "Can you show me?"

Output

The guide with timings, each question followed by its probe, and the three questions to keep if time runs short. Then a short list of what to listen for, tied to the research questions.

Don't

  • Don't pitch. Don't fill silences. Don't correct the participant.

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.