Sample size planner

A Claude skill that tells you how many participants your study needs, with the published source behind the number and a sentence you can paste into your plan.

Study designOctober 12, 2026

Download the skill

Enter your details to download the skill file.

What it does

"How many people do I need?" usually gets answered with "five", and no reason for it.

You give it the kind of study you're running and how many user groups you're studying. It tells you a recommended number or range, the published source behind it, and a sentence you can paste into your research plan. It can also tell you whether new interviews have stopped turning up new themes. Use it when you're planning a study, or when a stakeholder asks "is that enough people?".

What you get back

  • A starting range per segment and in total, with the source for each figure.
  • A paste-ready rationale paragraph for your research plan that says findings will be reported as counts.
  • A saturation check across your interviews, showing new themes per interview and whether the stopping rule is met.
  • Problem-discovery sample sizes for usability tests, with the assumption about problem frequency stated.
  • Confidence intervals for small samples, such as what "1 of 5 participants" can and can't support.
  • Task-time summaries calculated on log values, the way skewed timing data needs.

Install it in Claude, ChatGPT, Copilot or Gemini

The same skill file works in all four. Pick your tool for the steps.

Install in Claude

  1. 1

    Download the skill

    Fill in the short form to get the .skill file.

  2. 2

    Add it to Claude

    In the Claude app go to Settings → Capabilities → Skills and upload the file. In Claude Code, run the npx command shown after the form, or drop the folder into your project's skills folder.

  3. 3

    Just ask

    Ask in plain language. Claude picks up the skill on its own when the request matches.

How to use it

Once it's installed, ask in plain language. Your AI follows the skill's method when the request matches.

Example prompt 1
How many interviews do I need across four customer segments?
Example prompt 2
Here are the codes from each interview in order. Have we hit saturation?
Example prompt 3
My stakeholder wants a percentage from eight interviews. Help me explain why we'll report counts instead.

What it won't do

It won't run significance tests on interview data. Small-sample tests are valid, but purposive samples don't support inference to a population, so it explains that instead. It also won't present a range as a requirement: the number is a starting point that the study's aim and context should move.

Questions

Does it work for qualitative studies, or only quant?

Both, and qualitative planning comes first. It gives sourced ranges for interviews and focus groups, plans per segment, and treats reflexive thematic analysis on its own terms rather than forcing a saturation count onto it.

Where do the numbers come from?

Published sources, named in every output: Hennink and Kaiser's review and Hennink, Kaiser and Marconi for interviews, Guest, Namey and Chen for saturation, Malterud and colleagues for information power, and Faulkner, MeasuringU and NN/g for usability and survey maths.

Is five users enough for a usability test?

Sometimes. Five finds most problems that affect a large share of people, but a single study is one draw and may not be an average one. The skill shows what five covers at your expected problem frequency, so you can decide.

More skills

See all skills