agentleFS
miguelclavelmiguelclavel/ux-research-skills/skills/survey-design/SKILL.md

survey-design

Skill1 starsChanged 38 days agoMITView on GitHub

Design a survey with unbiased questions, the right scales, a sensible length and an analysis plan, and review existing surveys for bias. Use when someone wants to write a survey, questionnaire, NPS or satisfaction survey, or wants to know how many responses they need.

8 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. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 2

    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:

    Start from what you'll do with the answers: Every question maps to a decision or an analysis.

    line 12
  2. Distinctive:

    Don't ask people to predict their future behaviour and treat it as a forecast.

    line 27

“Common” is measured: kept by at least 6 in 10 of the 7 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

Survey design

Surveys count things. Use them when you need to know how many, not why.

Steps

  1. Start from what you'll do with the answers. Every question maps to a decision or an analysis. Cut the rest.
  2. Ask about behaviour and facts first, opinions second. "How many times did you compare quotes last year?" before "How satisfied are you?"
  3. Write neutral questions: one idea per question, no leading words, no double negatives, balanced scales with a neutral point and a "not applicable" when needed.
  4. Order: easy and relevant first, sensitive and demographic last, demographics optional.
  5. Length: under ten minutes. Long surveys get rushed answers.
  6. Sample: say who it's going to, how they're reached, and who's missing (people who already left, people who don't open email). For estimating a percentage, a few hundred responses gives a usefully narrow range; explain the margin rather than overselling precision.
  7. Pilot with five people and fix what confused them.
  8. Privacy: collect only what you need, say how it's used, keep answers anonymous where possible.

Output

The survey with question types and answer options, the reason for each question, the analysis plan, and the sampling notes.

Don't

  • Don't ask people to predict their future behaviour and treat it as a forecast. Don't make every question required.

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.