agentleFS
miguelclavelmiguelclavel/ux-research-skills/skills/research-plan/SKILL.md

research-plan

Skill1 starsChanged 38 days agoMITView on GitHub

Plan a research project: the decision it informs, research questions, the right method, participants, timeline and what done looks like. Use when someone says "we should talk to users", wants a research plan or brief, is choosing between interviews, a survey or a usability test, or needs to scope research.

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

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

  • 0

    Common

    Most of the 3 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 pick the method first.

    line 31

“Common” is measured: kept by at least 6 in 10 of the 3 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

Research plan

Research exists to change a decision. Start from the decision, not the method.

Steps

  1. The decision. What will the team decide differently depending on what we learn? If nothing, push back: it may not need research.
  2. What we already know. Analytics, past research, support tickets, sales notes. Don't research what's already answered.
  3. Research questions. Three to five questions about people's behaviour and context, not about our product ideas. "How do people choose an insurance plan today?" not "Would people like our new quote tool?"
  4. Pick the method from the question:
    • Why and how people do things today: interviews, contextual inquiry, diary study
    • Whether people can use something: usability testing
    • How many people do or think something: survey, analytics
    • How people group or find information: card sorting, tree testing
    • Which version performs better: A/B test
  5. Participants. Who, how many (five to eight per segment for interviews and usability tests is usually enough to see patterns), how to recruit, incentives, and accessibility needs.
  6. Ethics and privacy. Consent, what's recorded, who sees it, how long it's kept, and how names are removed from notes.
  7. Timeline and owners, and the readout: when, to whom, in what form.

Output

A one page plan: decision, what we know, research questions, method and why, participants, ethics, timeline, deliverable.

Don't

  • Don't pick the method first. Don't ask users to design the solution. Don't promise statistical certainty from eight interviews.

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.