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

research-readout

Skill1 starsChanged 38 days agoMITView on GitHub

Turn research findings into a short readout that changes decisions: insight statements, evidence, recommendations and confidence. Use when someone needs to present research, write a research report, share findings with stakeholders, or turn notes into insights.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Don't present findings without evidence counts.

    line 25

≈ “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

Research readout

Nobody acts on a 40 page report. Lead with what changes, and make every claim easy to check.

Structure

  1. The headline: the one thing the team should do differently, in a sentence.
  2. What we did: method, who took part (counts and segments), when. Two lines.
  3. Insights, three to five, each as: the insight in one sentence ("People don't trust a price until they see which insurer is behind it"), the evidence (how many participants, two quotes with ids, supporting data), what it means for the product, and a confidence level (strong, moderate, early signal).
  4. Recommendations, each tied to an insight, with an owner and what would show it worked.
  5. What we still don't know, and the next research step.
  6. Appendix: method details, the guide, and the raw findings for anyone who wants them.

Make it travel

A one page summary someone can forward, and a short clip or quote per insight. Remove names; use participant ids.

Don't

  • Don't present findings without evidence counts. Don't bury the decision on page ten. Don't overstate: eight interviews show patterns, not percentages.

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.