agentleFS
pedroromerolunapedroromeroluna/ai-first-product-skills/skills/ux-research/SKILL.md

ux-research

Skill5 starsChanged 27 days agoMITView on GitHub

Design one research round against the single riskiest hypothesis — behavioral screening, one modality chosen on purpose, a guide whose every question is tied to a hypothesis or a job dimension — and write the Research Plan as dated research of the loaded product node. Manually triggered, third station of the discovery pipeline.

16 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use seo.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • nilssonrSkill

    seo

    Full SEO workflow for auditing pages and creating SEO-optimized content. Provides checklists with educational explanations aligned with Google Search Central documentation.

    Also in 3 projects that use this

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 14 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:

    When the round explores a job-to-be-done, the guide covers the four forces of change, not just the functional one:

    line 49
  2. Distinctive:

    Every question in the guide is tied explicitly to a hypothesis from the Discovery Brief or to one of the four job dimensions.

    line 70
  3. Distinctive:

    Question guide: every question with the hypothesis or job dimension it is tied to.

    line 99

“Common” is measured: kept by at least 6 in 10 of the 14 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

ux-research — the Research Plan

Third station of the pipeline. It designs the research round that attacks the riskiest hypothesis of the Discovery Brief — never all of them at once — and closes with a Research Plan ready to pilot.

When it is invoked

WhenFrom / to
The Market Brief from market-research already sized the marketEntry from market-research (.agents/skills/market-research/SKILL.md)
The Research Plan is writtenExit toward synthetic-users (.agents/skills/synthetic-users/SKILL.md) — pilots the script before spending real fieldwork
With no prior Market BriefInvocable on its own, over the loaded product node, with the Discovery Brief as the minimum input

The interview

It is run with the pressure method of .agents/skills/grill/SKILL.md#method — cited by path, never copied — over the choice of hypothesis, the screening criterion and every question in the guide.

One objective per round

Each round attacks a single hypothesis: the riskiest one in the Discovery Brief, the same risk × impact prioritization product-strategy already did. Faced with a request to "research everything together", pressure is applied: which is the one that costs the most if it turns out wrong? That one belongs to this round; the others wait for the next.

Screening that avoids "users in general"

The criterion for who gets interviewed is written in verifiable behavior, never in demographics alone. "Active users" is not screening; "people who bought in the last two weeks and abandoned checkout at least once" is. Faced with a criterion that is too broad ("any user of the app"), it is returned with a counter-question: what behavior must this person have done or not done for their answer to be useful?

Exploratory → qualitative; sizing → quantitative

The modality is decided by what question the round asks. If the question is "why does this happen?" or "what do people do today?", qualitative — interviews, few people, depth. If the question is "how many people does this happen to?" or "how often?", quantitative — survey, representative sample. Mixing the two without deciding which one leads produces a plan without focus; one is chosen and the reason is stated.

JTBD in four dimensions

When the round explores a job-to-be-done, the guide covers the four forces of change, not just the functional one:

DimensionWhat it looks for
PushWhat about the current situation pushes toward looking for something different
PullWhat about the new solution attracts
AnxietyWhat doubt or fear holds the change back
HabitWhat about the current solution weighs by habit, even when it does not work well

A guide that only asks about the desired feature covers one of the four and is returned incomplete.

Master technique: reconstruct the last real time

The master question of any guide is not "what do you think of X?": it is "tell me about the last time [situation]" — reconstructing step by step what happened, at what moment, with whom, what they did right before and right after. Opinion questions ("would you like it if...?") are taken out of the guide unless they serve to close the session, never to explore.

Every question tied, or it comes out

Every question in the guide is tied explicitly to a hypothesis from the Discovery Brief or to one of the four job dimensions. A question that cannot be tied to either is taken out of the guide — "just in case" is not an inclusion criterion.

The Research Plan

It closes by writing the deliverable as dated research of the loaded product node, in:

research/<YYYY-MM-DD>-research-plan.md

Dated, never overwritten. The path falls inside content: */products/*/research/*.md line of the brain's own tree.md: no new glob and no resolver row are needed. Without a product node, this same file — <YYYY-MM-DD>-research-plan.md — is what lands in the current folder instead.

The Plan carries these four sections, in this order, each with its literal heading:

## Objective of the round
## Screening criterion
## Modality
## Question guide
  • Objective of the round: the chosen hypothesis and why it is the riskiest.
  • Screening criterion: in verifiable behavior, never demographics alone.
  • Modality: qualitative or quantitative, with the question that decides it.
  • Question guide: every question with the hypothesis or job dimension it is tied to.

What this deliverable does not claim

The Research Plan is the v1 guide: it has not been piloted yet. Piloting it against synthetic personas —before spending the first minute of real fieldwork— is the job of synthetic-users, the next station.

Destination

The skill resolves the destination before producing the deliverable, never after. Three cases, two destinations:

  • A product node is loaded: the deliverable goes to research/<YYYY-MM-DD>-<name>.md of that node.
  • There is a brain, but no product node — no workspace yet, or a workspace without one: the deliverable is written to a file in the current folder.
  • There is no brain at all: the deliverable is written to a file in the current folder.

With no product node, the file is written to the current folder anyway. The closing message names only the path it just wrote and stops there — that is the normal way this skill ends, not an anomaly to qualify.

This skill never asks which destination to use, and it never invents a third one.

The rest of the pack installs one skill at a time. Look at .agents/skills/ first and then .claude/skills/ (a skill present in both counts once) and offer only the ones that are not there — once per session: the first time this skill closes in the session, never again on a later close of the same or another deliverable:

  • grill — npx skills add pedroromeroluna/ai-first-product-skills --skill grill
  • market-research — npx skills add pedroromeroluna/ai-first-product-skills --skill market-research
  • product-strategy — npx skills add pedroromeroluna/ai-first-product-skills --skill product-strategy
  • synthetic-users — npx skills add pedroromeroluna/ai-first-product-skills --skill synthetic-users

The whole pack at once: npx skills add pedroromeroluna/ai-first-product-skills. That command installs what the pack offers; anything listed above it is installed by naming it.

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.