Skip to content
/EUXLab
v0.3.0 · 10 skills

Agent skills for real enterprise UX

Each skill reads a file, does one thing, and writes a file. Run one on the problem in front of you. Every claim it writes carries a citation back to a line in a transcript.

All you need is a folder you can write to and a coding agent. No Obsidian, no note-taking app, no second brain. Every file a skill reads or writes is plain markdown.

skills shipped
10skills shipped
groups
3groups
uncited claims allowed
0uncited claims allowed

01 · Install

Set up in three steps

Get the skills, configure one engagement, and run the first step of the loop.

  1. Step 1: Get the skills

    Claude Code

    plugin

    Install the whole set as a managed, read-only plugin. It updates when a new version ships.

    claude plugins marketplace add roxanneallard/euxlab-skills claude plugins install euxlab-skills@euxlab

    Update with: /plugin marketplace update euxlab

    Plugin skills carry the plugin prefix, so setup runs as /euxlab-skills:euxlab-setup.

    Codex and other agents

    skills.sh

    Pick the skills and the agents you use. The installer writes editable files into your project.

    npx skills@latest add roxanneallard/euxlab-skills

    Update with: npx skills update

    Take euxlab-setup and the four reference skills. The loop skills load them.

    Pick one. Installing both gives you every skill twice.

    Claude desktop or web? Download the skill zips from the latest release and upload each one under Settings > Capabilities > Skills. Upload the four reference skills first. Latest release.

  2. Step 2: Run /euxlab-setup

    Once per engagement, inside the engagement folder. It asks for:

    • The client, the product, and the domain
    • The design system every artifact has to obey
    • The consent and retention posture for research recordings
    • Who asks for the work, who signs off, and who is measured on the outcome

    Then it writes the folder scaffold every other skill reads.

  3. Step 3: Start the loop

    When a stakeholder request arrives, run /euxlab-grill-the-ask. Each skill writes the file the next one reads.

    See the whole loop

02 · The library

10 skills, 3 groups

The grouping answers what situation you are in, never what discipline the work belongs to.

01

Getting started

Run once per engagement. Everything else reads what this writes.

02

The loop

Request to reviewed design, in order. Every output is the next input.

03 · Two rules

What every skill refuses to do

Both rules hold across every skill. They are why a finding survives contact with a stakeholder six weeks later.

Every claim carries a pointer.

Participant ID plus a line range, back to raw. A claim with no pointer does not ship. This is what makes a contradiction detectable six weeks later, and what lets /euxlab-design-review walk from any screen back to the quote behind it.

Raw research is people.

Participants are identified by ID everywhere outside research/raw/. Redaction happens on the way out of every skill, not as a final cleanup pass.

04 · Credits

Where the shape came from

The skill shape, the grilling primitive, the completion-criterion discipline and the repo structure come from Matt Pocock’s skills (MIT). The UX content comes from fifteen years of enterprise engagements.