A general process for testing a product's user experience through expert checks, step-by-step task reviews, screen and journey analysis, language checks, and planned tests with real users. It can be used for websites and apps across different technology stacks.

Use it to evaluate key screens and tasks, run heuristic reviews, test different languages and screen sizes, perform cognitive walkthroughs, or create moderated and unmoderated user-test plans.

It helps find confusing screens, broken task flows, accessibility or language problems, and other issues that users may encounter.

test-ux — Skill for Codex by GalaxyRuler/Galactic-skills

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add GalaxyRuler/Galactic-skills --skill test-ux

Clone the repo

git clone --depth 1 https://github.com/GalaxyRuler/Galactic-skills

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/galaxyruler/galactic-skills/test-ux/github.svg)](https://agentmods.dev/skills/galaxyruler/galactic-skills/test-ux)

Your own site

<a href="https://agentmods.dev/skills/galaxyruler/galactic-skills/test-ux"><img src="https://agentmods.dev/badge/skills/galaxyruler/galactic-skills/test-ux/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/galaxyruler/galactic-skills/test-ux"><img src="https://agentmods.dev/badge/skills/galaxyruler/galactic-skills/test-ux.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 831 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00113	$0.00831
Opus 5.5	$0.00045	$0.00332
Sonnet 5.5	$0.00023	$0.00166
Haiku 4.5	$0.00011	$0.00083

Measured 2mo ago against content hash 45849d9f9976, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

test-ux scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/test-ux/SKILL.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/test-ux — portable UX testing runner

Execute the UX Testing Playbook (playbook.md, same folder) against the current product and emit a findings report (and a real-user test plan). Read it first — it's the method; this is the runbook. Works for any web/app product; a project-level test-ux overrides this when present.

Scope: an argument narrows to a flow/screen (/test-ux "signup flow"). No argument = the top tasks from Phase 0.

Phase 0 — Detect & scope

Find how to launch the app (project README/TESTING.md, dev script in package.json, or ask). Identify supported locales + text direction.
Read a project TESTING.md / docs/testing/* / the Project appendix in playbook.md and prefer its goals/tasks/personas.
Define the top 3–5 tasks as user goals (not features) + a one-line success criterion each; pick ≥1 novice persona.

Runbook (see playbook.md for the why)

Scope & journeys — goals, personas (≥1 novice), top tasks, environments (every locale + text direction, mobile + desktop).
Heuristic evaluation — Nielsen's 10 per key screen; screenshot evidence; heuristic# · screen · issue · severity 0–4 · fix.
Task walkthroughs — drive each task step-by-step; at each step apply the 4 learnability questions; log steps-vs-optimal, dead-ends, hesitation; verdict completed/friction/failed.
Journey & states — empty/loading/low-data/error/first-run/returning; error recovery; trust & provenance.
Content & i18n comprehension — plain language, no jargon, no raw technical identifiers shown to users, honest tone; per locale verify meaning parity + correct direction + no untranslated source text on the rendered page (not just resource files).
Real-user test-plan generator — moderated + unmoderated scripts, screener, metrics sheet (task success, time, SEQ, SUS). Save alongside the report.
Report — severity-sorted findings + top-3 blockers, top-3 quick wins, and the explicit "validate with real users" list.

Read the full file on GitHub · 36 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago Changed 45849d9f9976
2mo ago First seen · 36 lines · 113 tokens per session scan A 360b9e1daee6

Subscribe to this mod's changes

test-ux is a skill published in the GitHub repository GalaxyRuler/Galactic-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 113 tokens to every session and 831 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Design and UX Testing

test-ux next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
test-uxGalaxyRuler/Galactic-skills	Skill	5	2mo ago	MIT	A	113	Codex
webgl-holographic-foilnexu-io/open-design	Skill	107k	today	Apache-2.0	A	41	Claude Code, Codex
html-ppt-hermes-cyber-terminalnexu-io/open-design	Skill	107k	today	Apache-2.0	A	53	Claude Code, Codex
html-ppt-taste-brutalistnexu-io/open-design	Skill	107k	today	Apache-2.0	A	78	Claude Code, Codex
visual-ralphYeachan-Heo/oh-my-codex	Skill	34k	today	MIT	A	52	Codex
glance-canonical-layoutsandroid/skills	Skill	10k	2d ago	Apache-2.0	A	56	Claude Code
accessibilitymicrosoft/hve-core	Skill	1.6k	yesterday	MIT	A	47	Claude Code