cpux-agent-skills / rules
Cursor rule0 starsChanged 6 days agoApache-2.0View on GitHub
Conduct UX reviews, Persona Walkthroughs, 5-State UI checks, and ISO 9241-110:2020 usability fixes when creating or editing frontend components and templates.
We split this ux-review-walkthrough.mdc into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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
- Distinctive: line 9
When asked to review UX, improve usability, create/save personas, design a user flow, or build/refactor a UI component:
- Distinctive: line 12
5-State Completeness Check: Never ship Happy-Path-only UI.
- Distinctive: line 19
Problem vs. Solution Space: When specifying User Needs (*Erfordernisse*) or Qualitative User Requirements (*Nutzungsanforderungen*), never …
≈ “Common” is an estimate: at least 1 in 5 of the 6,350 Cursor rule 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.
Files
---
description: Conduct UX reviews, Persona Walkthroughs, 5-State UI checks, and ISO 9241-110:2020 usability fixes when creating or editing frontend components and templates.
globs: ["**/*.html", "**/*.twig", "**/*.vue", "**/*.tsx", "**/*.jsx", "**/*.svelte", "**/*View.java", "docs/ux/**/*.md"]
alwaysApply: false
---
# UX Review & Persona Walkthrough Rules (ISO 9241 / CPUX)
When asked to review UX, improve usability, create/save personas, design a user flow, or build/refactor a UI component:
1. **Persona Setup & Cognitive Walkthrough:** Check `docs/ux/personas.md` first to reuse existing project personas. Otherwise, define 1 Primary Persona (task-focused, context constraints like mobile/glare/time pressure) and 1 Edge-Case Persona (keyboard-only, screen-reader, or low-vision) and trace their step-by-step path through the component. When asked to save personas for reuse, write them to `docs/ux/personas.md`.
2. **5-State Completeness Check:** Never ship Happy-Path-only UI. Verify and implement:
- `Empty State` (motivating explanation + primary CTA)
- `Loading State` (`aria-busy="true"`, disabled submit to prevent double-triggers, skeleton/spinner)
- `Error State` (preserve all valid user input! Never call `form.reset()` on error; provide inline field recovery via `aria-invalid="true"` and `aria-describedby`)
- `Partial / Overflow State` (long German compound words, 100+ items, missing optional data)
- `Success State` (clear confirmation + Undo option or explicit verb confirmation for destructive actions)
3. **ISO 9241-110:2020 Principles:** Enforce *Aufgabenangemessenheit* (smart defaults, `autocomplete`, `inputmode`), *Selbstbeschreibungsfähigkeit* (persistent `<label>`, never placeholder-only), *Erwartungskonformität* (semantic `<button>` over `<div onClick>`, logical `Tab` order), *Steuerbarkeit* (back-navigation without data loss, `prefers-reduced-motion`), and *Robuste Verwendung* (forgiving input parsers that strip spaces in IBAN/phone automatically).
4. **Problem vs. Solution Space:** When specifying User Needs (*Erfordernisse*) or Qualitative User Requirements (*Nutzungsanforderungen*), never mention concrete UI widgets ("dropdown", "modal").
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 3,978 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository3 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ux-review-walkthroughSkill
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
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.