Przejdź do treści
Biblioteka skilli
Projektowanie i UX · Przegląd i audyt

ux

/ux

Przegląda i planuje UX dla interfejsów webowych i React Native, sprawdza realną ścieżkę użytkownika w kodzie oraz dostępność WCAG 2.2.

Repozytorium
agent-skills ↗
Licencja
MIT
Ostatnia zmiana repozytorium
27.10.2026

Ocena i bezpieczeństwo

100/ 100Klasa: dobry
Format25 / 25
Frontmatter z nazwą i opisem, poprawna nazwa, opis do 1024 znaków, nazwa zgodna z folderem.
Odkrywalność25 / 25
Opis mówi, kiedy użyć skilla, ma sensowną długość i jest w 3. osobie.
Treść35 / 35
Co najmniej 150 słów i do 500 linii, nagłówki, listy kroków, przykłady albo kod.
Higiena15 / 15
Bez zaślepek typu TODO, bez ścieżek Windows, z licencją.
Ryzykobrak sygnałów w skanie
Pliki w paczce
10
Skrypty
0
Komentarze HTML
0
Adresy URL w SKILL.md
0
Przestarzałość

Brak sygnałów. Repozytorium zmienione 27.10.2026, bez odwołań do wycofanych modeli i API.

Licencja

MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.

Co robi i kiedy

Przegląda i planuje UX dla interfejsów webowych i React Native, sprawdza realną ścieżkę użytkownika w kodzie oraz dostępność WCAG 2.2.

Wyzwalacze z opisu

ux reviewux auditcheck accessibilityis this accessibleplan the X flowimprove copy
Oryginalny opis (EN)

Reviews and plans UX for web and React Native (Expo) UIs: walks the user's real path through the code, checks what each control actually does, then goes deep on accessibility (WCAG 2.2) and microcopy. Never recommends a dark pattern. Triggers on "ux review", "ux audit", "check accessibility", "is this accessible", "plan the X flow", "improve copy", "/ux".

Jak działa

  1. Modes
  2. Step 0 — Scope
  3. Pass 1 — The user's path (first, always)
  4. Pass 2 — Accessibility and interaction depth
  5. Verify before reporting
  6. Report
  7. Hard rules
Sekcje z nagłówków SKILL.md, w oryginale · 87 linii, 857 słów
Podgląd SKILL.md
---
name: ux
description: >
  Reviews and plans UX for web and React Native (Expo) UIs: walks the user's
  real path through the code, checks what each control actually does, then goes
  deep on accessibility (WCAG 2.2) and microcopy. Never recommends a dark
  pattern. Triggers on "ux review", "ux audit", "check accessibility", "is this
  accessible", "plan the X flow", "improve copy", "/ux".
disable-model-invocation: false
license: MIT
metadata:
  author: mthines
  version: '2.0.0'
  workflow_type: advisory
  tags: [ux, accessibility, design, react-native, expo, web, wcag, usability, ux-writing, dark-patterns, flow-planning]
---

# UX

Audit or plan a UI the way a product reviewer does: start from what the user is trying to get done, prove what the code does, then add accessibility depth.
Read every target file completely before reporting on it.

## Modes

| Request | Mode | Order of work |
| --- | --- | --- |
| "review / audit this page", "ux feedback", `/ux` (default) | `audit` | Pass 1 → Pass 2 → Verify → Report |
| "plan the X flow", "design the onboarding", "how should X work" | `plan` | Flow plan first, then a Pass 1 + Pass 2 audit of any existing code the flow touches |
| "check accessibility", "is this accessible", "check contrast" | `a11y` | Pass 1 steps 1–2 only (job + task), then Pass 2 in full |
| "improve copy", "review microcopy" | `copy` | [`rules/ux-writing.md`](./rules/ux-writing.md) on every user-facing string, ordered by where it sits on the user's path |
| Consent, cancellation, paywall, sign-up, permission prompt, AI chat — in any mode | `dark-patterns` | Always also apply [`rules/dark-patterns.md`](./rules/dark-patterns.md); any hit is Critical |

## Step 0 — Scope

1. Resolve the target: the user's named files, else the changed UI files (`git diff --name-only <base>...HEAD`), else the current file.
2. Detect the platform: web (`<div>`, CSS, Tailwind), React Native (`View`, `Pressable`, `expo-router`), or both. Ask when ambiguous.
3. Read the target files, then the handlers, hooks, stores, routes, and API calls they reach — Pass 1 depends on them.

## Pass 1 — The user's path (first, always)

Outcome-changing findings (a broken flow, a control that does the wrong thing, a dead end) come from this pass, not from the checklist.
Follow [`rules/user-path.md`](./rules/user-path.md):

1. Name the page's job and the primary user task in one sentence each.
2. Walk the task end to end in the code, from entry to the next step after success.
3. For each control on the path, read its handler and state changes, and compare what it does with what the UI promises.
4. Cover empty, loading, stale, error, and first-run states.
5. Check the activation / next-step path: can the user actually do what the page tells them to do next?
6. Note what already works — the report keeps it.

## Pass 2 — Accessibility and interaction depth

Follow [`rules/accessibility.md`](./rules/accessibility.md) on every interactive element Pass 1 touched:

- Contrast computed from the actual tokens and resolved colors, in every theme.
- Focus management on open, close, delete, and route change.
- Live regions: what is announced, how often, and whether it floods.
- ARIA roles and patterns, keyboard paths, touch targets, reduced motion.

Load the extra rule files only when the code contains the trigger:

| Code contains | Load |
| --- | --- |
| Hard-coded colors, theme tokens, dark mode, type sizes | [`rules/visual-design.md`](./rules/visual-design.md) |
| User-facing strings | [`rules/ux-writing.md`](./rules/ux-writing.md) |
| Consent, subscriptions, cancellation, checkout, sign-up, permissions, AI surfaces | [`rules/dark-patterns.md`](./rules/dark-patterns.md) |
| Charts or dashboards | `Skill("charting")` for chart choice; keep contrast, labels, and targets here |
| Style direction, brand, "make it less generic" | `Skill("visual-design")`; merge its output with this report |

A missing companion skill never blocks; log `<name> — skipped (not installed)` and continue.

## Verify before reporting

Every claimed behaviour cites the `file:line` that proves it.
When the code cannot prove it statically, label the finding **unverified** and say what would confirm it.
Details and examples: [`rules/verify-before-reporting.md`](./rules/verify-before-reporting.md).

For a Critical or High finding about motion, timing, focus order, or hover-revealed content, `Skill("screencast")` may capture evidence (a `recording.json` whose `id` is the finding's `file-line`); append its `.mp4` path as a `Recording:` line.

## Report

Use [`templates/review-report.md`](./templates/review-report.md).

1. Order findings by impact on the primary task — a broken step outranks a contrast miss.
2. Put a severity label (`Critical` / `High` / `Medium` / `Low`) on each finding; severity is a label, not the document's section structure.
3. Give every finding `file:line`, what the user experiences, and a concrete fix (code when the fix is code).
4. Include **What works (keep)**, a **Plan** (first three moves), and **How we'll know it worked** (one measurable signal per top item).
5. Report at most ten findings; merge duplicates and drop nitpicks before cutting a real issue.

| Severity | Criteria |
| --- | --- |
| Critical | The user cannot finish the task, loses data, is misled, or is locked out (keyboard / screen reader); any dark pattern |
| High | The task finishes but with a wrong result, confusion, or an AA failure on the path |
| Medium | Friction or an AA failure off the main path |
| Low | Polish |

## Hard rules

1. Never recommend a dark pattern; if asked to add one, refuse, name the harm, and give the honest alternative ([`rules/dark-patterns.md`](./rules/dark-patterns.md)).
2. Never assert behaviour you did not read in the code.
3. Never apply an iOS rule to Android code or the reverse.
4. Match the bar to the context: a prototype gets the path and blockers, a production surface gets AA in full.
Pliki w paczce (10)
  • SKILL.md 6 KB
  • lens.md 2 KB
  • references/path-first.md 1 KB
  • rules/accessibility.md 5 KB
  • rules/dark-patterns.md 4 KB
  • rules/user-path.md 3 KB
  • rules/ux-writing.md 2 KB
  • rules/verify-before-reporting.md 2 KB
  • rules/visual-design.md 2 KB
  • templates/review-report.md 1 KB

Wersje

RepozytoriumWynikLicencja
Ta strona · mthines/agent-skills100MIT
Vamp-pire/hype-me100MIT
Vamp-pire/hype-me100MIT
molveau/skills100MIT
darioabc/massimo100MIT
rainmanjam/poka-yoke100MIT
ericrisco/rsc-harness90MIT
Esposter/Esposter90Apache-2.0
koolamusic/claudefiles90MIT

Migawka bazy z 13.11.2026 · wersja paczki 3880c6255277 (skrót SHA-256 całej paczki)

Pobrania w ostatnich 30 dniach: 0 · ranking

Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.

Podobne skille

  • 100accessibility
    Audytuje i poprawia dostępność web według WCAG 2.1: wsparcie czytników ekranu, nawigacja klawiaturą i zgodność WCAG.
  • 95accessibility
    Audytuje i poprawia dostępność stron według WCAG 2.1, w tym wsparcie czytników ekranu i nawigację klawiaturą.
  • 90accessibility
    Audytuje i poprawia dostępność stron według WCAG 2.1: czytniki ekranu, nawigację klawiaturą i zgodność z wytycznymi.
  • 84audit-accessibility
    Sprawdza komponenty i strony interfejsu pod kątem dostępności, w tym zgodności z WCAG i obsługi czytników ekranu.
  • 100wcag-accessibility
    Zapewnia zgodność z WCAG 2.2 AA wymaganą przez European Accessibility Act przy projektowaniu, budowie i przeglądzie interfejsów użytkownika.
  • 100accessibility-compliance-audit
    Audytuje interfejsy HTML, React, Vue i Angular pod kątem WCAG 2.2 AA i generuje gotowy kod poprawek.

Uwagi i zgłoszenia

Wiadomość trafi do Bartosza Sokolińskiego. Adres e-mail jest potrzebny tylko do odpowiedzi. Szczegóły w polityce prywatności.