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

improve-ui

/improve-ui

Ocenia istniejący interfejs lub powierzchnię produktu względem jego dowodów projektowych, ustala priorytety uwag i przygotowuje plany wdrożeniowe.

Repozytorium
UI-UX-Master ↗
Licencja
MIT
Ostatnia zmiana repozytorium
28.10.2026

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
51
Skrypty
3
Komentarze HTML
0
Adresy URL w SKILL.md
0
Przestarzałość

Brak sygnałów. Repozytorium zmienione 28.10.2026, bez odwołań do wycofanych modeli i API.

Licencja

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

Co sprawdzić przed instalacją
  • 3 skrypty w paczce. Przejrzyj je przed instalacją, bo Claude może je uruchomić.

Skrypty: resources/scripts/audit-rendered-ui.js, resources/scripts/contrast.mjs, resources/scripts/page-eval.mjs

Co robi i kiedy

Ocenia istniejący interfejs lub powierzchnię produktu względem jego dowodów projektowych, ustala priorytety uwag i przygotowuje plany wdrożeniowe.

Oryginalny opis (EN)

Critique an existing interface or audit a product surface against its own design evidence, then prioritize findings or prepare implementation plans. Read-only on product source; use when evaluation is requested rather than a clear direct correction.

Jak działa

  1. Modes
  2. Evidence for critique and audit
Sekcje z nagłówków SKILL.md, w oryginale · 28 linii, 526 słów
Podgląd SKILL.md
---
name: improve-ui
description: Critique an existing interface or audit a product surface against its own design evidence, then prioritize findings or prepare implementation plans. Read-only on product source; use when evaluation is requested rather than a clear direct correction.
---

# Improve UI

Own independent review and principle explanation. Read [coordination](resources/references/coordination.md), [policy](resources/references/policy.md), the selected mode in [review procedure](resources/references/review.md), and the review or explanation section of the [quality bar](resources/references/quality-bar.md).

## Modes

- **Critique:** Evaluate supplied rendered UI, screenshots, or a description with task/audience context. Identify heuristic recommendations as recommendations, not proven user behavior or measured defects.
- **Audit:** Select one coherent surface, trace its runtime owners, and test candidates against its binding design evidence. Prefer no finding to an unsupported one.
- **Plan:** Produce one self-contained [implementation plan](resources/templates/implementation-plan.md) per selected root correction, including exact scope, reuse, current evidence, expected outcome, and checks.
- **Reconcile:** Re-open plan evidence and update status, stale locations, assumptions, and affected consumers. Do not implement the plan.
- **Explain:** Answer a question about a UI principle or value directly: the correct ranges, the limits that make them actionable, a code example consistent with the advice, the accessibility angle stated precisely, and a quick test the reader can run. Use the [playbook](resources/references/playbook/index.md) entries as the source and say which statements are your own arithmetic.

## Evidence for critique and audit

1. Pick principles with the [task router](resources/references/playbook/task-router.md). When the input is code, check every declared value in its "CSS property → principles" table, not only values that look wrong.
2. Measure colour pairs with [contrast.mjs](resources/scripts/contrast.mjs) (`--non-text` for borders, rings and indicators at 3:1).
3. When the page renders, run [audit-rendered-ui.js](resources/scripts/audit-rendered-ui.js) through [page-eval.mjs](resources/scripts/page-eval.mjs) `--audit` at the stated desktop width and at `--width 390`; treat each result as a lead to confirm. Polish details (radius, shadows, icons, motion values) use [polish](resources/references/polish.md).
4. Report each finding with Before and After values and its basis ID in the [findings format](resources/templates/findings.md), ordered by user impact, ending with the verdict and the not-verified list.

Input is a bounded product surface and evidence. Source can prove token/variant/copy-contract contradictions; visual hierarchy or perceived clarity needs rendered/user evidence. Deduplicate root causes without merging distinct problems, prioritize by confidence and user impact, and default to at most three high-confidence findings for a design-drift audit unless broader coverage is requested; a critique or review of a whole screen lists every supported issue.

Assess visual impact, brand identity, narrative, and interaction richness alongside clarity. Weight them by the brief rather than assuming restraint is superior. For redesigns, compare original imagery and actual hover/focus, scroll, and transition behavior; lost storytelling or animation can be a major regression. Use the animate review contract when motion is central. Static screenshots do not verify interaction quality, and visual richness alone does not prove a performance problem.

Never change product source, install dependencies, run mutating formatters, or publish findings. Write only requested review/plan artifacts. Do not expand into functional debugging, architecture, performance, metadata, or a full accessibility audit merely because related code exists. A clearly requested small fix should go directly to its implementation owner instead.

If implementation was already authorized, return the accepted scope to that owner without asking for the same authorization again. Otherwise finish with findings/plans and the choices that need product judgment. Done when every finding states its evidence type, affected surface, confidence, supported correction, and verification. This skill remains separate to preserve the read-only assessment contract.
Pliki w paczce (51)
  • SKILL.md 4 KB
  • THIRD-PARTY-NOTICES.md 4 KB
  • collection-origin.json 2 KB
  • licenses/emil-kowalski-MIT.txt 1 KB
  • licenses/higgsfield-MIT.txt 1 KB
  • licenses/jakub-krehel-MIT.txt 1 KB
  • licenses/johnathan-mo-MIT.txt 1 KB
  • licenses/julien-thibeaut-MIT.txt 1 KB
  • licenses/shadcn-MIT.txt 1 KB
  • resources/references/accessibility.md 3 KB
  • resources/references/clear-writing.md 1 KB
  • resources/references/coordination.md 2 KB
  • resources/references/motion.md 7 KB
  • resources/references/policy.md 6 KB
  • resources/references/polish.md 5 KB
  • resources/references/quality-bar.md 9 KB
  • resources/references/review.md 4 KB
  • resources/references/playbook/index.md 40 KB
  • resources/references/playbook/source-notes.md 7 KB
  • resources/references/playbook/supplemental.md 3 KB
  • resources/references/playbook/task-router.md 10 KB
  • resources/references/playbook/principles/01-foundations.md 5 KB
  • resources/references/playbook/principles/02-visual-hierarchy.md 12 KB
  • resources/references/playbook/principles/03-proximity.md 4 KB
  • resources/references/playbook/principles/04-clarity.md 6 KB
  • resources/references/playbook/principles/05-alignment.md 11 KB
  • resources/references/playbook/principles/06-contrast.md 6 KB
  • resources/references/playbook/principles/07-simplicity.md 3 KB
  • resources/references/playbook/principles/08-whitespace.md 10 KB
  • resources/references/playbook/principles/09-layout.md 10 KB
  • resources/references/playbook/principles/10-balance.md 5 KB
  • resources/references/playbook/principles/11-consistency.md 11 KB
  • resources/references/playbook/principles/12-visual-cues.md 4 KB
  • resources/references/playbook/principles/13-depth.md 19 KB
  • resources/references/playbook/principles/14-color.md 10 KB
  • resources/references/playbook/principles/15-typography.md 38 KB
  • resources/references/playbook/principles/16-interaction-cost.md 24 KB
  • resources/references/playbook/principles/17-forms.md 9 KB
  • resources/references/playbook/principles/18-dialogs.md 6 KB
  • resources/references/playbook/principles/19-content-and-states.md 16 KB
  • resources/references/polish/animations.md 5 KB
  • resources/references/polish/enter-exit.md 4 KB
  • resources/references/polish/icon-transitions.md 3 KB
  • resources/references/polish/icons.md 4 KB
  • resources/references/polish/performance.md 2 KB
  • resources/references/polish/surfaces.md 4 KB
  • resources/scripts/audit-rendered-ui.js 21 KB
  • resources/scripts/contrast.mjs 2 KB
  • resources/scripts/page-eval.mjs 8 KB
  • resources/templates/findings.md 1 KB
  • resources/templates/implementation-plan.md 2 KB

Wersje

RepozytoriumWynikLicencja
Ta strona · aadarsh-jayswal/UI-UX-Master100MIT
ibelick/ui-skills100MIT
DanielD2G/dgstack100MIT
aadarsh-jayswal/UI-UX-Master100MIT

Migawka bazy z 13.11.2026 · wersja paczki b40548b04615 (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

  • 100superior-ui-audit
    Przeprowadza audyt istniejącego interfejsu bez zmian w kodzie i przygotowuje rekomendacje oraz plany wdrożeniowe.
  • 90audit-design-surface
    Ocenia istniejący interfejs i ścieżkę użytkownika pod kątem użyteczności, stanów, dostępności, responsywności i spójności.
  • 90improve-animations
    Ocenia animacje i przejścia interfejsu, wskazuje priorytety i przygotowuje gotowe plany wdrożenia.
  • 90integra-design-qa
    Przegląda istniejący interfejs lub przepływ pod kątem UX, jakości wizualnej, responsywności i ryzyk wdrożeniowych.
  • 100reviewing-interface-quality
    Ocenia istniejący interfejs użytkownika: dlaczego wygląda ogólnie, co jest niedopracowane i jak go dopolerować przed wdrożeniem.
  • 100design-review
    Przegląda istniejący interfejs względem własnego systemu designu, zgłasza błędy od najmocniej uderzających w użytkownika, z dowodami i poprawką.

Uwagi i zgłoszenia

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