Run any Skill in Manus with one click

ui-ux-review

Stars2

Forks0

UpdatedJuly 9, 2026 at 11:17

Reviews a running app's user experience by walking through every screen (or command/endpoint surface) and writing severity-tagged findings to docs/UI-UX-REVIEW.md. Use when the user asks for a UI review, UX walkthrough, design QA, or a "does the app feel right" pass on a live app.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

deepception

deepception/cc_tool

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Web and Digital Interface DesignersComputer and Mathematical Occupations·SOC 15-1255

File Explorer

2 files

SKILL.md

readonly

More from this repository

same repository

app-qa

deepception/cc_tool

Runs a full QA engagement for an app: e2e test plan and execution, UI/UX walkthrough review, and static frontend review — up to three docs in the project's docs/. Use when the user asks to "QA this app", "test and review the app", or wants the full treatment; for a single activity invoke e2e-testing, ui-ux-review, or frontend-review directly.

2026-07-092

e2e-testing

deepception/cc_tool

Plans and runs end-to-end tests against a running app — web, API, CLI, TUI, or mobile — producing docs/E2E-TEST-PLAN.md with executable scenarios and walkthrough results. Use when the user asks to e2e-test an app, verify user flows end to end, do a test walkthrough, or write an e2e test plan.

2026-07-092

frontend-review

deepception/cc_tool

Static source review of an app's interface layer — API client and auth plumbing, state management, component quality, i18n, type safety, accessibility, test coverage, build hygiene — written to docs/FRONTEND-REVIEW.md. Use when the user asks for a frontend code review or a source-level complement to live testing. Runs without the app running.

2026-07-092

loop-engineering

deepception/cc_tool

The structural model of an autonomous loop — the four loop types (turn-based, goal-based, time-based, proactive), the six components, and inner/outer layering — for designing a loop rather than one-off prompting. Consult when turning a repeated task into a loop, picking the right loop type, deciding what a loop must contain to run unattended, or when the user asks to "set up a loop / make this run on its own". For the native Workflow tool's orchestration patterns see dynamic-workflows; for the operational safety checklist see "Safe autonomous loops" in CLAUDE.md.

2026-07-082

vault

deepception/cc_tool

Self-writing vault — a single-inbox markdown vault for the USER'S raw project thinking (voice transcripts, quick notes, half-ideas), which Claude files, cross-links, and synthesizes on a schedule without the user. Operations: init (scaffold), process (inbox → linked notes + daily digest), synthesize (weekly themes/contradictions), health (graph pulse). Use when the user wants to set up a vault, capture a thought mid-session, process the inbox, or run note upkeep unattended. Distinct from knowledge-wiki (digests an EXTERNAL source corpus) and basic-memory (cross-project decision graph).

2026-07-082

design-director

deepception/cc_tool

Control layer for frontend visual design work — landing pages, hero sections, portfolios, marketing sites, redesigns, "make it look good / premium / not generic". Reads the brief, routes to the right globally-installed taste-skill variant (design-taste-frontend, minimalist-ui, industrial-brutalist-ui, high-end-visual-design, redesign-existing-projects), and composes a section-by-section master design prompt from the archetype templates in references/. For API/module interface shape use design-an-interface instead; for dashboards and data-heavy product UI this skill mostly does not apply.

2026-07-082

name	ui-ux-review
description	Reviews a running app's user experience by walking through every screen (or command/endpoint surface) and writing severity-tagged findings to docs/UI-UX-REVIEW.md. Use when the user asks for a UI review, UX walkthrough, design QA, or a "does the app feel right" pass on a live app.
user-invocable	true
argument-hint	["app-path-or-description"]

UI/UX Review

Your task is to review the running app's user experience surface by surface and write docs/UI-UX-REVIEW.md in the target project.

Steps

Baseline — Establish and record the vantage point: profile/role, viewport, theme, locale, date. The review is a snapshot from a stated baseline, not a universal claim.
Access the app — Reuse the driver detection in e2e-testing's driving-tools reference if installed alongside; otherwise probe ToolSearch for a browser/device driver. No driver → paired mode: the user walks, shares screenshots and observations, you record.
Walk every surface — Follow references/review-rubric.md: global findings first, then one section per screen, each finding tagged 🔴/🟡/🔵. For CLI/API apps the rubric's adaptation table redefines "screen".
Sweep beyond the happy path — The rubric's checklist: both themes, narrow viewport, i18n leaks and diacritics, empty states, loading states, error states.
Record what works — A "What already works well (keep)" section is part of the doc: it protects good patterns from churn and keeps the review actionable.
Close with fix order — A short numbered list: severity first, cheap-and-visible next.

Boundaries

A functional bug found on the way (crash, data loss, logout trap) belongs in the e2e test plan — cross-reference it if one exists; otherwise record it here and suggest running e2e-testing.
Root causes in source belong to frontend-review; here record the observed symptom.