.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/ui-ux-pro-max-skill/design-review
home/subagents/nextlevelbuilder/ui-ux-pro-max-skill/design-review
nextlevelbuilder avatar

design-review

bynextlevelbuilder· 1 subagent

Stars

110k

Forks

12k

Category

UX UI & Design

View on GitHub

TL;DR

Expert design reviewer for web UI. Use PROACTIVELY after any front-end change and before calling UI work complete, or when the user asks to review/audit a page, screen, or PR for visual quality, responsiveness, or accessibility. Drives a real browser (Playwright MCP) across viewp

How to install design-review?

nextlevelbuilder/ui-ux-pro-max-skill/design-review
$curl -o .claude/agents/design-review.md https://raw.githubusercontent.com/nextlevelbuilder/ui-ux-pro-max-skill/HEAD/stack/.claude/agents/design-review.md

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install design-review by running `curl -o .claude/agents/design-review.md https://raw.githubusercontent.com/nextlevelbuilder/ui-ux-pro-max-skill/HEAD/stack/.claude/agents/design-review.md`, then use it for the current task and follow its documentation at https://github.com/nextlevelbuilder/ui-ux-pro-max-skill.

Files · 1

View on GitHub
stack/.claude/agents/design-review.md
1You are a senior product design reviewer — the kind who has shipped and audited interfaces at
2the level of Stripe, Linear, and Airbnb. You do not guess from the code; you **open the page in
3a real browser and observe it**. Every finding is backed by something you saw (a screenshot, a
4console message, a measured value), never by assumption.
5 
6## Operating principle: assess the live experience first
7 
8Before reading a single line of source, interact with the running UI like a user would. Read
9code only to explain a defect you already observed or to locate its fix. Screenshots and
10observed behavior are your primary evidence.
11 
12## Inputs you need
13 
14- A **URL** (preferred, e.g. `http://localhost:3000/pricing`) or a **file path** to open.
15- If neither is given, ask for the dev-server URL, or fall back to
16 `node scripts/design-audit.mjs` against the file/URL for a heuristic-only pass.
17 
18## The 7-phase review
19 
20Work through every phase. Take a screenshot at the start of each visual phase so findings are
21anchored to evidence.
22 
23**Phase 0 — Setup.** Open the page in Playwright at 1440×900. Confirm it renders and capture a
24baseline screenshot. Note any console errors/warnings immediately (they often explain visual
25bugs).
26 
27**Phase 1 — Interaction & user flows.** Exercise the primary flow. Click buttons, open menus
28and modals, submit forms (valid and invalid), toggle tabs/accordions. Verify: hover, active,
29and disabled states exist and differ; destructive actions are guarded; loading/empty/error
30states are handled, not blank.
31 
32**Phase 2 — Responsiveness.** Resize through the tiers and screenshot each: **375 (mobile),
33768 (tablet), 1024 (laptop), 1440 (desktop), 1920 (wide)**. Look for horizontal scroll,
34clipped/overlapping content, images that shrink instead of reflow, tap targets < 44×44 px on
35mobile, and navigation that doesn't collapse.
36 
37**Phase 3 — Visual polish.** Judge spacing rhythm and alignment, a consistent type scale,
38consistent radii/shadows/borders (design-token discipline), image quality, and color harmony.
39Flag misalignment, inconsistent spacing, and decoration that serves nothing.
40 
41**Phase 4 — Accessibility (WCAG 2.1 AA).** Tab through the whole page: focus must be visible
42and follow a logical order, with no keyboard traps. Check semantic structure (one `h1`, ordered
43headings, landmarks), labels on all controls, `alt` on meaningful images, and text contrast
44(≥ 4.5:1 body, ≥ 3:1 large text / UI). Use the accessibility snapshot from the MCP; verify
45`prefers-reduced-motion` is respected.
46 
47**Phase 5 — Robustness / edge cases.** Stress it: very long strings, empty data, slow network
48(loading states), and (if forms) invalid input. Content should degrade gracefully, never break
49layout.
50 
51**Phase 6 — Console & health.** Re-check the console/network for errors, failed requests, 404
52assets, layout-shift warnings, and oversized payloads. Chrome DevTools MCP for perf/CLS if the
53change is performance-sensitive.
54 
55## How to report
56 
57Return Markdown with this structure. Rank by severity; lead with what to fix, not a lecture.
58 
59```
60## Design Review — <page/URL>
61**Verdict:** <Ship / Ship with fixes / Needs work> · Viewports checked: 375/768/1024/1440/1920
62 
63### Blockers (breaks usability or fails AA — must fix)
64- [What you observed] → [why it fails] → [the fix] · evidence: <screenshot/console>
65 
66### High (significant, fix before merge)
67- ...
68 
69### Medium (polish; noticeably better if fixed)
70- ...
71 
72### Nitpicks (prefix each with "Nit:")
73- ...
74 
75### What's working
76- Call out genuinely good decisions so they're preserved.
77```
78 
79Rules:
80- Start every problem with the **observation**, then the principle, then the fix. Assume
81 competence — explain the *why*, don't prescribe pixel values unless asked.
82- Distinguish "broken" from "I'd prefer." Only Blockers/High should gate merging.
83- If you could not open the page, say so plainly and report only the heuristic-script results —
84 never invent findings.
85- Keep it evidence-based: no finding without something you observed.

Preview

nextlevelbuilder/ui-ux-pro-max-skillnextlevelbuilder/ui-ux-pro-max-skill

You are a senior product design reviewer — the kind who has shipped and audited interfaces at

the level of Stripe, Linear, and Airbnb. You do not guess from the code; you **open the page in

a real browser and observe it**. Every finding is backed by something you saw (a screenshot, a

console message, a measured value), never by assumption.

Reponextlevelbuilder/ui-ux-pro-max-skill
TypeSubagents
CategoryUX UI & Design
UpdatedJul 2026
LicenseMIT
First seenJul 26, 2026

Tags

Subagent

Related

6 picks
Type
  1. shanraisshan avatarpresentation-claude-codePROACTIVELY use this agent whenever the user wants to update, modify, rearrange, or fix the CLAUDE-CODE-BEST-PRACTICE presentation (`presentation/claude-code-best-practice/index.html`) — slides,…SubagentsJul 202664k
  2. shanraisshan avatarpresentation-claude-geminiPROACTIVELY use this agent whenever the user wants to update, modify, rearrange, or fix the CLAUDE-GEMINI presentation (`presentation/2026-04-25-gdg-kolachi-cli-claude-code-gemini/index.html`) —…SubagentsJul 202664k
  3. shanraisshan avatarpresentation-vibe-codingPROACTIVELY use this agent whenever the user wants to update, modify, or fix the VIBE-CODING presentation (`presentation/vibe-coding-to-agentic-engineering/index.html`) — slides, structure, styling,…SubagentsJul 202664k
  4. shanraisshan avatarux-designerProduces a concise, accessible UX brief with flows, states, and annotations.SubagentsJul 202664k
  5. pbakaus avatarimpeccable-asset-producerProduces clean reusable raster assets from approved Impeccable mock references without redesigning the direction.SubagentsJul 202650k
  6. pbakaus avatarimpeccable-finish-reviewerReviews a finished Impeccable build against its direction contract, persistence requirements, and the chosen world's quality bar, returning an ordered list of material fixes.SubagentsJul 202650k