# Ywc Ui Ux Review

> >-

- **Type:** Skill
- **Install:** `agentstack add skill-yongwoon-ywc-agent-toolkit-ywc-ui-ux-review`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [yongwoon](https://agentstack.voostack.com/s/yongwoon)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [yongwoon](https://github.com/yongwoon)
- **Source:** https://github.com/yongwoon/ywc-agent-toolkit/tree/main/claude-code/skills/ywc-ui-ux-review

## Install

```sh
agentstack add skill-yongwoon-ywc-agent-toolkit-ywc-ui-ux-review
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# UI/UX Review — Hybrid (Code + Live UI)

**Announce at start:** "I'm using the ywc-ui-ux-review skill to combine static code analysis with live UI exploration."

Conduct a prioritized UI/UX review of a project by combining static code analysis with live UI exploration. Focus areas: Information Architecture and Visual Design. Output: a four-tier (Critical / High / Medium / Low) Markdown report.

## Rationalization Defense

When tempted to skip a step, check this table first:

| Excuse | Reality |
|---|---|
| "Code-only review is enough, no need to launch the browser" | Hybrid means **both**. Static analysis cannot detect runtime layout shift, focus traps, or hover state breakage. |
| "WCAG checks are exhaustive, skip them on internal tools" | Internal tools have employees with disabilities too. WCAG 2.2 AA is the minimum, not an opt-in. |
| "Reduced motion / dark mode are edge cases, drop them" | These are accessibility requirements, not edge cases. Test both. |
| "Severity feels Critical, mark it Critical regardless of impact" | Critical = blocks core flow or violates accessibility law. Reserve it. Inflated severity buries real critical findings. |
| "Visual taste is subjective, do not flag design inconsistency" | Inconsistency in tokens (color, spacing, typography) is objective. Always flag. |
| "Live exploration is risky on production, skip it" | Use a staging or preview URL. Skipping live exploration drops half the value of this skill. |
| "IA and Visual Design share context, run them together" | They share evidence but use distinct checklists; parallel subagents each read only one checklist, reducing context load and preventing cross-domain finding drift. |

**Violating the letter of these rules is violating the spirit.** Static-only review with no live UI is design auditing on paper.

## Triggers

- "Review the UI/UX of this project"
- "Audit usability of {feature/page}"
- Information Architecture or navigation evaluation
- Visual hierarchy / typography / spacing / color audit
- Pre-release UX checks against WCAG 2.2 AA
- Cross-cutting design review against an internal design system

## Workflow

Run the six phases in order. Skip a phase only with explicit user consent.

### Phase 1 — Scope & Context

Confirm the following with the user before any analysis. When ambiguous, ask:

- **Target**: pages, routes, or feature flows in scope
- **Primary user journey**: the one or two flows that matter most
- **Stack**: framework (React / Vue / Flutter / Astro / etc.) and design system in use
- **Live URL**: a running URL or local dev server (required for Phase 3)
- **Internal design system**: location of tokens, components, design guidelines (if any)

If no live URL is available, note it in the report and proceed with code-only review (degrade gracefully).

### Phase 2 — Code Reconnaissance

Use `Read`, `Grep`, `Glob` to map:

- Routing tree and navigation structure (router config, route files)
- Top-level layouts and shell components
- Design tokens (colors, typography, spacing) — typically `tokens.css`, `theme.ts`, `tailwind.config.*`, `*.tokens.json`, `design-system/`
- Shared UI components and their variants
- Localization / i18n surface, if any

Capture findings as raw notes — do not score yet.

### Phase 3 — Live UI Exploration (Chrome DevTools MCP)

Prefer Chrome DevTools MCP for inspection-focused analysis (token-efficient accessibility tree, automated audits, computed style access). Use Playwright MCP only when multi-step interaction automation is required.

Recommended tool sequence:

1. `mcp__chrome-devtools__new_page` or `navigate_page` — open the target URL
2. `mcp__chrome-devtools__take_snapshot` — get accessibility tree (token-efficient, structured)
3. `mcp__chrome-devtools__take_screenshot` — capture visual evidence per breakpoint
4. `mcp__chrome-devtools__resize_page` — repeat for 360 / 768 / 1280 / 1920
5. `mcp__chrome-devtools__lighthouse_audit` — automated accessibility / performance scoring
6. `mcp__chrome-devtools__list_console_messages` — surface runtime errors
7. `mcp__chrome-devtools__evaluate_script` — pull computed styles, contrast, focus chain when needed

For each piece of evidence record: URL, breakpoint, screenshot reference, snapshot excerpt.

### Phase 4 — Per-Domain Review (Parallel)

Use the Task tool to spawn 2 Sonnet subagents in parallel. Pass each subagent the code reconnaissance notes from Phase 2 and the live UI evidence from Phase 3:

| Subagent | Model | Reference |
|---|---|---|
| IA Reviewer | sonnet | `references/ia-checklist.md` |
| Visual Design Reviewer | sonnet | `references/visual-design-checklist.md` |

Each subagent returns findings with:
- Concrete location (file path + line number, OR screen + selector)
- Observed behavior
- Expected behavior (per heuristic)
- Preliminary heuristic citation

### Phase 4b — Merge & Cross-Check

Combine findings from both subagents. Cross-check each finding against `references/heuristics-combined.md` to attach an authoritative citation (Nielsen / WCAG / Material / HIG / internal design system). Deduplicate findings that share the same location.

### Phase 5 — Severity Triage

Load `references/severity-rubric.md` and classify every finding into one of: Critical / High / Medium / Low. The rubric is the single source of truth — do not invent custom levels.

### Phase 6 — Report Generation

Generate the report using `assets/report-template.md` as the structural template. Fill all placeholders. Default output path: `claudedocs/ui-ux-review-{YYYY-MM-DD}.md` unless the user specifies otherwise.

**Output format** — Default is a Markdown report. When the user passes `--format html` (parsed from `$ARGUMENTS`), emit a self-contained HTML report (`claudedocs/ui-ux-review-{YYYY-MM-DD}.html`) instead, following [html-output.md](../references/html-output.md): four severity tabs, color-coded finding cards, screenshots from Phase 3 embedded inline as `data:` URIs, and a `Copy as Markdown` button. The Markdown surface is preserved inside the file, so downstream integration is unaffected.

## Reference Files

| File | When to load |
|---|---|
| `references/ia-checklist.md` | Phase 4, IA review |
| `references/visual-design-checklist.md` | Phase 4, Visual Design review |
| `references/heuristics-combined.md` | Phase 4b, attaching authoritative citation |
| `references/severity-rubric.md` | Phase 5, severity classification |
| `assets/report-template.md` | Phase 6, report scaffolding |

## Output Rules

- **Every finding cites a heuristic** (Nielsen #N / WCAG SC X.X.X / Material spec / HIG section / internal token name)
- **Every finding has a location** (file:line OR screen:selector)
- **Every finding has a concrete recommendation** — code snippet or design change, not just "improve UX"
- Group findings under the four severity tiers exactly as the template defines
- Lead the report with an executive summary: count per tier, top 3 systemic patterns, top 5 recommended actions
- Keep tone factual and respectful — review the work, not the people

## Advisor Escalation Policy

**Budget**: up to **2 Opus advisor calls per invocation**.

Escalate to an Opus advisor only when the executor cannot resolve the severity classification from `references/severity-rubric.md` alone. Two conditions qualify:

| Condition | Example |
|---|---|
| **Borderline Critical vs High** | An accessibility issue blocks assistive-technology users on a primary flow, but only under a specific screen-reader / browser combination that the rubric does not explicitly address — both Critical and High are defensible |
| **Heuristic conflict** | Nielsen's "Visibility of system status" (#1) and Apple HIG's "Clarity" principle produce opposite recommendations for the same UI element (e.g., a persistent loading indicator that aids status visibility but creates visual noise per HIG clarity) |

For all other borderline cases — High vs Medium, Medium vs Low, uncertain evidence from code-only analysis — choose the more conservative (lower) tier and add a brief inline note explaining the uncertainty. Do not escalate these to Opus.

## Boundaries

**Will:**

- Review IA, Visual Design, accessibility, and usability of the target project
- Combine static code evidence with live UI evidence
- Produce a prioritized, citation-backed Markdown report

**Will Not:**

- Re-design or refactor code on the user's behalf (review only — implementation is a separate task)
- Fabricate findings without code or runtime evidence
- Replace formal user testing with real users
- Score subjective beauty — every judgment is anchored to a heuristic

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [yongwoon](https://github.com/yongwoon)
- **Source:** [yongwoon/ywc-agent-toolkit](https://github.com/yongwoon/ywc-agent-toolkit)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-yongwoon-ywc-agent-toolkit-ywc-ui-ux-review
- Seller: https://agentstack.voostack.com/s/yongwoon
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.