Agent skill

Review UI

by aaddrick in aaddrick/claude-pipeline

Comprehensive UI/CSS review using parallel agents. An agent skill from aaddrick/claude-pipeline.

MITAuto-check passedFrontend & Design

Install Review UI

skills CLI
$ npx skills add aaddrick/claude-pipeline --skill review-ui -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install aaddrick/claude-pipeline review-ui --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/aaddrick/claude-pipeline.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/review-ui .claude/skills/review-ui && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
review-ui
GitHub stars
130
Token cost
~2.5k tokens
SKILL.md length
374 words
Files
3
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Comprehensive UI/CSS review using parallel agents. An agent skill from aaddrick/claude-pipeline.

  • Works in 4 steps: Scope Identification: Determines what… → Parallel Dispatch: Launches independent… → Compilation: Aggregates findings into a… → …
  • Reviewing frontend code
  • SKILL.md covers Overview, Usage, How It Works and Review Domains, plus 9 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Review UI is an agent skill from aaddrick/claude-pipeline. Comprehensive UI/CSS review using parallel agents. Each agent reviews against a specific UI design fundamentals section. Use when reviewing frontend code, CSS, Blade templates, or components.

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agent-prompts.md` and `review-criteria.md`).

It sits in Frontend & Design, covering UI design and Subagents. The repository describes itself as: Portable Claude Code multi-agent pipeline - skills, agents, hooks, orchestration scripts, and quality gates. The licence is MIT.

When your agent uses it

  • Reviewing frontend code
  • Blade templates

Example prompts

  • “/review-ui”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Scope Identification: Determines what files/components to review
  2. Parallel Dispatch: Launches independent agent tasks, each focused on one UI fundamentals section
  3. Compilation: Aggregates findings into a prioritized action list
  4. Summary: Produces executive summary with critical issues highlighted

What it can do on your machine

Read from SKILL.md and the folder at commit 402eac7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown and bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Review UI loads about 2.5k tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 374 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~50
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from aaddrick/claude-pipeline at commit 402eac7, republished under its MIT licence (© aaddrick). 374 words, ~2,474 tokens.

Download SKILL.mdSave it as .claude/skills/review-ui/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
review-ui
description
Comprehensive UI/CSS review using parallel agents. Each agent reviews against a specific UI design fundamentals section. Use when reviewing frontend code, CSS, Blade templates, or components.

UI Review Skill

Overview

Reviews frontend code against the complete UI design fundamentals specification using parallel bulletproof-frontend-developer agents. Each agent focuses on one design domain, producing a comprehensive, multi-perspective review.

Usage

/review-ui <scope>

Scope can be:

  • File path: /review-ui resources/css/components/buttons.css
  • Component: /review-ui resources/views/components/landing/
  • Glob pattern: /review-ui resources/css/**/*.css
  • Description: /review-ui "the pricing section on the welcome page"

How It Works

  1. Scope Identification: Determines what files/components to review
  2. Parallel Dispatch: Launches independent agent tasks, each focused on one UI fundamentals section
  3. Compilation: Aggregates findings into a prioritized action list
  4. Summary: Produces executive summary with critical issues highlighted

Review Domains

Each parallel agent reviews against one of these UI design fundamentals sections:

DomainReference FileFocus Areas
Grid & Spacinggrid-and-spacing.md8pt grid compliance, margins, gutters, white space, alignment
Typographytypography.mdType scale, font weights, line heights, hierarchy, readability
Colorscolors.mdWCAG contrast (4.5:1+), color roles, 60-30-10 balance, dark mode
Buttonsbuttons.mdAnatomy, states, hierarchy, tap targets (44px+), CTAs
Formsforms.mdLabels, validation, input states, accessibility, sizing
Cardscards.mdAnatomy, spacing consistency, content truncation, hover states
Navigationnavigation.mdActive states, sticky behavior, mobile patterns, hover
Hero Sectionshero-sections.mdAbove the fold, headline hierarchy, CTA placement, social proof
Modals & Dropdownsmodals-and-dropdowns.mdClose methods, focus trap, keyboard nav, overlay
Searchsearch.mdPlacement, autocomplete, no-results handling
Shadows & Depthshadows-and-depth.mdElevation levels, shadow direction, dark mode shadows
Pricingpricing.mdPlan highlighting, feature lists, risk reducers
Style Consistencystyle-guides.mdToken usage, naming conventions, component patterns
Show full SKILL.md (136 more words)Show less

Agent Prompt Template

Each agent receives this structured prompt:

markdown
Review the following files for **{DOMAIN}** compliance:

**Files to review:**
{FILE_LIST}

**Reference standard:**
.claude/skills/ui-design-fundamentals/{REFERENCE_FILE}

**Review criteria from {DOMAIN}:**
{CRITERIA_SUMMARY}

**Your task:**
1. Read each file and identify {DOMAIN}-related patterns
2. Compare against the reference standard
3. List issues found with:
   - Severity (Critical/Warning/Suggestion)
   - Location (file:line or component name)
   - Issue description
   - Recommended fix
4. Note any exemplary patterns worth preserving

**Output format:**
## {DOMAIN} Review

### Critical Issues
- ...

### Warnings
- ...

### Suggestions
- ...

### Exemplary Patterns
- ...

Execution Flow

/review-ui <scope>
       │
       ▼
┌──────────────────────┐
│  1. Identify files   │
│     to review        │
└──────────────────────┘
       │
       ▼
┌──────────────────────────────────────────────────────────────┐
│  2. Dispatch parallel bulletproof-frontend-developer agents  │
├──────────────────────────────────────────────────────────────┤
│  Task 1: Grid & Spacing review                               │
│  Task 2: Typography review                                   │
│  Task 3: Colors review                                       │
│  Task 4: Buttons review                                      │
│  Task 5: Forms review                                        │
│  Task 6: Cards review                                        │
│  Task 7: Navigation review                                   │
│  Task 8: Hero Sections review (if applicable)                │
│  Task 9: Modals/Dropdowns review (if applicable)             │
│  Task 10: Search review (if applicable)                      │
│  Task 11: Shadows & Depth review                             │
│  Task 12: Pricing review (if applicable)                     │
│  Task 13: Style Consistency review                           │
└──────────────────────────────────────────────────────────────┘
       │
       ▼
┌──────────────────────┐
│  3. Collect results  │
│     from all agents  │
└──────────────────────┘
       │
       ▼
┌──────────────────────┐
│  4. Compile unified  │
│     review report    │
└──────────────────────┘

Output Format

Executive Summary
markdown
## UI Review Summary: {SCOPE}

**Files Reviewed:** X files
**Review Domains:** X domains (Y applicable, Z not applicable)
**Total Issues:** X (Y critical, Z warnings, W suggestions)

### Critical Issues (Fix Immediately)
1. [Colors] Contrast ratio 2.1:1 on `.btn--secondary` text (requires 4.5:1)
2. [Buttons] Touch target 32px on mobile nav (requires 44px minimum)

### Top 5 Priority Fixes
1. ...
2. ...

### Exemplary Patterns
- [Typography] Consistent type scale using CSS custom properties
- [Cards] Proper BEM naming and hover states
Detailed Findings
markdown
## Detailed Review by Domain

### Grid & Spacing
**Status:** ⚠️ 2 warnings, 3 suggestions

**Warnings:**
- `card.css:15` - Padding 12px breaks 8pt grid (use 8px or 16px)
- `layout.css:42` - Inconsistent section gaps (64px vs 72px)

**Suggestions:**
- Consider container queries for card grid
- ...

---

### Typography
**Status:** ✅ 1 suggestion

**Suggestions:**
- Add `text-wrap: balance` to headings

---

[... continues for each domain ...]

Smart Filtering

Not all domains apply to all code. The skill intelligently skips irrelevant domains:

Scope ContainsApplicable Domains
CSS onlyGrid, Typography, Colors, Shadows, Style Consistency
Component with form+ Forms, Buttons
Landing page+ Hero, Pricing, Cards, Navigation
Dashboard+ Cards, Navigation, Modals
Single buttonButtons, Colors, Typography

Configuration Options

Optionally pass flags to customize the review:

bash
# Focus on specific domains only
/review-ui resources/css/buttons.css --domains=buttons,colors,accessibility

# Skip certain domains
/review-ui resources/views/components/ --skip=pricing,hero

# Critical issues only
/review-ui resources/css/ --severity=critical

# Generate fix suggestions with code
/review-ui resources/css/ --with-fixes

Integration with Code Review

Use this skill before creating PRs:

  1. Run /review-ui on changed files
  2. Address critical issues
  3. Document intentional deviations
  4. Create PR with review results in description
  • bulletproof-frontend — CSS implementation patterns, Tailwind refactoring
  • ui-design-fundamentals — Design values and specifications (referenced by this skill)
  • requesting-code-review — General code review workflow

Reference Files

All review criteria come from:

.claude/skills/ui-design-fundamentals/
├── SKILL.md                    # Overview and core principles
├── grid-and-spacing.md         # 8pt grid, layouts, white space
├── typography.md               # Type scales, hierarchy, fonts
├── colors.md                   # WCAG contrast, palettes, dark mode
├── buttons.md                  # Anatomy, states, CTAs
├── forms.md                    # Labels, validation, inputs
├── cards.md                    # Anatomy, consistency, types
├── navigation.md               # Nav bars, mobile, breadcrumbs
├── hero-sections.md            # Above fold, headlines, CTAs
├── modals-and-dropdowns.md     # Dialogs, dropdowns, accordions
├── search.md                   # Search bars, autocomplete
├── pricing.md                  # Pricing sections, psychology
├── shadows-and-depth.md        # Elevation, shadows, gradients
└── style-guides.md             # Tokens, documentation, naming

Example Session

User: /review-ui resources/views/components/landing/

Claude: Starting UI review of landing components...

**Scope identified:** 8 files
- how-it-works.blade.php
- resources.blade.php
- hero.blade.php
- pricing.blade.php
- testimonials.blade.php
- features.blade.php
- cta-banner.blade.php
- footer.blade.php

**Applicable domains:** Grid, Typography, Colors, Buttons, Cards, Hero, Navigation, Pricing, Shadows, Style Consistency

**Dispatching 10 parallel review agents...**

[Agents complete reviews in parallel]

## UI Review Summary: Landing Components

**Files Reviewed:** 8 Blade templates + associated CSS
**Review Domains:** 10 domains applied
**Total Issues:** 12 (3 critical, 5 warnings, 4 suggestions)

### Critical Issues (Fix Immediately)

1. **[Colors]** `hero.blade.php` - CTA button text contrast is 3.8:1 (requires 4.5:1)
   - Location: `.hero__cta` with `color: #7c8db0` on `background: #4f46e5`
   - Fix: Change text to `#ffffff` for 8.1:1 contrast

2. **[Buttons]** `pricing.blade.php` - "Get Started" button is 36px height on mobile
   - Location: `.pricing-card__cta`
   - Fix: Add `min-height: 44px` for touch target compliance

3. **[Forms]** `cta-banner.blade.php` - Email input has no visible label
   - Location: `.cta-banner__input`
   - Fix: Add `<label>` element or `aria-label` attribute

### Top 5 Priority Fixes
1. Fix CTA button contrast in hero section
2. Increase touch targets on pricing buttons
3. Add labels to form inputs
4. Standardize section padding to 8pt grid
5. Add focus-visible states to all interactive elements

[... detailed findings by domain ...]

© aaddrick, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files in .claude/skills/review-ui of aaddrick/claude-pipeline.

  • SKILL.md
  • agent-prompts.md
  • review-criteria.md

Open the folder on GitHubat commit 402eac7

Compare with similar skills

Review UI next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Review UI compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Review UI this skillaaddrick/claude-pipeline130—~2.5kAutomated safety check: PassMIT
Instruction Dashboard Tuningadam-s/intercept189—~4.3kAutomated safety check: PassMIT
UI StylingOhh-889/skyroc79513 repos~2.5kAutomated safety check: PassMIT
LobeHub Interactive Prototypelobehub/lobehub83k—~1.6kAutomated safety check: PassCustom licence
Make Interfaces Feel Bettersamuelclay/NewsBlur7.6k10 repos~1.5kAutomated safety check: PassMIT
UI UX Pro MaxZxBing0066/pixel-converter18113 repos~2.6kAutomated safety check: NotesBSD-2-Clause

Similar skills

  • Use sub-agents to iteratively improve dashboard-building instructions.

    189 GitHub stars~4.3k tokensUpdated 2 mo ago
    Frontend & DesignAuto-check passed
  • UI Styling

    Ohh-889/skyroc

    Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs.

    795 GitHub starsUsed in 13 repos~2.5k tokens
    Frontend & DesignAuto-check passed
  • Builds single-file interactive HTML prototypes rendered with the real LobeHub UI components and written as production-style React, so they can later be split into files.

    83k GitHub stars~1.6k tokensUpdated today
    Frontend & DesignAuto-check passed
  • Make Interfaces Feel Better

    samuelclay/NewsBlur

    Design engineering principles for making interfaces feel polished.

    7.6k GitHub starsUsed in 10 repos~1.5k tokens
    Frontend & DesignAuto-check passed
  • UI UX Pro Max

    ZxBing0066/pixel-converter

    UI/UX design intelligence with searchable database. An agent skill from ZxBing0066/pixel-converter.

    181 GitHub starsUsed in 13 repos~2.6k tokens
    Frontend & DesignAuto-check: notes
  • Design Dna

    zanwei/design-dna

    Extract, define, and apply design DNA across three dimensions: design system (tokens), design style (qualitative feel), and visual effects (Canvas, WebGL, 3D, particles, shaders, scroll effects…

    1.9k GitHub starsUsed in 1 repo~2.1k tokens
    Frontend & DesignAuto-check passed

More from aaddrick/claude-pipeline

All 12 skills in this repo
  • Writing Agents

    aaddrick/claude-pipeline

    A skill your agent uses when creating new agents, editing existing agents, or defining specialized subagent roles for the Task tool

    130 GitHub starsUsed in 1 repo~3.3k tokens
    Auto-check passed
  • Adapting Claude Pipeline

    aaddrick/claude-pipeline

    A skill your agent uses when adapting the generic .claude pipeline folder to a specific codebase - adjusting skills, agents, hooks, scripts, prompts, and settings for the target project's tech stack…

    130 GitHub stars~2.8k tokensUpdated 7 mo ago
    Auto-check passed
  • A skill your agent uses when asked to create user stories from a codebase, document existing features as stories, or reverse-engineer requirements from code

    130 GitHub stars~2.2k tokensUpdated 7 mo ago
    Auto-check passed
  • Using Git Worktrees

    aaddrick/claude-pipeline

    A skill your agent uses when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees in .worktrees/

    130 GitHub stars~1.3k tokensUpdated 7 mo ago
    Auto-check passed
  • Implement Issue

    aaddrick/claude-pipeline

    A skill your agent uses when given a GitHub issue number and base branch to implement end-to-end

    130 GitHub starsUsed in 1 repo~889 tokens
    Auto-check passed
  • Write Docblocks

    aaddrick/claude-pipeline

    A skill your agent uses when documentation coverage is low, after composer docs:coverage shows gaps, or when asked to batch-write PHPDoc blocks across multiple files

    130 GitHub stars~956 tokensUpdated 7 mo ago
    Auto-check passed

Questions about Review UI

What does Review UI do?

Comprehensive UI/CSS review using parallel agents. An agent skill from aaddrick/claude-pipeline. Review UI is an agent skill from aaddrick/claude-pipeline. Comprehensive UI/CSS review using parallel agents.

When should I use Review UI?

Review UI fits situations like: reviewing frontend code; blade templates.

How do I install Review UI in Claude Code?

Run `npx skills add aaddrick/claude-pipeline --skill review-ui -a claude-code`. Or copy the skill folder (.claude/skills/review-ui in aaddrick/claude-pipeline) into .claude/skills/review-ui in your project. Claude Code loads it when a task matches its description.

How do I install Review UI in Codex?

Run `npx skills add aaddrick/claude-pipeline --skill review-ui -a codex`. Or copy the skill folder (.claude/skills/review-ui in aaddrick/claude-pipeline) into .agents/skills/review-ui in your project. Codex loads it when a task matches its description.

Can I use Review UI in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aaddrick/claude-pipeline --skill review-ui -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/review-ui, .gemini/skills/review-ui, .github/skills/review-ui and .opencode/skills/review-ui in your project.

What does Review UI need to run?

SKILL.md names no scripts, command-line tools or credentials: Review UI is instructions for the agent only.

Does Review UI access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Review UI safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Review UI use?

Review UI is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Review UI use?

About 2.5k tokens (SKILL.md is roughly 9.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Review UI?

Skills that share tags, products or a category with Review UI: Instruction Dashboard Tuning (adam-s/intercept, 189 stars), UI Styling (Ohh-889/skyroc, 795 stars), LobeHub Interactive Prototype (lobehub/lobehub, 83k stars) and Make Interfaces Feel Better (samuelclay/NewsBlur, 7.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Review UI?

aaddrick (a GitHub user) maintains it in aaddrick/claude-pipeline, which has 130 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on February 25, 2026.

Source: aaddrick/claude-pipeline on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.