Skip to main content
ClaudeWave
Skill4.3k repo starsupdated 7d ago

ui-ux-pro-max

**ui-ux-pro-max** generates cohesive design systems and implementation guidance for UI projects by extracting product signals, recommending palettes and typography, and providing stack-aware code direction. Use it when a user needs to design or review interfaces, build dashboards or landing pages, improve accessibility, or establish consistent styling across multiple pages, especially after the product direction is already determined.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/Galaxy-Dawn/claude-scholar /tmp/ui-ux-pro-max && cp -r /tmp/ui-ux-pro-max/skills/ui-ux-pro-max ~/.claude/skills/ui-ux-pro-max
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# UI/UX Pro Max

Use this skill to turn a vague UI request into a **concrete design system plus implementation guidance**.

## Role

This skill is for:
- design-system selection,
- palette and typography choices,
- UX review and remediation,
- stack-aware frontend implementation guidance,
- lightweight design-system persistence for multi-page work.

It is **not** a replacement for product strategy or user research. Use it to make execution sharper after the product direction is already roughly known.

## Core workflow

### 1. Infer the request shape

Extract the minimum design signals first:
- product type,
- industry,
- style keywords,
- target platform,
- implementation stack.

If the user does not specify a stack, default to `html-tailwind`.

### 2. Generate the design system first

Use the helper script to produce a compact design recommendation:

```bash
python3 "${CLAUDE_PLUGIN_ROOT}/skills/ui-ux-pro-max/scripts/search.py" "<product_type> <industry> <keywords>" --design-system -p "Project Name"
```

This produces:
- recommended style direction,
- palette family,
- typography direction,
- interaction / visual effects,
- landing or layout bias,
- anti-patterns to avoid.

If the work spans multiple turns or pages, persist the design system:

```bash
python3 "${CLAUDE_PLUGIN_ROOT}/skills/ui-ux-pro-max/scripts/search.py" "<query>" --design-system --persist -p "Project Name"
python3 "${CLAUDE_PLUGIN_ROOT}/skills/ui-ux-pro-max/scripts/search.py" "<query>" --design-system --persist -p "Project Name" --page "dashboard"
```

This creates:
- `design-system/MASTER.md`
- optional page-level override notes under `design-system/pages/`

### 3. Pull targeted guidance only when needed

Use a focused search instead of loading everything at once:

```bash
python3 "${CLAUDE_PLUGIN_ROOT}/skills/ui-ux-pro-max/scripts/search.py" "glassmorphism dark" --domain style
python3 "${CLAUDE_PLUGIN_ROOT}/skills/ui-ux-pro-max/scripts/search.py" "animation accessibility" --domain ux
python3 "${CLAUDE_PLUGIN_ROOT}/skills/ui-ux-pro-max/scripts/search.py" "real-time dashboard" --domain chart
python3 "${CLAUDE_PLUGIN_ROOT}/skills/ui-ux-pro-max/scripts/search.py" "elegant luxury serif" --domain typography
```

Supported domains:
- `product`
- `style`
- `color`
- `typography`
- `landing`
- `chart`
- `ux`

### 4. Add stack-specific guidance before coding

```bash
python3 "${CLAUDE_PLUGIN_ROOT}/skills/ui-ux-pro-max/scripts/search.py" "forms table responsive" --stack html-tailwind
```

Supported stacks:
- `html-tailwind`
- `react`
- `nextjs`
- `vue`
- `svelte`
- `swiftui`
- `react-native`
- `flutter`
- `shadcn`
- `jetpack-compose`

### 5. Synthesize before implementation

After gathering the design system, convert it into:
- layout structure,
- component rules,
- visual tokens,
- interaction rules,
- accessibility constraints,
- implementation notes for the chosen stack.

Do not dump raw search output into the final answer. Use it to justify a coherent design direction.

## Default output shape

A good response should usually include:
1. product and UI framing,
2. recommended style system,
3. palette and typography,
4. component and layout rules,
5. accessibility and interaction checks,
6. stack-aware implementation notes.

## Safety rules

- Do not hardcode a design language without connecting it to the product type.
- Do not use emoji as primary UI iconography.
- Do not weaken text contrast for visual flair.
- Do not scale interactive cards on hover if it destabilizes layout.
- Do not use animation that violates `prefers-reduced-motion`.
- Do not invent unsupported helper scripts or datasets; use the bundled `search.py` and `data/ui-reasoning.csv` only.

## References

Load only what is needed:
- `references/USAGE.md` - recommended command patterns and retrieval flow
- `data/ui-reasoning.csv` - compact product-to-design heuristics used by the helper script
- `scripts/search.py` - deterministic helper for design-system, domain, and stack lookup
code-reviewerSubagent

Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.

kaggle-minerSubagent

Use this agent when the user provides a Kaggle competition URL or asks to learn from Kaggle winning solutions. Examples:

literature-reviewerSubagent

Use this agent when the user asks to "conduct literature review", "search for papers", "analyze research papers", "identify research gaps", "review related work", or mentions starting a research project. This agent integrates with Zotero for automated paper collection, organization, and full-text analysis. Examples:

paper-minerSubagent

Use this agent when the user provides a research paper (PDF/DOCX/arXiv link) or asks to learn writing patterns from papers, extract venue-specific writing signals, study paper structure, or mine rebuttal strategies. The agent writes extracted knowledge into the active installed paper-miner writing memory for ml-paper-writing. It does not maintain project-specific writing memory.

rebuttal-writerSubagent

Use this agent when the user asks to "write rebuttal", "respond to reviewers", "analyze review comments", or needs help with academic paper review response. This agent specializes in systematic rebuttal writing with professional tone and structured responses.

tdd-guideSubagent

Test-driven development guide for writing tests first, implementing the smallest passing change, and keeping verification tight. Use when the user explicitly wants TDD or when a task should be driven by failing tests before code.

analyze-resultsSlash Command

Run a blocker-first post-experiment workflow: validate evidence, produce strict statistical analysis when possible, and generate a decision-oriented results report only when the analysis bundle is sufficient. Uses results-analysis + results-report as a gated two-stage workflow.

commitSlash Command

Commit changes following Conventional Commits format (local only, no push).