Atlas / Skills / cexll / Prototype Prompt Generator

Prototype Prompt GeneratorSAFE

skills/cexll/prototype-prompt-generator

Multi-agent orchestration workflow (Claude Code Codex Gemini OpenCode)

Verdict
SAFE
Grade
B
Trust score
89 /100
Version
—
Hosts
—
License
AGPL-3.0
Stars
2,746
01

Overview

Multi-agent orchestration workflow (Claude Code Codex Gemini OpenCode)

Read from source at commit efe1633380f1OBSERVED · 2026-10-21
Advertisement
02

What it tells the agent

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: prototype-prompt-generator
description: This skill should be used when users need to generate detailed, structured prompts for creating UI/UX prototypes. Trigger when users request help with "create a prototype prompt", "design a mobile app", "generate UI specifications", or need comprehensive design documentation for web/mobile applications. Works with multiple design systems including WeChat Work, iOS Native, Material Design, and Ant Design Mobile.
---

# Prototype Prompt Generator

## Overview

Generate comprehensive, production-ready prompts for UI/UX prototype creation. Transform user requirements into detailed technical specifications that include design systems, color palettes, component specifications, layout structures, and implementation guidelines. Output prompts are structured for optimal consumption by AI tools or human developers building HTML/CSS/React prototypes.

## Workflow

### Step 1: Gather Requirements

Begin by collecting essential information from the user. Ask targeted questions to understand:

**Application Type & Purpose:**
- What kind of application? (e.g., enterprise tool, e-commerce, social media, dashboard)
- Who are the target users?
- What are the primary use cases and workflows?

**Platform & Context:**
- Target platform: iOS, Android, Web, WeChat Mini Program, or cross-platform?
- Device: Mobile phone, tablet, desktop, or responsive?
- Viewport dimensions if known (e.g., 375px for iPhone, 1200px for desktop)

**Design Preferences:**
- Design style: WeChat Work, iOS Native, Material Design, Ant Design Mobile, or custom?
- Brand colors or visual preferences?
- Any design references or inspiration?

**Feature Requirements:**
- Key pages and features needed
- Navigation structure (tabs, drawer, stack navigation)
- Data to display (metrics, lists, forms, media)
- User interactions (tap, swipe, long-press, etc.)

**Content & Data:**
- Actual content to display (realistic text, numbers, names)
- Empty states, error states, loading states
- Any specific business logic or rules

**Technical Constraints:**
- Framework preference: Plain HTML, React, Vue, or framework-agnostic?
- CSS approach: Tailwind CSS, CSS Modules, styled-components?
- Image assets: Real images, placeholders, or specific sources?
- CDN dependencies or version requirements?

**Ask questions incrementally** (2-3 at a time) to avoid overwhelming the user. Many details can be inferred from context or filled with sensible defaults.

### Step 2: Select Design System

Based on the gathered requirements, choose the appropriate design system from `references/design-systems.md`:

**WeChat Work Style:**
- **When to use**: Chinese enterprise applications, work management tools, B2B platforms, internal business systems
- **Characteristics**: Simple and professional, tech blue primary color, clear information hierarchy
- **Key audience**: Chinese business users, corporate environments

**iOS Native Style:**
- **When to use**: iOS-specific apps, Apple ecosystem integration, apps targeting iPhone/iPad users
- **Characteristics**: Minimalist, spacious layouts, San Francisco font, system colors
- **Key audience**: Apple users, consumer apps, content-focused applications

**Material Design Style:**
- **When to use**: Android-first apps, Google ecosystem integration, cross-platform with Material UI
- **Characteristics**: Bold graphics, elevation system, ripple effects, Roboto font
- **Key audience**: Android users, Google services, developer tools

**Ant Design Mobile Style:**
- **When to use**: Enterprise mobile applications with complex data entry and forms
- **Characteristics**: Efficiency-oriented, consistent components, suitable for business applications
- **Key audience**: Business users, enterprise mobile apps, data-heavy interfaces

**If the user hasn't specified a design system**, recommend one based on:
- Geographic location: Chinese users → WeChat Work, Western users → iOS/Material
- Platform: iOS → iOS Native, Android → Material Design
- Application type: Enterprise B2B → WeChat Work or Ant Design, Consumer app → iOS or Material

Load the complete design system specifications from `references/design-systems.md` to ensure accurate color codes, component dimensions, and interaction patterns.

### Step 3: Structure the Prompt

Using the template from `references/prompt-structure.md`, construct a comprehensive prompt with these sections:

**1. Role Definition**
Define expertise relevant to the prototype:
```
# Role
You are a world-class UI/UX engineer and frontend developer, specializing in [specific domain] using [technologies].
```

**2. Task Description**
State clearly what to build and the design style:
```
# Task
Create a [type] prototype for [application description].
Design style must strictly follow [design system], with core keywords: [3-5 key attributes].
```

**3. Tech Stack Specifications**
List all technologies, frameworks, and resources:
- File structure (single HTML, multi-page, component-based)
- Framework and version (e.g., Tailwind CSS CDN)
- Device simulation (viewport size, device chrome)
- Asset sources (Unsplash, Pexels, real images)
- Icon libraries (FontAwesome, Material Icons)
- Custom configuration (Tailwind config, theme variables)

**4. Visual Design Requirements**
Provide detailed specifications:

**(a) Color Palette:**
Include all colors with hex codes:
- Background colors (main, section, card)
- Primary and accent colors with usage
- Status colors (success, warning, error)
- Text colors (title, body, secondary, disabled)
- UI element colors (borders, dividers)

**(b) UI Style Characteristics:**
Specify for each component type:
- Cards: background, radius, shadow, border, padding
- Buttons: variants (primary, secondary, ghost), dimensions, states
- Icons: style, sizes, colors, containers
- List items: layout, height, divider style, active state
- Shadows: type and usage

**(c) Layout Structure:**
Describe each major section:
- Top navigation bar: height, title style
03

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeNA
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.

Audited 2026-10-21 · audit v0.4.1 · source sha efe1633380f1full audit observations/trust-audit/skill/cexll__prototype-prompt-generator.json · Report an issue / request a re-scan
04

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-21efe1633380f1SAFEB89first audit
05

Questions

What does the prototype-prompt-generator — cexll/myclaude skill do?

Multi-agent orchestration workflow (Claude Code Codex Gemini OpenCode)

Is prototype-prompt-generator — cexll/myclaude safe to install?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.

What can prototype-prompt-generator — cexll/myclaude access on my machine?

The audit observed no filesystem, network or shell use at all in its source.

How current is this page?

The grade is for one exact copy of the source (efe1633380f1), read on 2026-10-21. The repository is watched, and a new audit runs when it changes — this is the first audit.

Add this badge to your README

Shows this page's audit result and links back to it. It updates when the audit does.

ModelsAtlas audit badge

Markdown
[![ModelsAtlas audit: Prototype Prompt Generator](https://modelsatlas.com/skills/cexll/prototype-prompt-generator/badge.svg)](https://modelsatlas.com/skills/cexll/prototype-prompt-generator/)

Not your listing, or something out of date? Claim or update your listing.

Advertisement