design-proposals — design-proposals install design-proposals, chinese-flashcards, community, design-proposals install, ide skills, HTML mockup generation, UX direction exploration, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Perfect for UX-focused AI Agents needing streamlined design process integration with HTML mockup generation. Design-proposals is a skill that generates 2-3 standalone HTML mockups for visually comparing UX directions before implementation.

Features

Generates 2-3 standalone HTML mockups for UX direction exploration
Checks for project design system reference in .design-proposals/design-system.md
Supports two-phase workflow: exploration via HTML mockups and implementation with real components
Allows for visual comparison of UX directions before committing to one
Streamlines design process with HTML mockup generation

# Core Topics

Nicoowr Nicoowr
[0]
[0]
Updated: 3/8/2026

Agent Capability Analysis

The design-proposals skill by Nicoowr is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance. Optimized for design-proposals install, HTML mockup generation, UX direction exploration.

Ideal Agent Persona

Perfect for UX-focused AI Agents needing streamlined design process integration with HTML mockup generation.

Core Value

Empowers agents to generate standalone HTML mockups for UX direction exploration, utilizing a two-phase workflow that streamlines the design process with real components, and referencing project design systems via .design-proposals/design-system.md files.

Capabilities Granted for design-proposals

Generating HTML mockups for UX direction comparison
Implementing chosen design directions with real components
Exploring project design languages via design system references

! Prerequisites & Limits

  • Requires project design system reference file (.design-proposals/design-system.md)
  • Limited to two-phase workflow
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

design-proposals

Install design-proposals, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

Design Proposals

Generate 2–3 standalone HTML mockups so the user can visually compare UX directions before committing to one. This is a two-phase workflow: first explore via HTML mockups, then implement the chosen direction with real components.

Phase 1 — HTML Mockups (exploration)

Step 1: Understand the project's design language

Before creating any mockup, check if a project design system reference exists:

  1. Look for .design-proposals/design-system.md in the project root.
  2. If it exists, read it — it contains the project's colors, fonts, CSS utilities, layout patterns, and example markup ready to reuse in mockups. Skip discovery and go to Step 2.
  3. If it doesn't exist, discover the design language manually:
    • Find the global CSS file (e.g., globals.css, index.css, tailwind.config.*) — extract colors, fonts, border radii, and any custom utilities.
    • Scan 1–2 existing page/layout files to understand overall structure (navigation, spacing, dark/light mode).
    • Note the component library in use (shadcn, Radix, MUI, Chakra, plain HTML…).
    • Then offer to create the reference file for future sessions (see "Creating a design system reference" below).

Step 2: Create the mockups

  1. Create a .design-proposals/ directory at the project root (add it to .gitignore if not already present, along with .screenshots/).
  2. For each proposal, create a self-contained HTML file:
    • Name files descriptively: option-a-<short-label>.html, option-b-<short-label>.html, etc.
    • Use Tailwind CDN (<script src="https://cdn.tailwindcss.com"></script>) for utility classes.
    • Import the same font the project uses (e.g., Google Fonts link).
    • Replicate the project's color palette and visual style via inline <style> — match dark/light mode, glass effects, gradients, border styles, etc.
    • Each file must be fully self-contained (no external dependencies beyond CDN links).
    • Add a colored annotation banner fixed at the top of each page, briefly describing the design direction (use a distinct color per option so they're easy to tell apart).
    • Populate with realistic placeholder content relevant to the feature.

Step 3: Present the mockups

  1. Start a local HTTP server in .design-proposals/:
    python3 -m http.server 8899
    
    Run it in the background (block_until_ms: 0, full_network permission).
  2. Open each mockup in the Cursor built-in browser at http://localhost:8899/<filename>.html.
  3. Resize the browser to 1440×900 before taking screenshots.
  4. Take a screenshot of each option.
  5. After all screenshots, provide a structured comparison:
    • For each option: a short description, best for, and trade-off.
    • Ask the user which direction they prefer, or if they want to mix elements.

Iteration

When the user requests tweaks to a specific option, edit that HTML file in place and reload the browser. Do not recreate the file from scratch.

Phase 2 — Real implementation (after the user picks a direction)

Once a direction is chosen:

  1. Create a temporary design route or page in the project (e.g., src/app/(design)/... or equivalent for the framework in use).
  2. Implement the chosen design using the project's actual components, styles, and data types.
  3. Let the user validate on the dev server.
  4. When approved, move the implementation to its final location and clean up design artifacts.

Creating a design system reference

When a project doesn't have a design-system.md yet, offer to create one after the first design session. The file captures everything needed to replicate the project's visual style in standalone HTML mockups.

Store it at .design-proposals/design-system.md (already gitignored alongside the mockups).

The reference should include:

  • Theme: dark/light mode, background colors (HSL values)
  • Color palette: primary, secondary, muted, accent, destructive — with exact HSL values from the CSS
  • Typography: font family, Google Fonts import URL, key sizes
  • Border & radius: radius values, border colors
  • Custom utilities: any project-specific CSS like glass effects, gradients, shadows — copy the exact CSS
  • Layout patterns: typical page structure (e.g., "3-column: filters | main card | sidebar")
  • Component library: which library is used, key components (Button, Card, etc.)
  • HTML boilerplate: a ready-to-copy <head> block with all CDN links, font imports, and <style> block so new mockups can be started instantly

Keep the reference concise (under 150 lines). It's a cheat sheet, not full documentation.

Rules

  • Never use the image generation tool for design proposals — it produces hallucinated UI elements and doesn't match the project's design system.
  • Always propose 2–3 options, not just one. The value is in comparison.
  • Each option should represent a fundamentally different UX approach (e.g., side panel vs. full page vs. drawer), not just color or spacing variations.
  • Keep mockups focused on layout, information hierarchy, and interaction flow — pixel-perfect polish is not the goal at this stage.
  • Use an opaque (not glass/transparent) background on the drawer/panel containers if the page background is dark — semi-transparent glass is invisible against matching dark backgrounds in standalone mockups.

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is design-proposals?

Perfect for UX-focused AI Agents needing streamlined design process integration with HTML mockup generation. Design-proposals is a skill that generates 2-3 standalone HTML mockups for visually comparing UX directions before implementation.

How do I install design-proposals?

Run the command: npx killer-skills add Nicoowr/chinese-flashcards/design-proposals. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for design-proposals?

Key use cases include: Generating HTML mockups for UX direction comparison, Implementing chosen design directions with real components, Exploring project design languages via design system references.

Which IDEs are compatible with design-proposals?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for design-proposals?

Requires project design system reference file (.design-proposals/design-system.md). Limited to two-phase workflow.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add Nicoowr/chinese-flashcards/design-proposals. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use design-proposals immediately in the current project.

Related Skills

Looking for an alternative to design-proposals or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI