explainx.ainewsletter3.4k
Frontend

gemini-designer▌

oil-oil/gemini-designer · updated Apr 8, 2026

MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.

$npx skills add https://github.com/oil-oil/gemini-designer --skill gemini-designer
0 commentsdiscussion
summary

Delegate design tasks to Gemini via ZenMux API. Gemini creates HTML page designs, SVG icons, and provides design advice.

skill.md

Gemini Designer — Your Design Partner

Delegate design tasks to Gemini via ZenMux API. Gemini creates HTML page designs, SVG icons, and provides design advice.

Critical rules

  • ONLY interact with Gemini through the bundled shell script. NEVER call the API directly.
  • Run the script ONCE per task. Read the output file and proceed.
  • The script requires a ZenMux API key. It checks (in order): ZENMUX_API_KEY env var, .env.local in current/parent dirs, ~/.config/gemini-designer/api_key file.

How to call the script

The script path is:

~/.claude/skills/gemini-designer/scripts/ask_gemini.sh

HTML page design

~/.claude/skills/gemini-designer/scripts/ask_gemini.sh "Design a modern landing page for a SaaS product called FlowSync" --html

SVG icon

~/.claude/skills/gemini-designer/scripts/ask_gemini.sh "Create a minimal settings gear icon, 24x24, stroke style" --svg

Design advice (text)

~/.claude/skills/gemini-designer/scripts/ask_gemini.sh "Suggest a color palette and typography for a developer blog"

Custom output path (auto-infers type from extension)

~/.claude/skills/gemini-designer/scripts/ask_gemini.sh "Design a pricing card component" \
  -o ./designs/pricing-card.html

The script prints on success:

output_path=<path to output file>

Read the file at output_path to get Gemini's response.

Output types

  • html — Self-contained HTML file with inline CSS. Ready to open in browser. Use --html shorthand or --output-type html.
  • svg — Clean SVG code. Can be saved directly or embedded in HTML/React. Use --svg shorthand or --output-type svg.
  • text (default) — Design advice in markdown: color palettes, typography, layout suggestions.

If you pass -o with a .html or .svg extension and don't specify an output type, the type is auto-inferred from the file extension.

Configuration

  • ZENMUX_API_KEY - API key (required)
  • ZENMUX_BASE_URL - API base URL (default: https://zenmux.ai/api/v1)
  • ZENMUX_MODEL - Model name (default: google/gemini-3.1-pro-preview)

When to use

  • Need a visual reference or HTML mockup for a UI component or page
  • Need SVG icons or simple illustrations
  • Need color palette, typography, or layout suggestions
  • Need design feedback or critique on an existing design
  • Want a quick single-page HTML prototype to show a concept

Workflow

  1. Only describe what the page/component is for and the core content — do NOT add your own design opinions (colors, fonts, layout style, etc.) unless the user explicitly specified them.
  2. Run the script with the appropriate output type flag (--html, --svg, or default text).
  3. Read the output file.
  4. For HTML/SVG: save to the project and iterate if needed.
  5. For text advice: apply the suggestions to your implementation.

Tips

  • Keep the task prompt short and focused on what it is, not how it should look.
  • If the user didn't specify a style/color/font, don't invent one — let Gemini decide.
  • Only pass explicit user preferences (e.g. "dark mode", "use blue") when the user actually said so.
  • Chinese prompts work well — Gemini responds in the same language.
how to use gemini-designer

How to use gemini-designer on Cursor

AI-first code editor with Composer

1

Prerequisites

Before installing skills in Cursor, ensure your development environment meets these requirements:

  • ›Cursor installed and configured on your development machine
  • ›Node.js version 16.0+ with npm package manager (verify with node --version)
  • ›Active project directory or workspace where you want to add gemini-designer
2

Execute installation command

Execute the skills CLI command in your project's root directory to begin installation:

$npx skills add https://github.com/oil-oil/gemini-designer --skill gemini-designer

The skills CLI fetches gemini-designer from GitHub repository oil-oil/gemini-designer and configures it for Cursor.

3

Select Cursor when prompted

The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:

◆ Which agents do you want to install to?
│
│ ── Universal (.agents/skills) ── always included ────
│ • Amp
│ • Antigravity
│ • Cline
│ • Codex
│ ●Cursor(selected)
│ • Cursor
│ • Windsurf
4

Verify installation

Confirm successful installation by checking the skill directory location:

.cursor/skills/gemini-designer

Reload or restart Cursor to activate gemini-designer. Access the skill through slash commands (e.g., /gemini-designer) or your agent's skill management interface.

⚠

Security & Verification Notice

We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.

Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.

Additional Resources

›View source code on GitHub›Skills CLI documentation›Learn more about Cursor›What are agent skills?

List & Monetize Your Skill

Submit your Claude Code skill and start earning

GET_STARTED →

Use Cases▌

Task Automation & Efficiency

Automate repetitive workflows and reduce manual effort

Example

Generate reports, summarize documents, draft communications

✓

Save 3-5 hours per week on routine tasks

Knowledge Enhancement

Learn new skills, understand complex topics, get expert guidance

Example

Explain concepts, provide examples, suggest learning resources

✓

Accelerate learning and skill development by 2x

Quality Improvement

Enhance output quality through reviews, suggestions, and refinements

Example

Review drafts, suggest improvements, catch errors

✓

Improve work quality by 30-40% with less effort

Implementation Guide▌

Prerequisites

  • ›Claude Desktop or compatible AI client with skill support
  • ›Clear understanding of task or problem to solve
  • ›Willingness to iterate and refine outputs

Time Estimate

15-45 minutes depending on use case complexity

Installation Steps

  1. 1.Install skill using provided installation command
  2. 2.Test with simple use case relevant to your work
  3. 3.Evaluate output quality and relevance
  4. 4.Iterate on prompts to improve results
  5. 5.Integrate into regular workflow if valuable

Common Pitfalls

  • ⚠Expecting perfect results without iteration
  • ⚠Not providing enough context in prompts
  • ⚠Using skill for tasks outside its intended scope
  • ⚠Accepting outputs without review and validation

Best Practices▌

✓ Do

  • +Start with clear, specific prompts
  • +Provide relevant context and constraints
  • +Review and refine all outputs before using
  • +Iterate to improve output quality
  • +Document successful prompt patterns

✗ Don't

  • −Don't use without understanding skill limitations
  • −Don't skip validation of outputs
  • −Don't share sensitive information in prompts
  • −Don't expect skill to replace human judgment

💡 Pro Tips

  • ★Be specific about desired format and style
  • ★Ask for multiple options to choose from
  • ★Request explanations to understand reasoning
  • ★Combine AI efficiency with human expertise

When to Use This▌

✓ Use When

Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.

✗ Avoid When

Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.

Learning Path▌

  1. 1Familiarize yourself with skill capabilities and limitations
  2. 2Start with low-risk, non-critical tasks
  3. 3Progress to more complex and valuable use cases
  4. 4Build expertise through regular use and experimentation

Discussion

Product Hunt–style comments (not star reviews)
  • No comments yet — start the thread.
general reviews

Ratings

4.5★★★★★39 reviews
  • ★★★★★Kofi Mensah· Dec 28, 2024

    We added gemini-designer from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.

  • ★★★★★Chaitanya Patil· Dec 24, 2024

    gemini-designer has been reliable in day-to-day use. Documentation quality is above average for community skills.

  • ★★★★★Aisha Gupta· Dec 8, 2024

    Useful defaults in gemini-designer — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.

  • ★★★★★Michael Iyer· Dec 4, 2024

    Solid pick for teams standardizing on skills: gemini-designer is focused, and the summary matches what you get after install.

  • ★★★★★Mei Brown· Nov 23, 2024

    I recommend gemini-designer for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • ★★★★★Kofi Kim· Nov 19, 2024

    gemini-designer fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.

  • ★★★★★Piyush G· Nov 15, 2024

    gemini-designer reduced setup friction for our internal harness; good balance of opinion and flexibility.

  • ★★★★★Harper Gill· Oct 14, 2024

    Keeps context tight: gemini-designer is the kind of skill you can hand to a new teammate without a long onboarding doc.

  • ★★★★★Kofi Li· Oct 10, 2024

    gemini-designer has been reliable in day-to-day use. Documentation quality is above average for community skills.

  • ★★★★★Harper Ghosh· Oct 10, 2024

    Useful defaults in gemini-designer — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.

showing 1-10 of 39

1 / 4