Skip to content
TrustedSkillsbeta
Back to all skills

Gemini Designer

Checked
oil-oil·vlatest·ai-ml

Gemini Designer generates creative visuals like images and art based on your prompts, boosting design workflows and sparking imaginative concepts.

Repository

Install on your platform

This skill no longer installs under the name gemini-designer. oil-oil/grok-designer has no skill named "gemini-designer" any more. It was renamed, moved or deleted upstream.

We check each listing against its upstream repository with the rules the skills CLI uses, last on 2026-09-28. We don't show a command we know will fail.

Repository install instructions

What we know about this skill

Publisher

oil-oil

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Only contacts known or declared hosts: github.com, 127.0.0.1.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

    Hosts contacted

    github.comsource host127.0.0.1local

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned oil-oil/gemini-designer at d1c59d0a3c.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
d1c59d0a3c
Manifest
SKILL.md
Scanned
31 files, 2,317 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

Gemini Designer is an AI skill that generates creative visuals and design advice using Google’s Gemini model, accessed through the ZenMux API. It can produce HTML page designs, SVG icons, and provide textual design suggestions like color palette and typography recommendations. The skill facilitates design workflows by allowing users to delegate specific design tasks to the AI agent.

When to use it

  • 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

Key capabilities

  • Generates HTML page designs with inline CSS.
  • Creates SVG icon code.
  • Provides textual design advice (color palettes, typography, layout suggestions).
  • Automatically infers output type from file extension when using the -o flag.
  • Supports custom output paths specified by the user.

Example prompts

  • ~/.claude/skills/gemini-designer/scripts/ask_gemini.sh "Design a modern landing page for a SaaS product called FlowSync" --html
  • ~/.claude/skills/gemini-designer/scripts/ask_gemini.sh "Create a minimal settings gear icon, 24x24, stroke style" --svg
  • ~/.claude/skills/gemini-designer/scripts/ask_gemini.sh "Suggest a color palette and typography for a developer blog"

Tips & gotchas

  • API Key Required: You must provide a ZenMux API key, which can be set as an environment variable (ZENMUX_API_KEY), in a .env.local file, or in ~/.config/gemini-designer/api_key.
  • Run Once Per Task: The script should only be run once for each design task. Read the output file to obtain Gemini's response.
  • Prompt Specificity: Keep prompts short and focused on what needs to be designed, rather than dictating specific stylistic choices.