Skip to content
Get packs

Ideate Design Concepts

Generates three distinct image-based design directions from a product design brief before any build work.

Source Download skill
Repository
XiaomiMiMo/MiMo-Code
Stars
13,743
Licence
MIT
Files
2 files

What it does

When installed, the agent pauses to confirm the design brief and gathers existing context such as screenshots, Figma frames, tokens, and component references. It then generates three separate, visually distinct design concept images using a built-in image generation tool, and waits for you to pick one before building anything.

Great for

  • Product designers exploring layout or visual directions for a screen or feature
  • Developers who want mockup options before writing front-end code
  • Teams that want variants grounded in their existing design system or screenshots

Skip it if

  • Teams needing pixel-exact final designs, since the output is generated images, not editable design files
  • Projects that require the agent to skip the selection step, because the workflow is built to stop for user approval
  • Sensitive or confidential designs uploaded to an image generation service, since the attached references may be sent to that tool

Try asking

  • “Give me three alternative layouts for a mobile checkout screen, using the screenshots in my /designs folder”
  • “Explore three product directions for a team onboarding dashboard”
  • “Remix this landing page screenshot into new visual approaches”
Step-by-step guide: how to use Ideate Design ConceptsInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 2 original files, the MIT licence and an attribution note.

    ideate.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip ideate.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip ideate.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Provide screenshots, Figma links, or token files up front so the concepts match your existing design language
  • State the target surface (mobile, desktop, landing page) so the agent picks the right dimensions
  • Name the concept you prefer by its descriptive name or number after the images appear to avoid selection mix-ups

What's inside

  • agents/openai.yaml
  • SKILL.md

Redistributed unmodified from XiaomiMiMo/MiMo-Code under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.