Skip to content
Get packs

Get Context Design Brief

Clarifies the product and goal before UI design work, then plays the brief back before building

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

What it does

Before the agent starts designing or building product interface work, this skill makes it ask targeted questions about what product, screen, or feature is involved and what the user should be able to do. Once the target and goal are clear, it summarizes the brief and its default choices in a short note and moves on without waiting for approval. It also checks saved references such as design files, screenshots, or brand assets when they are relevant to the task.

Great for

  • Designers starting a redesign or new screen who want the agent to confirm the goal first
  • Developers asking for a UI prototype or an image-to-code build who want fewer wrong assumptions
  • Teams using AI agents for product UI work that needs a clear, shared brief

Skip it if

  • Quick, tiny static edits or simple research, since the gate adds clarifying questions the task does not need
  • Work that must not pause for questions, because the skill blocks implementation until the target and user outcome are known

Try asking

  • “Design a onboarding screen for my fitness app”
  • “Redesign our pricing page based on this screenshot”
  • “Turn this image into a React component”
  • “Prototype a checkout flow for a coffee shop website”
Step-by-step guide: how to use Get Context Design BriefInstall, 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.

    get-context.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

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

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip get-context.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

  • State the product, the screen, and the user goal in your first message to skip most questions
  • Share saved references such as Figma links, screenshots, or repo paths so the agent can ground the brief in them
  • Correct the playback briefly if style, scope, or interactivity is off; the agent will adjust

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.