Skip to content
agentusehub
Sign in+ Submit
Content & CreativeAny

Let AI agents design in Figma

A CLI that lets coding agents create shapes, text, frames and components in Figma, so agents can build layouts and component systems.

Read the experience
Time saved
Not reported
Setup time
Not reported
Running cost
Not reported
Cost range
Not reported

Use case overview

A CLI that lets coding agents create shapes, text, frames and components in Figma, so agents can build layouts and component systems.

Read the original report ↗

Reported experience

  1. What they did

    The figma-use CLI connects to the Figma desktop app over Chrome DevTools Protocol and runs commands through Figma's Plugin API. Agents either issue commands one at a time or pipe JSX into a render command. They can build frames, text, icons, grid layouts, components and variants. A SKILL.md file and an MCP server with 90+ tools are included for agents.

  2. How it went

    The demos show button components and a Tailwind UI calendar. The README gives no benchmarks. Stdin JSX takes no logic, so components and variants need .figma.tsx files.

  3. Worth knowing

    Figma 126+ blocks remote debugging, so you need the daemon's pipe mode (figma-use daemon start --pipe), or use the OpenPencil alternative the README suggests.

Example prompts

Try with Claude Code
Using a Figma CLI tool such as figma-use, create a [type of design, e.g. pricing page layout] in my Figma file [file link] with frames, text, and reusable components for [button, card, etc.]. Follow this style: [colors, fonts, spacing]. Finish when the layout and components exist on a new page and describe what you made. Do not modify or delete my existing pages.

Related use cases

Content & Creative

Turn AI newsletters into a daily podcast

An agent runs overnight, collects the author's AI newsletter subscriptions and produces a daily podcast to listen to on walks.

Other or custom