Figma opens the canvas for agents.
What is this: Figma’s use_figma MCP tool lets AI agents create and edit designs directly in Figma, working with your original components, variables, and auto-layouts, not against them.
problem: Every AI-generated design has one thing in common: it doesn’t look like your product. Ingredients are invented. Spacing is arbitrary. Output is technically a UI, but it’s not anyone’s design system. So the designers throw it out and start over.
Solution: Skills are Markdown files that encode your team’s design conventions. Agents read them before touching the canvas. Combined with use_figma, agents now have both access and context they know how to work in Figma and they know how to work in your Figma.
What you can do with it:
🏗️ Build component libraries from the codebase
🔗 Synchronize design tokens between code and figma variables, with enhanced detection
♿ Automatically generate screen reader details from UI designs.
🔄 Run parallel workflows across multiple agents.
Who is it for: Product and design engineering teams that use Figma as a common source of truth and want their AI agent workflows to be connected to it. Heavy users of Claude Code, Codex, Cursor, and Copilot will notice this immediately.
Be a victim of the latest and greatest launches in tech, SaaS and AI at PS, follow to stay informed → @rohan suggests.