Figma’s guide to spending fewer AI credits with the agent: scope prompts clearly, attach only the context the task needs, and start a new chat when you switch tasks, since long chats raise the cost of every prompt. For repeated jobs, turn the work into a generative plugin — building it costs credits, but every run after that costs zero.

Harvey treats its Figma like a codebase: Agentic Brand Guidelines act as the top-level AGENTS​.md, and each project folder adds only what it needs. On top of that, agents script, voice with ElevenLabs, and build hundreds of personalized films inside Figma Motion — one batch of 36 took 69 minutes.

Guidelines let a design systems team upload Markdown rules to a published library, and the Figma agent reads them every time someone prompts with that library. Include dos and don’ts, anti-patterns, and unwritten taste. When the agent keeps inventing navigation, add a rule.

At Config India, Figma also put code sources in closed beta and previewed one place to manage a whole system.

The Figma agent is out of beta, with lower latency, file search across the platform, and the ability to watch your teammates’ agents work live on the canvas. Generative plugins are now generally available too.

Mentha is Mintlify’s design system for an agent-heavy team. Fay Dakrouri’s takeaway: the more instructions, skills, and component constraints you feed an agent, the better its first direction, though someone still has to judge whether the result solves the problem tastefully.

Brett McMillin, Designer Advocate at Figma, runs a skill that pulls user personas from a Notion page and critiques selected frames as one persona, in his demo a fintech app for teens. The findings land as annotations on the canvas covering comprehension, findability, visual hierarchy and trust, and the skill is told never to touch the design. ​“Nothing will take the place of actual user testing and talking to our customers.”

Peng Zheng’s personal site updates itself, as he shows host Claire Vo on How I AI. Send his check-in bot a photo, a screenshot or just the name of a place, and it looks the place up through the Google Places API, fixes the perspective, removes people and generates light and dark 3D miniature versions for the site.

The skills demo is the one to watch. Rodrigo calls a slash command for a skill his teammate Tammy wrote in plain English, carrying her own design-review conventions, and the agent returns the critique as annotations right on the canvas. Team practice becomes a callable command.

Detach the agent chat into its own window on the desktop app, move it anywhere, keep it in view while you design. Figma expects you to be watching an agent work while you do something else, which turns the chat from a sidebar into a persistent companion window.

Jake Albaugh, Developer Advocate at Figma, points a fleet of agents at an entire component library, then reuses the same agents as validators: each file re-fetches from Figma and surfaces what drifted after a property rename. His real argument for Code Connect is context economy – without it the MCP server hands the agent every style value it might need, and compaction is lossy.

The post above shows the skills, this one shows the plumbing. Miggi builds 3 skills: a type scale generator that also writes the variables, an image audit that drops a DPI card beside every image, and Shader Starter, which pairs neatly with the shaders update below.

Miggi rounds up ten community skills for the Figma agent, though the real news is in the first line: you can now author skills inside Figma. Ask the agent to draft one using a design frame as reference, preview it, then keep iterating in chat or open the markdown editor for manual changes. Emil Kowalski’s /find-animation-opportunities, which scans a file for places that don’t animate but should, and Jakub Krehel’s /better-interface which catches the details your interface is missing, are the ones I’d install first.