# Figma (ChatGPT Plugin) > Figma design-to-code workflows - Type: plugin - Publisher: Figma (official) - Categories: Design, Development - Website: https://github.com/openai/plugins/tree/main/plugins/figma - Docs: https://learn.chatgpt.com/docs/plugins - Source: https://github.com/openai/plugins - Open in ChatGPT: https://chatgpt.com/plugins/plugin_connector_68df038e0ba48191908c8434991bbac2 - GitHub stars: 7248 - Listed: 2026-03-12 ## Overview The Figma plugin does two jobs depending on where you use it. In Codex, it is Figma's recommended way to connect a coding agent: paste a link to a frame (right-click, **Copy link to selection**) and have the agent build it with your existing components, or have it create and update screens and design-system pieces in a Figma file. In a ChatGPT chat, it turns a prompt, document or rough sketch into a FigJam diagram or Figma Slides deck that you finish in Figma. The Codex side suits front-end developers and design-system teams; the ChatGPT side, anyone who needs a quick flowchart or first-draft deck. ## From the publisher Figma workflows for design implementation, Code Connect templates, and design system rule generation. Bundles Figma's skills (figma-use, design-to-code, Code Connect, generate-design/library, FigJam, Slides, motion) with the Figma app connection. Listed in OpenAI's curated Codex marketplace (openai-curated); the manifest declares skills and an app connector. ## What you need - **A Figma account**, approved when you install. The agent only works with files that account can open. - **Codex:** in the ChatGPT desktop app, open **Plugins** and select **+** next to Figma; in the CLI, run `codex plugin add figma@openai-curated`. Figma's docs also show `codex mcp add figma --url https://mcp.figma.com/mcp`, which adds the server without Figma's skills. - **A suitable Figma plan and seat.** Usage limits depend on your seat. Writing to the canvas needs a Professional, Education, Organization or Enterprise plan and edit access to the file. Code Connect context needs a Full or Dev seat on Professional, Organization, Government or Enterprise. - **ChatGPT:** install from the Plugins tab on the web or desktop app. Figma says diagrams and decks work on any Figma plan but aren't available in the EU. ## Good to know - **Writing to the canvas is in beta.** Figma says it's free during the beta and will become a usage-based paid feature, and suggests testing on a duplicate file with a backup. - **Unclaimed files are public.** A file created from ChatGPT can be viewed by anyone with the link until you sign in and add it to your drafts. - **Slides generation is in beta**, with usage limits that are largest for Full seats on paid plans. - **Disconnecting.** In ChatGPT, open **Settings** > **Plugins** (or **Apps**), select Figma and choose **Disconnect**. Uninstalling the plugin alone leaves a connected integration in place until you disconnect it. ## Install 1. **Add it in ChatGPT** Open Plugins in the ChatGPT sidebar (web or desktop), search for “Figma” and select +. You'll be asked to sign in to any connected service on first use. Then type @ in a chat to call it. 2. **Or install it in Codex** Codex CLI: ```bash codex plugin add figma@openai-curated ``` ## Disconnect or uninstall 1. **In ChatGPT** Disconnect an account in Settings → Apps or Plugins. To remove the plugin itself, open Figma in the Plugin Directory and select Uninstall plugin. Uninstalling can disconnect every account connected through it, and plugins your workspace installs may not offer the option. 2. **In Codex** Codex CLI: ```bash codex plugin remove figma@openai-curated ``` ## Skills - **figma-code-connect**: Creates and maintains Figma Code Connect template files that map Figma components to code snippets. Use when the user mentions Code Connect, Figma component mapping, design-to-code translation, or asks to create/update .figma.ts or .figma.js files. - **figma-code-workflows**: Import or upload local HTML or project files into Figma, choose editable Design frames, runnable Code Layers or standalone Code (also known as Make), and repair imported previews. Use only when the user explicitly names editable Design layers, a runnable Code Layer, or a standalone Code/Make file, or supplies a Figma file key/link as the import destination. Generic code or code-component requests need output clarification before using this workflow. - **figma-create-new-file**: Always use this skill when the user wants to create a new Figma Design, FigJam, or Slides file. You MUST invoke this skill BEFORE every `create_new_file` tool call. - **figma-design-to-code**: **MANDATORY prerequisite** — you MUST invoke this skill BEFORE calling the `get_design_context` Figma MCP tool. You MUST trigger this skill whenever the user wants to implement, build, port, or code up a Figma design as code. Example prompts (not exhaustive) are 'implement this Figma design', 'build this screen from Figma', 'turn this Figma into code', 'design to code'. This skill provides critical instructions and steps to the agent on how to correctly implement Figma designs in code and must NOT be skipped. - **figma-generate-design**: Use this skill alongside figma-use when the task involves translating an application page, view, or multi-section layout into Figma. Triggers: 'write to Figma', 'create in Figma from code', 'push page to Figma', 'take this app/page and build it in Figma', 'create a screen', 'build a landing page in Figma', 'update the Figma screen to match code', 'convert this modal/dialog/drawer/panel to Figma'. This is the preferred workflow skill whenever the user wants to build or update a full page, modal, dialog, drawer, sidebar, panel, or any composed multi-section view in Figma from code or a description. Discovers design system components, variables, and styles from Code Connect files, existing screens, and library search, then imports them and assembles views incrementally section-by-section using design system tokens instead of hardcoded values. - **figma-generate-diagram**: MANDATORY prerequisite — load this skill BEFORE every `generate_diagram` tool call. NEVER call `generate_diagram` directly without loading this skill first. Trigger whenever the user asks to create, generate, draw, render, sketch, or build a diagram — flowchart, architecture diagram, sequence diagram, ERD or entity-relationship diagram, state diagram or state machine, gantt chart, or timeline. Also trigger when the user mentions Mermaid syntax or wants a system architecture, decision tree, dependency graph, API call flow, auth handshake, schema, or pipeline visualized in FigJam. Routes to type-specific guidance, sets universal Mermaid constraints, and tells you when to use a different diagram type or skip the tool entirely (mindmaps, pie charts, class diagrams, etc.). - **figma-generate-library**: Build or update a professional-grade design system in Figma from a codebase. Use when the user wants to create variables/tokens, build component libraries, create individual components with proper variant sets and variable bindings, set up theming (light/dark modes), document foundations, or reconcile gaps between code and Figma. Also use when the user asks to create or generate any component in Figma — even a single one — since components require proper variable foundations, variant states, and design token bindings to be production-quality. This skill teaches WHAT to build and in WHAT ORDER — it complements the `figma-use` skill which teaches HOW to call the Plugin API. Both skills should be loaded together. - **figma-generative-plugins**: **MANDATORY prerequisite** — load this skill before calling `create_generative_plugin` or `update_generative_plugin`. Use when the user asks to create, author, change, fix, or extend a reusable generative Figma plugin. - **figma-implement-motion**: Translates Figma motion and animations into production-ready application code. Use when implementing animation/motion from a Figma design — user mentions "implement this motion", "add animation from Figma", "animate this component", provides a Figma URL whose node is animated, or when `get_design_context` returns motion data or instructs you to call `get_motion_context`. - **figma-shaders**: **MANDATORY prerequisite** — load this skill before calling `create_shader` or `update_shader`. Use when the user asks to create, author, change, fix, or iterate on a shader effect, shader fill, custom effect, custom fill, or procedural shader in Figma. - **figma-spec**: This skill is required to create, read, edit, review, or comment on Figma specs. You must read it when working on a PRD, brief, RFC or any kind of document in either a standalone Figma spec or a Figma spec embedded in a Figma Design or Figjam file. - **figma-swiftui**: SwiftUI ↔ Figma translation. Use whenever the user mentions Swift, SwiftUI, iOS, iPhone, or iPad — in EITHER direction — translating a Figma design into SwiftUI (design → code), or pushing SwiftUI views / screens / tokens back into a Figma file (code → design). Triggers on phrases like 'implement this Figma design in SwiftUI', 'build this screen in Swift', 'push this SwiftUI view to Figma', 'mirror my Swift code in a Figma file', or whenever a Figma URL appears alongside `.swift` files / an `.xcodeproj`. Routes to a direction-specific reference doc; loads alongside `figma-use` for the code → design path. - **figma-use**: **MANDATORY prerequisite** — you MUST invoke this skill BEFORE every `use_figma` tool call. NEVER call `use_figma` directly without loading this skill first. Skipping it causes common, hard-to-debug failures. Trigger whenever the user wants to perform a write action or a unique read action that requires JavaScript execution in the Figma file context — e.g. create/edit/delete nodes, set up variables or tokens, build components and variants, modify auto-layout or fills, bind variables to properties, or inspect file structure programmatically. - **figma-use-figjam**: This skill helps agents use Figma's use_figma MCP tool in the FigJam context. Can be used alongside figma-use which has foundational context for using the use_figma tool. - **figma-use-motion**: Motion / animation context for the `use_figma` MCP tool — animating Figma nodes via manual keyframes, animation styles, easing, and timeline duration. Load alongside figma-use whenever a task involves adding, editing, or inspecting animation on a node. ## Example prompts - "Inspect a Figma design and implement it in code" - "Create Code Connect templates for my components" - "Build or update a screen in Figma" ## Also available as - app: [Figma](https://chatgptplugins.directory/apps/figma.md) - MCP server: [Figma](https://chatgptplugins.directory/mcp/figma.md) ## Figma alternatives - [Superpowers](https://chatgptplugins.directory/plugins/superpowers.md): Plan, develop, and debug code - [Codex Security](https://chatgptplugins.directory/plugins/codex-security.md): Security scanning for your codebase - [Build Web Apps](https://chatgptplugins.directory/plugins/build-web-apps.md): Build frontend-focused web apps with generated assets, browser testing, payments, and... - [GitHub](https://chatgptplugins.directory/plugins/github.md): Triage PRs, issues, CI, and publish flows - [Adobe](https://chatgptplugins.directory/plugins/adobe.md): Design, combine, and edit - [Creative Production](https://chatgptplugins.directory/plugins/creative-production.md): Create marketing visuals from a brief or product image. ## FAQ ### Can ChatGPT turn a Figma design into code? Yes, in Codex. Install the plugin, paste a link to a frame, and ask Codex to implement it in your stack. The agent reads the design context, screenshots and variables from Figma, and with Code Connect set up it reuses your real components. Review the result like any other change. See [Use plugins and MCP servers in Codex](/tutorials/use-plugins-in-codex). ### Can ChatGPT create Figma files? Yes. In a chat it can create FigJam diagrams and Figma Slides presentations, which open in Figma for editing; other Figma file types aren't supported there. In Codex, the agent can also build frames, components and variables inside Figma files you can edit, a beta feature with the plan requirements above. ### How many Figma requests can I make? Figma meters its MCP server by seat and plan. Starter plans and View or Collab seats get up to 20 tool calls a month. Full or Dev seats get up to 200 a day on Professional, Education and Organization plans and 600 on Enterprise, plus per-minute limits. Some tools that write to files, such as creating a new file, don't count. ### What's the difference between the Figma plugin, app and MCP server? The [Figma app](/apps/figma) is Figma's connection inside ChatGPT, used for diagrams and decks. The plugin bundles that connection with Figma's skills for design-to-code work and installs in ChatGPT and Codex. The [Figma MCP server](/mcp/figma) is Figma's server behind the Codex setup, which you can add to Codex or another client yourself, without the skills. _Guide updated 2026-10-24. Sources: https://learn.chatgpt.com/docs/plugins, https://github.com/openai/plugins/tree/main/plugins/figma, https://developers.figma.com/docs/figma-mcp-server/remote-server-installation/, https://developers.figma.com/docs/figma-mcp-server/rate-limits-access/, https://developers.figma.com/docs/figma-mcp-server/write-to-canvas/, https://developers.figma.com/docs/figma-mcp-server/code-connect-integration/, https://help.figma.com/hc/en-us/articles/35326636109975-Use-ChatGPT-with-Figma._ --- Source: https://chatgptplugins.directory/plugins/figma · Index: https://chatgptplugins.directory/llms.txt · Independent and community-run. Not affiliated with or endorsed by OpenAI. ChatGPT is a trademark of OpenAI.