Communitygithub.com

openai/figma

Utilisez le serveur MCP Figma pour récupérer le contexte de conception, des captures d'écran, des variables et des actifs depuis Figma, et pour traduire les nœuds Figma en code de production. Déclenché lorsqu'une tâche implique des URLs Figma, des ID de nœud, une implémentation design-vers-code, ou la configuration et le dépannage du MCP Figma.

Qu'est-ce que figma ?

Cette compétence permet à un agent IA d'interagir avec le serveur MCP (Model Context Protocol) de Figma. Elle est conçue pour extraire des informations de conception détaillées (contexte, captures d'écran, variables, actifs) directement depuis des fichiers Figma, et pour convertir automatiquement des nœuds de conception en code de production (par exemple, React, HTML/CSS). La compétence est déclenchée automatiquement lorsqu'un utilisateur fournit des URLs Figma, des ID de nœuds ou demande une implémentation design-vers-code. Elle gère également la configuration initiale du serveur MCP Figma, comme la définition de la variable d'environnement `FIGMA_ACCESS_TOKEN`, et fournit des conseils de dépannage pour les problèmes courants (jetons invalides, limitations de requêtes, etc.). Elle est compatible avec les plateformes d'agents qui supportent le protocole MCP, comme Claude Code, Cursor et Codex.

Compatible avec~Claude Code✓Codex CLI~Cursor
Part ofDesign & UI
npx skills add https://github.com/openai/skills/tree/main/skills/figma
Voir l'original→Voir toutes les compétences

Demander à votre IA préférée

Ouvre une nouvelle conversation avec cette compétence d'agent déjà préchargée.

OpenAIChatGPTClaudeClaudeGeminiGeminiGrokGrokPerplexityPerplexityDeepSeekDeepSeek

Documentation

Que fait figma ?

Utilisez le serveur MCP Figma pour récupérer le contexte de conception, des captures d'écran, des variables et des actifs depuis Figma, et pour traduire les nœuds Figma en code de production. Déclenché lorsqu'une tâche implique des URLs Figma, des ID de nœud, une implémentation design-vers-code, ou la configuration et le dépannage du MCP Figma.

Description

Cette compétence permet à un agent IA de se connecter à l'API Figma via le serveur MCP Figma. Elle offre les fonctionnalités suivantes :

  • Récupération de contexte de conception : Obtenez des informations détaillées sur les calques, les composants, les styles et les propriétés de n'importe quel nœud Figma.
  • Captures d'écran : Générez et récupérez des captures d'écran de nœuds ou de pages Figma spécifiques.
  • Variables et actifs : Extrayez les variables de conception (couleurs, polices, espacements) et téléchargez des actifs (icônes, images).
  • Génération de code : Convertissez automatiquement les nœuds Figma en code de production (par exemple, React, HTML/CSS, SwiftUI).

Quand est-ce déclenché ?

  • L'utilisateur fournit une URL Figma (https://www.figma.com/file/... ou https://www.figma.com/design/...).
  • L'utilisateur mentionne un ID de nœud Figma (par exemple, 1234:5678).
  • La tâche nécessite une implémentation design-vers-code (par exemple, « transforme cette maquette en composant React »).
  • L'utilisateur demande de configurer ou de dépanner le serveur MCP Figma.

Configuration

Avant d'utiliser cette compétence, assurez-vous que le serveur MCP Figma est configuré avec un jeton d'accès Figma valide.

  1. Obtenir un jeton d'accès Figma :

    • Allez dans vos paramètres Figma : https://www.figma.com/settings/tokens
    • Générez un nouveau jeton d'accès personnel.

  2. Définir la variable d'environnement :

    export FIGMA_ACCESS_TOKEN="votre_jeton_figma_ici"

  3. Vérifier la configuration : L'agent confirmera que le serveur MCP Figma est opérationnel avant d'effectuer des appels d'API.

Dépannage

ProblèmeSolution
Jeton invalideVérifiez que FIGMA_ACCESS_TOKEN est correctement défini et non expiré.
Nœud introuvableConfirmez que l'ID de nœud est valide et que l'URL Figma est accessible.
Limitation de requêtesAttendez quelques secondes avant de réessayer.
Erreur de génération de codeVérifiez que le nœud contient des données de conception valides (pas une image).

Exemple d'utilisation

Prompt utilisateur :

Utilise le fichier Figma à l'URL https://www.figma.com/file/abc123/maquette-site pour générer un composant React pour le bouton d'en-tête.

Action de l'agent :

  1. Récupère le contexte de conception depuis l'URL Figma.
  2. Identifie le nœud « en-tête ».
  3. Extrait les propriétés (couleur, taille, police).
  4. Génère le code React et des styles CSS.
  5. Retourne le code à l'utilisateur.

Commandes

  • figma:get-context <url> : Récupère le contexte de conception d'un fichier Figma.
  • figma:get-screenshot <url> <node-id> : Prend une capture d'écran d'un nœud spécifique.
  • figma:get-variables <url> : Liste les variables de conception dans un fichier.
  • figma:generate-code <url> <node-id> : Génère du code de production à partir d'un nœud.

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

openai/aspnet-core

Build, review, refactor, or architect ASP.NET Core web applications using current official guidance for .NET web development. Use when working on Blazor Web Apps, Razor Pages, MVC, Minimal APIs, controller-based Web APIs, SignalR, gRPC, middleware, dependency injection, configuration, authentication, authorization, testing, performance, deployment, or ASP.NET Core upgrades.

openai/chatgpt-apps

Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply Apps SDK metadata or CSP or domain settings, or produce a docs-aligned project scaffold. Prefer a docs-first workflow by invoking the openai-docs skill or OpenAI developer docs MCP tools before generating code.

openai/cli-creator

Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a companion skill.

openai/cloudflare-deploy

Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.

openai/develop-web-game

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with render_game_to_text.

openai/doc

Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks.

openai/figma-code-connect-components

Connects Figma design components to code components using Code Connect mapping tools. Use when user says "code connect", "connect this component to code", "map this component", "link component to code", "create code connect mapping", or wants to establish mappings between Figma designs and code implementations. For canvas writes via `use_figma`, use `figma-use`.

openai/figma-create-design-system-rules

Generates custom design system rules for the user's codebase. Use when user says "create design system rules", "generate rules for my project", "set up design rules", "customize design system guidelines", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server connection.

openai/figma-create-new-file

Create a new blank Figma file. Use when the user wants to create a new Figma design or FigJam file, or when you need a new file before calling use_figma. Handles plan resolution via whoami if needed. Usage — /figma-create-new-file [editorType] [fileName] (e.g. /figma-create-new-file figjam My Whiteboard)

openai/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'. This is the preferred workflow skill whenever the user wants to build or update a full page, screen, or view in Figma from code or a description. Discovers design system components, variables, and styles via search_design_system, imports them, and assembles screens incrementally section-by-section using design system tokens instead of hardcoded values.

openai/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, set up theming (light/dark modes), document foundations, or reconcile gaps between code and Figma. 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.

openai/figma-implement-design

Translates Figma designs into production-ready application code with 1:1 visual fidelity. Use when implementing UI code from Figma files, when user mentions "implement design", "generate code", "implement component", provides Figma URLs, or asks to build components matching Figma specs. For Figma canvas writes via `use_figma`, use `figma-use`.

openai/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.

openai/frontend-skill

Use when the task asks for a visually strong landing page, website, app, prototype, demo, or game UI. This skill enforces restrained composition, image-led hierarchy, cohesive content structure, and tasteful motion while avoiding generic cards, weak branding, and UI clutter.

openai/gh-address-comments

Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.

openai/gh-fix-ci

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.

openai/hatch-pet

Create, repair, validate, visually QA, and package Codex-compatible animated pets and pet spritesheets from character art, generated images, company or prospect brand cues, or visual references. Use when a user wants a lightweight-worker Codex pet workflow, a non-pixel custom pet style, a prospect or company mascot pet, or a full 8x9 animated pet atlas with transparent unused cells, QA contact sheets, and pet.json packaging. This skill composes the installed $imagegen system skill for visual generation and uses bundled scripts for deterministic spritesheet assembly.

openai/imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG/vector/code-native assets, extending an established icon or logo system, or building the visual directly in HTML/CSS/canvas.

openai/jupyter-notebook

Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.

openai/linear

Manage issues, projects & team workflows in Linear. Use when the user wants to read, create or updates tickets in Linear.

Skills associés

steipete/sag

ElevenLabs text-to-speech with mac-style say UX.

community

steipete/oracle

Oracle CLI second-model review/debug/refactor/design with selected files, dry-run token checks, API or browser engine.

community

steipete/peekaboo

Capture and automate macOS UI with the Peekaboo CLI.

community

mattpocock/design-an-interface

Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".

community

mattpocock/prototype

Build a throwaway prototype to flesh out a design — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route.

community

mattpocock/grill-me

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

community