Figma — Design skill for Claude Code
Fetch design context, screenshots, and assets from Figma for implementation.
How to install Figma
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open openai/skills and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Figma does
Fetch design context, screenshots, and assets from Figma for implementation.
One of 28 entries listed from openai/skills. The repository README
describes the whole collection, not this skill — read it on GitHub.
Alternatives in Design
- Weather Orchestrator Command — Fetch the current temperature for Dubai, UAE and create a visual SVG weather card 20.2k ★
- Canvas — Open, create, or update a visual canvas — add images, text, PDFs, wiki pages, and banana-generated assets to O 3.3k ★
- Extract Skill — Reverse-engineer design systems, tokens, and components from live products or screenshots 2.8k ★
Related Skills
Brand Context
Load and validate brand assets before any design work — logo, colors, typography, voice
Stark Assets
Plan UI assets for a Stark design before implementation, including references, icons, typography, generated pr
Writing Plans
Use when design is complete and you need detailed implementation tasks for engineers with zero codebase contex
Figloo
Chrome extension + local MCP server that lets coding agents like Claude Code and Codex read Figma designs thro
Auxi Mobile Designer
Dedicated mobile designer skill for the Auxi RN app. Use when the task involves design work BEFORE implementat
Ad Variation Generator
Claude Code skill: generate ad headline variations directly in Figma. Read your product context, find winning
Related Agents
Design Fidelity Reviewer
Reviews a designer's Figma delivery (via its captured handoff folder — screenshots, tokens.json, assets) again
Flutter Design Iteration Coordinator
Use this agent when coordinating the complete design-to-implementation workflow for Flutter apps, from initial
Ads Context Scanner Worker
Invoke this agent to do the mechanical page-scanning work for context-scanner — navigating pages, running JS s
