figma-design-system-to-design-md

Convert Figma design tokens into structured design.md documentation for AI coding tools.

4|Updated May 16, 2026
One-click install
npx skills add https://github.com/reason-machines/design-skills --skill figma-design-system-to-design-md-reason-machines
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: figma-design-system-to-design-md
Source: https://github.com/reason-machines/design-skills/tree/main/skills/figma-design-system-to-design-md
Command: npx skills add https://github.com/reason-machines/design-skills --skill figma-design-system-to-design-md-reason-machines

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Design systems live in Figma and scattered code files, but documentation is outdated or missing, forcing developers to guess at color roles, spacing scales, and typography when working with AI coding assistants. ## Core Features & Use Cases - Automatic Token Detection: Scans projects for CSS variables, Tailwind configs, and TypeScript theme files, then parses and classifies tokens into colors, typography, spacing, radius, and breakpoints. - Structured design.md Generation: Produces a complete design.md with semantic color roles, type scales, and spacing values that Cursor, Claude Code, and Copilot can consume. - Optional Figma MCP Enrichment: Pulls component variants and effect styles from Figma via the Dev Mode MCP Server. - Use Case: A team with tokens spread across tokens.css and tailwind.config.ts runs one command to generate a unified design.md, then commits it so every AI-assisted coding session uses accurate design system context. ## Quick Start Ask the AI to generate a design.md file from the design tokens in your project, optionally pointing it at your styles directory.

Frequently Asked Questions about figma-design-system-to-design-md

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate a design.md file from my design tokens?▼

Run the skill command in your project root and it automatically detects token files like tokens.css, tailwind.config.ts, or theme.ts. It parses colors, typography, spacing, and breakpoints into a structured design.md that AI coding tools can read.

What token file formats are supported for design.md generation?▼

Supported sources include CSS variable files (tokens.css, variables.css, globals.css), JSON/JS/TS token files, and framework configs like tailwind.config.js and uno.config.ts. Multiple sources in one project are merged into a single design.md.

Does this work with Tailwind CSS projects?▼

Yes, it parses tailwind.config.js or tailwind.config.ts files, extracting colors, fontFamily, spacing, borderRadius, and breakpoints from theme.extend. The config must export values under theme.extend to be detected.

Why are no tokens detected when I run the command?▼

Detection fails when token files are not in common paths or use non-standard names. Point the tool at your styles directory explicitly, or rename files to match patterns like tokens.css or variables.css.

Do I need Figma MCP to use this skill?▼

No, Figma MCP is optional and only adds component variants and effect styles to the output. Core sections like colors, typography, and spacing are generated entirely from token files in your codebase.

Why are some design.md sections missing after generation?▼

Overview and Do's and Don'ts sections require manual writing, and component data requires Figma MCP. Elevation values may also be absent if shadows are not defined in your Tailwind config or Figma file.