figma-variables-tokens-generator

|

podo/design-agent-skills65 installsMITSynced Aug 22

Works with

Claude CodeCursorCodex CLIGitHub CopilotGemini CLI
---
name: figma-variables-tokens-generator
description: |
license: MIT
---

# figma-variables-tokens-generator

> Catalogue stub — full package: [Shanmus4/figma-variables-tokens-generator](https://github.com/Shanmus4/figma-variables-tokens-generator)

## Decision tree

1. **Is the skill already installed?** Check `~/.design-agent-skills/skills/` for `figma-variables-tokens-generator` or related directories.
   - Yes → invoke and proceed
   - No → go to step 2

2. **Shell access?** Yes → install below. No → show user the command (Claude Code: send with `!` as a chat message — add `-g` for global or omit for project-only).

## Install command

```bash
npx skills add Shanmus4/figma-variables-tokens-generator
```

## Invoke after install

- Skill name: `figma-variables-tokens-generator`
- Triggers: "Figma variables", "token generator", "W3C token ZIP", "Shanmus4"

## What it does

Runs a structured questionnaire to understand your design system needs, then generates a W3C Design Token Community Group (DTCG) compliant ZIP archive. The ZIP contains JSON token files organized into collection tiers: Primitives (raw values), Semantic (contextual aliases), and Component (component-specific tokens). Also provides a companion Figma plugin that imports these JSON files into Figma Variables, respecting dependency order across tiers.

## When NOT to use

- Code-side token management and pipelines — use `design-tokens-skill`
- Existing design systems not based in Figma
- Figma design operations unrelated to tokens — use the Figma MCP (`figma-official-skills`)

More Design Systems skills

stitch-design-taste

leonxlnx/taste-skill

Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.

265.6k

figma

heygen-com/hyperframes

Import Figma content into a HyperFrames composition — rendered assets, brand tokens, components, storyboard sections → reconstructed motion (frames read as states, not slides) (REST/CLI), connector-assisted motion when available, and shaders from a connector or native export. Use when the user pastes a figma.com link or asks to bring a Figma design, frame, logo, brand, or animation into a video/composition.

101.8k

image

coreyhaines31/marketingskills

When the user wants to create, generate, edit, or optimize images for marketing — blog heroes, social graphics, product mockups, profile banners, listing visuals, or brand assets. Also use when the user mentions 'AI image generation,' 'generate an image,' 'create a graphic,' 'product mockup,' 'hero image,' 'social media graphic,' 'banner image,' 'cover photo,' 'profile banner,' 'listing screenshot,' 'Flux,' 'Flux Kontext,' 'Midjourney,' 'DALL-E,' 'GPT Image,' 'ChatGPT Images,' 'Ideogram,' 'Gemini image,' 'Nano Banana,' 'Recraft,' 'Stable Diffusion,' 'Canva,' 'Figma,' 'image optimization,' 'compress images,' 'WebP,' or 'OG image.' Use this for general-purpose marketing image creation and optimization. For paid ad image creative and platform-specific ad specs, see ad-creative. For video production, see video.

62.9k

← All Design Systems skills

Check your AI visibility

One URL in, a 0–100 score and the exact fixes out.

RUN THE CHECK

Browse all the tools

15 tools across six categories
13 of them never send your data anywhere

Free · No signup · No trial clock

SEE THE DIRECTORY