agentleFS
Sign inStart free
podopodo/design-agent-skills/skills/figma-skill/SKILL.md

figma-skill

Skill32 starsChanged 6 months agoMITView on GitHub

Figma design bridge for Claude Code: browse Figma files through the figma-developer-mcp server, download assets, extract design tokens, and generate code for Tailwind, React, Vue, Svelte, React Native, Flutter and plain CSS. Also finds Figma Community resources that match the project. Needs a Figma access token and the figma-developer-mcp server.

  • Reads credentials

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before first use, set up the prerequisites the heads-up lists: a Figma personal access token, the figma-developer-mcp server in your …

    line 65

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

figma-skill

Catalogue stub — full skill: nafiurrahmanniloy/figma-skill (figma)

<!-- das:install:start — generated from stub.yaml by `npm run generate`; edit stub.yaml, not this block -->

Decision tree

  1. Is the full skill already installed? Upstream names this skill figma, so it installs next to this pointer (the pointer is not replaced).
    • Global: f=~/.agents/skills/figma/SKILL.md; [ -f "$f" ] && ! grep -q "^das:" "$f" && echo "installed" || echo "pointer"
    • Project: f=.agents/skills/figma/SKILL.md; [ -f "$f" ] && ! grep -q "^das:" "$f" && echo "installed" || echo "pointer"
    • installed → the skill is installed as figma, invoke it and proceed
    • pointer → go to step 2

  2. Detect scope, then install:

    [ -e ~/.agents/skills/figma-skill ] && echo "global" || echo "project"

    Global:

    npx skills add nafiurrahmanniloy/figma-skill --skill figma -g -y

    Project:

    npx skills add nafiurrahmanniloy/figma-skill --skill figma -y

    Claude Code: send a command as a chat message starting with ! to run it without leaving the conversation.

Heads-up

  • Requires: Figma personal access token (FIGMA_API_KEY); the figma-developer-mcp server configured in .mcp.json; Python 3.8+ (for the token and code scripts)
  • License: MIT
<!-- das:install:end -->

Invoke after install

  • Skill name: figma
  • Triggers: "figma-skill", "Figma API extract", "Figma to framework", "Figma Community resources"

Before first use, set up the prerequisites the heads-up lists: a Figma personal access token, the figma-developer-mcp server in your .mcp.json, and Python 3.8+. Without the MCP server the skill cannot read any Figma file.

What it does

A Figma-to-code workflow built on the figma-developer-mcp server. It browses a Figma file or a single node, downloads image assets, extracts design tokens (CSS variables, Tailwind config, SCSS or JSON) with a bundled Python script, and generates component code for Tailwind, React, Vue, Svelte, React Native, Flutter or plain CSS. A separate workflow builds a project profile and searches Figma Community for UI kits and design systems that fit it. Everything runs through your own Figma token.

When NOT to use

  • Official Figma file operations (reading/writing your files) — use the Figma MCP (figma-official-skills)
  • Design system token enforcement in Figma — use claude2figma
  • Token architecture without Figma — use design-tokens-skill

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free