Figma Analyze Component Set logo

Figma Analyze Component Set

Organization
southleft
figma-analyze-component-set

Analyze a Figma COMPONENT_SET as a state machine for code generation — extract variant axes (state/size/etc.), map state variants to CSS pseudo-classes (hover→:hover, focus→:focus-visible, disabled→:disabled, error→[aria-invalid]), and compute per-variant visual diffs (only what changes per state). Use when generating an interactive component from a Figma variant set — triggers: 'analyze this component set', 'turn these variants into CSS states', 'generate a button/input/checkbox from Figma variants', 'what changes between the hover and default state', 'map Figma variants to component props', 'extract the state machine for this component'. Resolves bound variables to token names. NOT covered by the native MCP's get_design_context/get_metadata, which don't give you a variant-axis→CSS-state machine.

Overview

Publishersouthleft
Repositoryfigma-console-mcp-skills
Skill namefigma-analyze-component-set
Stars
94
Forks
4
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by southleft on GitHub. Read the source before you install it.

Installation

Install the Figma Analyze Component Set AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/southleft/figma-console-mcp-skills/tree/main/skills/figma-analyze-component-set
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/southleft/figma-console-mcp-skills.git /tmp/figma-console-mcp-skills
mkdir -p .claude/skills
cp -r /tmp/figma-console-mcp-skills/skills/figma-analyze-component-set .claude/skills/figma-analyze-component-set
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Figma Analyze Component Set in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Figma Analyze Component Set on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Figma Analyze Component Set is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

figma-analyze-component-set — variant state machine → CSS

Take a Figma COMPONENT_SET (the purple dashed container holding all the variants of one component) and turn it into a code-generation blueprint: which property axes are state vs size, how each state maps to a CSS pseudo-class or ARIA attribute, and the minimal visual delta each state applies on top of the default variant. This is the bridge between "Figma has 12 button variants" and "emit one .btn rule + :hover/:disabled overrides."

Skill boundaries

  • use_figma rules — load the official figma-use skill first; it is the full Figma Plugin API reference. Essentials these scripts rely on: plain JS with top-level await + return (no IIFE, no figma.closePlugin(); console.log is not returned), inputs inlined as const at the top of each script, colors in 0–1 range, load fonts before any text op, await figma.getNodeByIdAsync(...), and atomic errors (a failed script applies nothing — read the error, fix, retry).
  • Full recursive tree (unlimited depth, reactions, instance refs) → use figma-deep-component.
  • Reorganizing variants into a labeled grid → use figma-arrange-component-set.
  • Adding/removing the properties themselves → use figma-component-properties.
  • This is a design-system code-gen capability that the native MCP's get_design_context / get_metadata do not provide — they return raw structure, not a variant→CSS state machine.

Workflow

  1. Get the COMPONENT_SET id. From the user's selection (figma_get_selection), a search, or a node id they paste. It must be the set, not an individual variant — the script validates type.
  2. Run scripts/analyze-component-set.js via use_figma (skillNames: "figma-analyze-component-set"). Set const COMPONENT_SET_ID at the top first.
  3. Read the result. It returns variantAxes (each axis + its options), componentProps (non-variant TEXT/BOOLEAN/INSTANCE_SWAP props → code props), a stateMachine with cssMapping (state name → CSS selector) and defaultSignature, and per-variant diffFromDefault.
  4. Generate code. Implement the default variant from defaultSignature, then add one rule per cssMapping entry applying only that variant's diffFromDefault. Map componentProps to framework props: BOOLEAN→boolean, TEXT→string, INSTANCE_SWAP→ReactNode/slot, VARIANT→union.
  5. Validate. Cross-check that every state in stateMachine.states got a CSS rule, and that token names in the diff (e.g. Color/Brand/Primary) resolve to your exported tokens.

How states map to CSS

The script normalizes the state axis value (case-insensitive) to a selector:

Variant valueCSS / ARIA selector
default(base rule, no selector)
hover:hover
focus / focused / focus-visible:focus-visible
active / pressed:active
disabled:disabled, [aria-disabled="true"]
error / invalid[aria-invalid="true"]
selected[aria-selected="true"]
checked:checked
loading[aria-busy="true"]
open / closed`[aria-expanded="true"
filled.has-value

Notes

  • Diffs are computed against the default variant, so a state's diffFromDefault lists only the properties that change (fill token, stroke, text color, opacity, effects, child visibility). Emit exactly those as overrides — don't re-specify unchanged properties.
  • The script resolves boundVariables (fills/strokes) to token names when available, falling back to raw hex. Prefer the token name in generated code.
  • Axis detection is heuristic: an axis named state/status/interaction is the state axis; size/scale is the size axis. If your set names axes differently, the cssMapping may be empty — read variantAxes and map states yourself.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Figma Analyze Component Set AI skill do?

Analyze a Figma COMPONENT_SET as a state machine for code generation — extract variant axes (state/size/etc.), map state variants to CSS pseudo-classes (hover→:hover, focus→:focus-visible, disabled→:disabled, error→[aria-invalid]), and compute per-variant visual diffs (only what changes per state). Use when generating an interactive component from a Figma variant set — triggers: 'analyze this component set', 'turn these variants into CSS states', 'generate a button/input/checkbox from Figma variants', 'what changes between the hover and default state', 'map Figma variants to component props...

Why use Figma Analyze Component Set on TypingMind?

Because you install it once and use it with any model. Figma Analyze Component Set is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Figma Analyze Component Set in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/southleft/figma-console-mcp-skills/tree/main/skills/figma-analyze-component-set. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Figma Analyze Component Set?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Figma Analyze Component Set?

As many as you like. As long as a model supports skills, you can use Figma Analyze Component Set with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Figma Analyze Component Set AI skill free?

Yes. It is published on GitHub by southleft under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇