Component Properties Figma logo

Component Properties Figma

Organization
southleft
component-properties-figma

Add, edit, and delete Figma component properties (TEXT, BOOLEAN, INSTANCE_SWAP, VARIANT) on a COMPONENT or COMPONENT_SET, and instantiate a component then set its instance properties. Use when authoring or wiring up a component's API in Figma — triggers: 'add a component property', 'add a boolean prop to this component', 'make this text a component property', 'add an instance-swap slot', 'create a variant property', 'rename/delete a component property', 'place an instance of this component', 'instantiate this component and set its label/state', 'set properties on this instance'. Properties must be added to the parent COMPONENT_SET, not individual variants. NOT covered by the native MCP's read-only get_design_context/get_metadata.

Overview

Publishersouthleft
Repositoryskills-for-figma
Skill namecomponent-properties-figma
Stars
20
Forks
1
Bundled files
2
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.

  • 2 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 Component Properties Figma 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/skills-for-figma/tree/main/skills/component-properties-figma
  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/skills-for-figma.git /tmp/skills-for-figma
mkdir -p .claude/skills
cp -r /tmp/skills-for-figma/skills/component-properties-figma .claude/skills/component-properties-figma
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Component Properties Figma 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 Component Properties Figma 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 Component Properties Figma 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.

component-properties-figma — define a component's API + instantiate it

Two related jobs:

  1. Author the component's property API — add/edit/delete TEXT, BOOLEAN, INSTANCE_SWAP, and VARIANT properties so the component exposes the right knobs (the Figma equivalent of a React component's props).
  2. Use the component — create an instance and set its properties (label text, boolean toggles, variant selection, swapped sub-instances).

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).
  • Reading a component's existing property definitions / state machine → use analyze-component-set-figma or deep-component-figma.
  • These are design-system authoring writes the native MCP's get_design_context / get_metadata (read-only) do not cover.

Property types

TypeWhat it controlsdefaultValueNotes
TEXTA text-layer string override"Label"Bind in UI to a text node's characters
BOOLEANShow/hide a layertrue/falseBind to a layer's visibility
INSTANCE_SWAPWhich sub-component fills a slota component keyPass preferredValues to populate the picker
VARIANTA variant axis (Size, State…)one option stringOnly meaningful on a COMPONENT_SET

Workflow — authoring properties

  1. Target the COMPONENT_SET (or standalone COMPONENT). You cannot add properties to an individual variant — the script errors and tells you to use the parent set.
  2. Add with scripts/add-property.js (use_figma, skillNames: "component-properties-figma"). Set NODE_ID, PROPERTY_NAME, PROPERTY_TYPE, DEFAULT_VALUE. addComponentProperty returns a name with a #id suffix — capture it.
  3. Edit / delete by reusing the same script's editComponentProperty(name, {...}) / deleteComponentProperty(name) calls (commented variants are in the script). Use the suffixed name returned at creation for edits/deletes of non-variant props.
  4. Verify by re-reading node.componentPropertyDefinitions (the script returns it).

Workflow — instantiate + set instance properties

  1. Get a component identity. A published library componentKey (preferred) and/or a local nodeId. Pass both when you have them — the script tries the library import first, then the local node.
  2. Run scripts/instantiate-and-set.js. Set COMPONENT_KEY / COMPONENT_ID, optional VARIANT (e.g. { Size: "md", State: "default" }), OVERRIDES, POSITION, and PARENT_ID.
  3. Set properties on an existing instance with the same script's setProperties path — it loads the main component, then matches plain names and Name#id-suffixed names automatically.

Notes

  • Instance property keys carry #nodeId suffixes for TEXT/BOOLEAN/INSTANCE_SWAP ("Label#12:3"); VARIANT props use the bare name. The instantiate script resolves both, so you can pass the human name (Label) and it finds the suffixed key.
  • Direct text editing of an instance's text layer fails silently — always go through setProperties / instance properties, never set .characters on a nested instance text node.
  • componentKey only works for published components. For local/unpublished ones use nodeId.

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 Component Properties Figma AI skill do?

Add, edit, and delete Figma component properties (TEXT, BOOLEAN, INSTANCE_SWAP, VARIANT) on a COMPONENT or COMPONENT_SET, and instantiate a component then set its instance properties. Use when authoring or wiring up a component's API in Figma — triggers: 'add a component property', 'add a boolean prop to this component', 'make this text a component property', 'add an instance-swap slot', 'create a variant property', 'rename/delete a component property', 'place an instance of this component', 'instantiate this component and set its label/state', 'set properties on this instance'. Properties...

Why use Component Properties Figma on TypingMind?

Because you install it once and use it with any model. Component Properties Figma 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 Component Properties Figma in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/southleft/skills-for-figma/tree/main/skills/component-properties-figma. 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 Component Properties Figma?

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 Component Properties Figma?

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

Is the Component Properties Figma 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 👇