Figma Shaders logo

Figma Shaders

OrganizationPopular
figma
figma-shaders

**MANDATORY prerequisite** — load this skill before calling `create_shader` or `update_shader`. Use when the user asks to create, author, change, fix, or iterate on a shader effect, shader fill, custom effect, custom fill, or procedural shader in Figma.

Overview

Publisherfigma
Repositorymcp-server-guide
Skill namefigma-shaders
Stars
2K
Forks
194
Bundled files
1
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 figma on GitHub. Read the source before you install it.

Installation

Install the Figma Shaders 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/figma/mcp-server-guide/tree/main/skills-figquery/figma-shaders
  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/figma/mcp-server-guide.git /tmp/mcp-server-guide
mkdir -p .claude/skills
cp -r /tmp/mcp-server-guide/skills-figquery/figma-shaders .claude/skills/figma-shaders
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Figma Shaders 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 Shaders 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 Shaders 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.

Create and update Figma shaders

Load this skill before every create_shader or update_shader call. It covers account-library shader authoring through the Figma MCP server. Reading or applying an existing shader does not require this skill.

Shaders have two kinds:

  • effect samples and transforms the rendered layer beneath it. Use it for blur, distortion, glow, color grading, pixelation, halftone, or other post-processing.
  • fill generates pixels without an input raster. Use it for gradients, patterns, noise, textures, and procedural backgrounds.

Do not silently switch kinds during an update. The kind passed to update_shader must match the existing shader.

Create workflow

  1. Decide whether the request is an effect or fill. Ask only when the visual intent does not resolve the distinction.
  2. Resolve planKey. Reuse one supplied by the user; otherwise call whoami. Use the sole eligible plan automatically, or ask the user to choose when several materially different plans are available.
  3. Call create_shader once with a concise name, description, selected kind, and planKey. This creates a starter scaffold, not the requested final shader.
  4. Call get_shader with the returned id, then read every source URI. If the client cannot read MCP resources, call get_shader with includeSource: true instead. This establishes the runtime imports and the scaffold's fixed metadata contract.
  5. Author the complete replacement main.ts for the requested result.
  6. Call update_shader with the returned id, the same kind, files: [{ path: "main.ts", content: "..." }], and a specific commitMessage. Use metadata when changing the name, description, or animation capabilities. Set metadata.isAnimated: true when the source reads time-related frame inputs and metadata.usesMouse: true when it reads frame.mousePosition.

Never stop after create_shader: the starter scaffold is only a structural starting point.

Update workflow

  1. Identify the shader with list_shaders, then call get_shader. Use its type (effect or fill) as the required update kind.
  2. Read every source URI returned by get_shader before editing. If the client cannot read MCP resources, call it with includeSource: true. Treat those files as the current source of truth.
  3. Preserve existing controls and behavior unless the user asks to change them.
  4. Call update_shader with the complete replacement main.ts in the files array, not a diff or partial fragment. An empty files array is valid only for a metadata-only update.

Authoring rules

  • Before writing the main.ts replacement, read Shader source authoring. It contains the required module shape, WebGPU lifecycle, supported parameter schemas, effect/fill alpha rules, and WGSL failure checklist.
  • Match animation metadata to the source. Set metadata.isAnimated: true if main.ts reads frame.time, frame.deltaTime, or frame.frame, and set metadata.usesMouse: true if it reads frame.mousePosition. Set the corresponding value to false when removing the last such use. update_shader applies these metadata fields to the fixed features.json manifest even though that file cannot be replaced directly.
  • Prefer frame.time for animation so skipped frames do not change the result. It is an absolute millisecond clock; convert it to seconds with Number(frame.time) * 0.001 when useful.
  • Expose controls for values users are likely to tune per layer; hardcode implementation details.
  • Keep numeric ranges bounded and defaults visually useful.
  • For effects, sample the input raster intentionally. For fills, do not assume an input raster exists.
  • Treat a non-error update_shader result as success. Record the returned version when present; a successful response may omit it.
  • On a build error, use the returned compiler output to make the smallest source correction and retry once. If it still fails, surface the error instead of repeatedly rewriting the shader.
  • If the tool reports that animation or mouse input is unavailable, treat that as a terminal capability gate: do not retry or attempt to bypass it. Offer to author a static shader whose exposed properties can be keyframed in Motion mode instead.

Completion

Report the shader name, kind, and id, plus the returned version when present. Briefly identify the controls or behavior that were added. Construct and include a clickable URL that opens a new Design file with the unpublished shader ready to try, using the exact shader id as try-tool-resource-content-id. Set try-tool-resource-type from the shader kind: gen_effect for an effect and gen_fill for a fill.

https://www.figma.com/file/new?try-tool-resource-content-id=<id>&try-tool-resource-type=<gen_effect|gen_fill>&type=design&mode=design

After presenting the new-file link, ask whether the user wants to open the shader in an existing Figma Design file instead. If yes, reuse a file URL already provided or ask for one, then add the same try-tool-resource-content-id and resolved try-tool-resource-type query parameters to that URL. Never guess the file URL.

Replace the type placeholder with exactly one value; do not include angle brackets or the pipe in the returned URL.

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 Shaders AI skill do?

**MANDATORY prerequisite** — load this skill before calling `create_shader` or `update_shader`. Use when the user asks to create, author, change, fix, or iterate on a shader effect, shader fill, custom effect, custom fill, or procedural shader in Figma.

Why use Figma Shaders on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/figma/mcp-server-guide/tree/main/skills-figquery/figma-shaders. 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 Shaders?

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 Shaders?

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

Is the Figma Shaders AI skill free?

It is published on GitHub by figma. Check the repository for licensing terms. 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 👇