Figma Web Capture logo

Figma Web Capture

Organization
memi-design
figma-web-capture

Figma web capture workflow - import live webpages or DOM elements into editable Figma layers with the public html-to-design capture.js bookmarklet

Overview

Publishermemi-design
Repositorydesign-skills
Skill namefigma-web-capture
Stars
7
Forks
0
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 memi-design on GitHub. Read the source before you install it.

Installation

Install the Figma Web Capture 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/memi-design/design-skills/tree/main/skills/figma-web-capture
  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/memi-design/design-skills.git /tmp/design-skills
mkdir -p .claude/skills
cp -r /tmp/design-skills/skills/figma-web-capture .claude/skills/figma-web-capture
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Figma Web Capture 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 Web Capture 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 Web Capture 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 Web Capture

Use this when a user wants to bring a webpage into Figma as editable layers instead of a screenshot.

This is a practical workflow built on Figma's public html-to-design capture asset. Treat it as an unofficial bookmarklet path, not as a guaranteed product surface. Re-check the script URL if Figma changes the flow.

What It Does

  • Loads Figma's public capture.js helper into the current page.
  • Serializes the rendered DOM into Figma layers.
  • Copies the capture to the clipboard so it can be pasted into any open Figma file.
  • Supports capturing the full viewport or a selected element.

Public Script

The capture helper lives at:

https://mcp.figma.com/mcp/html-to-design/capture.js

Load that script into the page, then use the capture toolbar to copy the result to the clipboard.

As of March 27, 2026, this public URL returns HTTP 200.

Recommended Workflow

  1. Open the target page in a desktop browser.
  2. Wait for fonts, images, and lazy-loaded content to finish rendering.
  3. Scroll to the exact section you want to capture.
  4. Run the bookmarklet or injected script that loads capture.js.
  5. In the toolbar, choose Copy to clipboard.
  6. Switch to Figma and paste into a dedicated scratch frame or page.
  7. If you only need part of the page, use Select element before copying.

Safe Positioning

  • Capture the smallest stable container that still includes the content you need.
  • Paste into a scratch frame first, then move pieces into the final canvas.
  • Keep one capture per page or frame so imported layers stay organized.
  • Capture after scrolling into the intended viewport, not before.

Example Bookmarklet

javascript
javascript:(function(){var s=document.createElement('script');s.src='https://mcp.figma.com/mcp/html-to-design/capture.js';document.head.appendChild(s);setTimeout(function(){window.location.hash='figmacapture&figmadelay=1000';var s2=document.createElement('script');s2.src='https://mcp.figma.com/mcp/html-to-design/capture.js';document.head.appendChild(s2);},500);})();

When To Prefer It

  • Fast visual reverse-engineering from a live site into Figma.
  • Pulling one viewport or one component into a scratch page for redesign.
  • Capturing authenticated or in-progress UI that already renders correctly in the browser.

When Not To Use It

  • Sites with strict CSP that block injected scripts.
  • Cases where you need semantic code, reusable tokens, or a live sync instead of a one-time capture.
  • Mobile-browser workflows, since javascript: bookmarklets are commonly blocked there.

Caveats

  • Strict CSP sites can block external scripts, which prevents the toolbar from appearing.
  • Mobile browsers usually block javascript: bookmarklets.
  • Auth-gated pages capture what your current browser session can see.
  • Lazy-loaded content must be visible before capture.
  • The result is editable layers, but it is still a DOM capture, not live code.
  • Only run the bookmarklet on pages you trust, because it injects remote JavaScript into the page.
  • This is a public Figma-hosted script, but it is still an implementation detail and could change without notice.

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 Web Capture AI skill do?

Figma web capture workflow - import live webpages or DOM elements into editable Figma layers with the public html-to-design capture.js bookmarklet

Why use Figma Web Capture on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/memi-design/design-skills/tree/main/skills/figma-web-capture. 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 Web Capture?

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 Web Capture?

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

Is the Figma Web Capture AI skill free?

Yes. It is published on GitHub by memi-design 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 👇