Svg Hand Drawn Preview logo

Svg Hand Drawn Preview

Community
shaom
svg-hand-drawn-preview

Generate a hand-drawn SVG animation package from a local SVG file or SVG URL. Use when the user wants an SVG drawing demo with path-plus-fill animation, or wants the default deliverables to be a standalone preview.html plus a reusable player.js.

Overview

Publishershaom
Repositorysvg-hand-drawn-skill
Skill namesvg-hand-drawn-preview
Stars
267
Forks
31
Bundled files
4
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.

  • 4 bundled files

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

  • Open source

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

Installation

Install the Svg Hand Drawn Preview 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/shaom/svg-hand-drawn-skill/tree/main/skills/svg-hand-drawn-preview
  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/shaom/svg-hand-drawn-skill.git /tmp/svg-hand-drawn-skill
mkdir -p .claude/skills
cp -r /tmp/svg-hand-drawn-skill/skills/svg-hand-drawn-preview .claude/skills/svg-hand-drawn-preview
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Svg Hand Drawn Preview 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 Svg Hand Drawn Preview 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 Svg Hand Drawn Preview 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.

SVG Hand-Drawn Preview

Use this skill when the task is to turn an SVG into a hand-drawn animation deliverable.

Default operating mode:

  • The agent should generate the output files directly for the user.
  • Do not require the user to run Python, Node, or any local build step unless they explicitly ask for a self-serve generator.

Default output:

  • A standalone preview.html file that can be opened directly in the browser
  • A reusable player.js file for embedding into another web page

Optional side outputs:

  • animated.svg
  • animation-plan.json
  • an embed demo page when the user wants component-style integration

Keep this skill independent from any project-specific demo page unless the user explicitly asks to integrate into an existing file.

What To Produce

By default, produce:

  • a self-contained preview.html
  • a reusable player.js

The default result should:

  • load a target SVG file or inline SVG markup
  • animates path drawing first
  • animates fill afterward
  • expose a compact control surface when useful: play, speed, progress
  • preserves source colors as closely as possible
  • reuse the same playback core across both outputs

Only produce side artifacts when they help:

  • animated.svg for reuse in other apps
  • animation-plan.json when the user wants structured animation metadata
  • an embed demo page when the user wants to show integration inside a normal web page

Inputs

Accept either:

  • a local SVG file path
  • an SVG URL

Optional inputs:

  • preferred animation mode
  • desired output file name
  • whether to include playback controls
  • whether to emit side artifacts

If the user does not specify these, use:

  • output: preview.html plus player.js
  • include controls: yes
  • default animation: path draw plus fill reveal

Workflow

  1. Inspect the SVG source first.
  • Check whether shapes are stroke-based, fill-only, or mixed.
  • Check whether colors live in attributes or inline style.
  • Check whether there are unsupported constructs such as foreignObject, raster images, or masks that cannot be reproduced faithfully.
  1. Normalize for animation.
  • Mark drawable path-like elements.
  • Separate path timing from fill timing.
  • For fill-only shapes, create a fill layer plus a temporary stroke layer if needed.
  • Preserve original colors and opacity.
  1. Build the preview page.
  • Prefer a single-file HTML result.
  • Keep CSS and JS inside the HTML unless the user explicitly wants multiple files.
  • Ensure the page opens cleanly without requiring a local server when possible.
  • Emit a sibling player.js in the same output directory by default.
  1. When the user asks about webpage embedding.
  • Prefer a small player.js player plus a host-page demo over an iframe-only answer.
  • Keep the embed API simple: target selector or element plus SVG markup and playback options.
  1. Validate the result.
  • Check that the page still renders the complete static SVG before playback.
  • Check that playback starts from zero.
  • Check that path and fill both appear in the expected order.
  • Check that imported fill-only SVGs do not lose their colors.

Output Rules

  • Default to preview.html and player.js in the current working directory unless the user asks for another location.
  • If you create animated.svg or animation-plan.json, place them next to preview.html.
  • Keep output names predictable and easy to move into another repository.

Animation Defaults

Use these defaults unless the SVG or user request suggests otherwise:

  • Path animation: smooth hand-draw
  • Fill animation: soft reveal after path completion
  • Speed: 1x
  • Controls: enabled
  • Background: neutral, minimal, not tied to any brand

For fill-heavy illustration SVGs:

  • do not guess a thick temporary stroke
  • prefer conservative stroke width estimation
  • preserve original fill colors exactly

When To Read Additional References

Constraints

  • Do not assume the input SVG already uses animation-friendly structure.
  • Do not hard-couple the skill to one existing project file.
  • Do not silently drop fill behavior for path animation modes unless the user explicitly asks for stroke-only output.
  • Do not change source colors unless the selected animation mode intentionally overrides them.

Completion Checklist

Before finishing, verify:

  • the output HTML opens as a standalone preview
  • player.js is emitted next to the preview output
  • the SVG is visible before playback starts
  • path drawing is visible during playback
  • fill appears after path completion
  • colors remain close to the source SVG
  • any optional side outputs remain consistent with the preview behavior

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 Svg Hand Drawn Preview AI skill do?

Generate a hand-drawn SVG animation package from a local SVG file or SVG URL. Use when the user wants an SVG drawing demo with path-plus-fill animation, or wants the default deliverables to be a standalone preview.html plus a reusable player.js.

Why use Svg Hand Drawn Preview on TypingMind?

Because you install it once and use it with any model. Svg Hand Drawn Preview 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 Svg Hand Drawn Preview in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/shaom/svg-hand-drawn-skill/tree/main/skills/svg-hand-drawn-preview. 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 Svg Hand Drawn Preview?

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 Svg Hand Drawn Preview?

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

Is the Svg Hand Drawn Preview AI skill free?

It is published on GitHub by shaom. 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 👇