SVG Generator
Generate scalable vector graphics from text descriptions.
Installation
- Make sure Claude is on your device and in your terminal.
Skills load from
~/.claude/skills/when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then runclaudein any terminal to verify.One-time setupnpm i -g @anthropic-ai/claude-codeAlready have it? Skip ahead.
- Paste into Claude Code or into your terminal.
This copies the whole skill folder into
~/.claude/skills/create-svg-from-prompt-aiskillstore/— the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.Faster alternative (instruction-only skills)
Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.
Quick install (SKILL.md only)Sign up to copy - Restart Claude Code.
Quit and reopen Claude Code (or any other agent that loads from
~/.claude/skills/). New skills are picked up on startup. - Just ask Claude.
Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.
Prefer to read the source first? Open on GitHub.
When Claude uses it
Generate an SVG of a user-requested image or scene
What this skill does
Setup
if autotrace is not available in the environment, then install it with the following command:
sudo apt update
sudo apt install git build-essential intltool imagemagick libmagickcore-dev pstoedit libpstoedit-dev autopoint
git clone https://github.com/autotrace/autotrace.git
cd autotrace
./autogen.sh
LD_LIBRARY_PATH=/usr/local/lib ./configure --prefix=/usr
make
sudo make install
Core Workflow
When the user prompts the model to generate an SVG of and image or scene:
User wants an SVG of an image or scene
To generate an SVG of an image or scene use Google Gemini and autotrace:
curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-image:generateContent" -H "x-goog-api-key: <GEMINI_API_KEY>" -H "Content-Type: application/json" -d '{ "contents": [{ "parts": [ {"text": "<IMAGE_PROMPT>"}]}]}' | grep -o '"data": "[^"]*"' | cut -d'"' -f4 | base64 --decode | autotrace -output-format svg -despeckle-level 10 -despeckle-tightness 2.0 -output-file <OUTPUT_FILE>.svg
Arguments from prompt:
<GEMINI_API_KEY>: The Gemini API key gotten from the environment variable "GEMINI_API_KEY"<IMAGE_PROMPT>: The user's initial prompt modified to change phrases like "Generate an svg" to "Generate an image." Do not modify the rest of the prompt or add any extra instructions or descriptions.<OUTPUT_FILE>: An 8-30 character filename based on the image the user wants
Related skills
React & Next.js Performance
vercel-labs
Optimize React and Next.js code following Vercel's performance best practices.
React Composition Patterns
vercel-labs
Build flexible, maintainable React components using composition techniques.
Senior Frontend Engineer
alirezarezvani
Build and optimize React and Next.js applications with performance analysis and accessibility.
UI Design Guidelines Reviewer
vercel-labs
Review UI code for compliance with web interface best practices and accessibility standards.