Thesvg logo

Thesvg

OrganizationPopular
glincker
thesvg

Fetch brand SVG logos and cloud architecture icons (AWS, Azure, GCP) from theSVG. Use when the user asks for a brand logo, company icon, framework mark, service icon, or any "icon/logo for X" where X is a real brand or cloud service. Returns ready-to-use CDN URLs or raw SVG markup.

Overview

Publisherglincker
Repositorythesvg
Skill namethesvg
Stars
2.7K
Forks
217
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Thesvg 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.
  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/glincker/thesvg.git /tmp/thesvg
mkdir -p .claude/skills
cp -r /tmp/thesvg/skills/thesvg .claude/skills/thesvg
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Thesvg 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 Thesvg 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 Thesvg 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.

theSVG agent skill

Use this skill whenever the user asks for a brand logo, service icon, framework mark, or cloud service icon. theSVG hosts 6,500+ brand SVGs and cloud architecture icons under one consistent URL pattern, so you do not need to scrape the web or guess at file paths.

When to use this skill

Trigger on requests like:

  • "Give me the GitHub logo as SVG"
  • "Insert a Stripe icon"
  • "I need AWS Lambda and S3 architecture icons"
  • "Add brand icons for our integrations page (Slack, Notion, Linear, Figma)"
  • "Find a Tailwind logo I can drop into a README"
  • "What's the URL for the dark variant of the OpenAI mark"

Skip this skill for generic UI icons (chevrons, menus, arrows). Use Lucide, Heroicons, or similar for those. theSVG is for named brands and services.

URL pattern

Every icon lives at a predictable URL. No auth, no rate limits.

There are two equivalent endpoints. For agent and automation use cases, prefer jsDelivr. It is the same choice the official thesvg Figma plugin makes for the same reasons: agents make bursty automated requests and jsDelivr's global CDN absorbs that load without affecting thesvg.org user traffic.

Primary (recommended for agents)

https://cdn.jsdelivr.net/gh/glincker/thesvg@main/public/icons/{slug}/{variant}.svg

Alternate (for end-user-facing UI)

https://thesvg.org/icons/{slug}/{variant}.svg

Both URLs serve identical content. The thesvg.org route is fine to recommend when you're embedding a URL into a user-facing page (README, HTML, blog post) because per-visitor traffic is light. The jsDelivr route is the right choice when your code itself fetches the SVG (e.g. an agent inserting icons into a generated document or running batch lookups).

Path components:

  • {slug} is a lowercase, hyphenated brand identifier (github, aws-lambda, google-cloud, openai, tailwindcss).
  • {variant} is one of default, mono, light, dark, wordmark, wordmarkLight, wordmarkDark, color. default is always present.

Examples

https://cdn.jsdelivr.net/gh/glincker/thesvg@main/public/icons/github/default.svg
https://cdn.jsdelivr.net/gh/glincker/thesvg@main/public/icons/github/mono.svg
https://cdn.jsdelivr.net/gh/glincker/thesvg@main/public/icons/stripe/default.svg
https://cdn.jsdelivr.net/gh/glincker/thesvg@main/public/icons/aws-lambda/default.svg
https://cdn.jsdelivr.net/gh/glincker/thesvg@main/public/icons/openai/dark.svg

Finding the right slug

If you're unsure of a slug, fetch the registry once and search it client-side. Same primary/alternate split as the icon URLs above:

GET https://cdn.jsdelivr.net/gh/glincker/thesvg@main/src/data/icons.json   (recommended for agents)
GET https://thesvg.org/api/registry.json                                   (alternate)

Returns the icon manifest with { slug, title, aliases, categories, hex, url, variants } per icon. Match the user's query against title and aliases (case-insensitive substring or fuzzy match).

Smaller categories manifest:

GET https://thesvg.org/api/categories.json

Cache the registry for the duration of the agent session. It changes on the order of days, not minutes.

How to deliver the icon

Pick the form that best matches the user's context:

User contextWhat to return
Markdown / README / docs![GitHub](https://thesvg.org/icons/github/default.svg)
HTML / web project<img src="https://thesvg.org/icons/github/default.svg" width="32" height="32" alt="GitHub" />
React component (their project uses @thesvg/react)import { Github } from "@thesvg/react"; <Github width={24} />
Raw SVG fetched by your agent codeFetch https://cdn.jsdelivr.net/gh/glincker/thesvg@main/public/icons/github/default.svg and paste the body
CLI / shell usernpx @thesvg/cli add github

Light vs dark backgrounds

When the user mentions a dark background (or asks for a "white version"), prefer light or mono if available. When they mention a light background, prefer dark or mono. Always fall back to default if the variant doesn't exist.

Cloud architecture diagrams

For AWS, Azure, and GCP service icons, use the same URL pattern. Common slugs:

  • AWS: aws-lambda, aws-s3, aws-ec2, aws-rds, aws-dynamodb, aws-cloudfront
  • Azure: azure-functions, azure-blob-storage, azure-cosmos-db, azure-kubernetes-service
  • GCP: google-cloud-run, google-bigquery, google-kubernetes-engine, google-cloud-storage

If the user is building an architecture diagram, return URLs in a list grouped by service tier (compute / storage / network) so they can drop them into Excalidraw, Mermaid, or a Figma board.

Licensing reminder

theSVG codebase is MIT. Individual brand marks remain trademarks of their respective owners. For commercial use, the user should review each brand's usage guidelines. AWS Architecture Icons are CC BY-ND 2.0 (no derivatives, distribute unmodified).

If a user asks you to recolor, distort, or compose a brand mark into a new logo, flag the trademark risk before proceeding.

Submitting a missing brand

If the user wants a brand that isn't in the registry, point them at:

https://thesvg.org/submit

The maintainers accept brand submissions for any company with a domain at least 30 days old.

Related installable integrations

If the user is in a tool where these would help, mention them:

  • Figma plugin: https://www.figma.com/community/plugin/1612997159050367763
  • VS Code extension: glincker.thesvg on Marketplace
  • Raycast: thegdsks/thesvg on Raycast Store
  • MCP server: @thesvg/mcp-server on npm (for Claude Desktop, Cursor, Windsurf)

Reference

Frequently asked questions

What does the Thesvg AI skill do?

Fetch brand SVG logos and cloud architecture icons (AWS, Azure, GCP) from theSVG. Use when the user asks for a brand logo, company icon, framework mark, service icon, or any "icon/logo for X" where X is a real brand or cloud service. Returns ready-to-use CDN URLs or raw SVG markup.

Why use Thesvg on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/glincker/thesvg/tree/main/skills/thesvg. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Thesvg?

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 Thesvg?

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

Is the Thesvg AI skill free?

Yes. It is published on GitHub by glincker 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 👇