Vm0 Illustration logo

Vm0 Illustration

Organization
vm0-ai
vm0-illustration

Generate vm0-style vm0 in-app spot illustrations: bold hand-drawn ink line art with white-filled interiors, a soft rounded color backdrop, transparent output, and simple iconic metaphors for product states.

Overview

Publishervm0-ai
Repositoryvm0-skills
Skill namevm0-illustration
Stars
76
Forks
18
Bundled files
Instructions only
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 vm0-ai on GitHub. Read the source before you install it.

Installation

Install the Vm0 Illustration 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/vm0-ai/vm0-skills.git /tmp/vm0-skills
mkdir -p .claude/skills
cp -r /tmp/vm0-skills/illustration-template/vm0-illustration .claude/skills/vm0-illustration
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Vm0 Illustration 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 Vm0 Illustration 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 Vm0 Illustration 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.

vm0 Illustration

Use this register-only image style when the user asks for a vm0 in-app spot illustration, empty-state artwork, billing/permission/error state artwork, or a small product UI illustration in the vm0 style.

This style is separate from Notion Illustration. Notion Illustration is black brush-pen editorial character artwork on pure white. vm0 Illustration is a vm0 product illustration style built around a single iconic object or metaphor, white-filled line art, and one soft color backdrop.

Locked Style

  • Square spot illustration, usually 1024 x 1024.
  • Transparent final background in the delivered artifact.
  • Preferred generation setup: generate on a flat full-canvas warm gray background (#eeeeee), then remove only that gray background to transparency. This preserves pure-white object interiors. Direct transparent-background generation often creates unwanted glow/vignette and gray object fills.
  • One central product metaphor or object, not a character scene.
  • Bold confident black brush-pen ink line drawing, with thick chunky decisive strokes and natural hand-drawn wobble. Lines should look committed and drawn once, not ruler-straight or vector-clean.
  • Outlines have intentional small gaps and breaks for a breathy hand-drawn quality.
  • Minimal detail: only essential contours and one or two key details. No fine textures, no crosshatching, no heavy shading.
  • Pure white (#FFFFFF) filled interior inside the line art so the drawing stays opaque over the color shape. The interior must not be gray, dark, shaded, translucent, or blended with the backdrop.
  • The black ink drawing sits firmly on top of the white fill. Where the subject overlaps the color block, the white-filled object completely hides the color underneath.
  • One solid opaque flat soft-rounded color block behind the drawing, like a halo, chunky oval, generous pill, or rounded-square badge.
  • The color block has no gradient, no watercolor, no texture, no glow, and no transparency. Slightly imperfect hand-drawn edges are fine.
  • The color block supports the drawing; it should not fully contain it.
  • The drawing extends beyond the color block on at least 2-3 sides.
  • The color block occupies roughly 30-40% of the canvas and may be slightly off-center or rotated for editorial flair.
  • The full composition fills roughly 60-75% of the canvas with generous breathing room around it.
  • Pixels outside the line art and color block must be transparent in the final artifact. Do not add any glow, vignette, cast shadow, ambient lighting, gray paper, or background wash.
  • No logo, no text, no letters, no numbers, no UI chrome, no watermark, no border, no third color.

Color Direction

Prefer one accent color from the vm0 avatar/product palette:

  • yellow: #EDC43E
  • teal: #3EB7B8
  • grey: #97918A
  • pink: #FF81B2
  • brown: #E88033
  • wheat: #EDC183
  • light pink: #F3BAB1
  • sienna: #C77242
  • peach: #EBC2AA

Pick one color per image. Use vibrant colors for friendly states and warmer neutral colors for permission, billing, or security states. Use pink sparingly.

Prompt Construction

Turn the user's request into a short concrete metaphor, then generate one polished image in this style.

Good metaphors:

  • no permission: a chunky padlock with a rounded shackle and keyhole, with a small key beside it
  • empty schedule: a simple calendar page with one loose checkmark and a small sparkle
  • empty chat: two rounded speech bubbles overlapping, one with a small sparkle
  • billing plan: a small receipt or stacked card with a coin and checkmark
  • product update: a gift box with lid lifting and a few sparkles
  • retry/loop: two curved arrows chasing each other in a circular refresh loop

Use a concise prompt with these constraints. If the generation tool supports background removal or post-processing, prefer the warm-gray-background workflow:

text
vm0-style vm0 in-app spot illustration of <metaphor>.
Square 1:1 spot illustration on a flat full-canvas warm gray #eeeeee background that will be removed to transparency after generation. Bold confident black brush-pen ink line art with thick chunky decisive strokes, natural hand-drawn wobble, and intentional small contour breaks. The object has an opaque pure white #FFFFFF filled interior, not gray, not dark, not shaded, and not blended with the backdrop. The white-filled object sits on top of a single solid opaque flat soft-rounded <color name> color block using <hex>, like a pill, chunky oval, or rounded-square halo. The color block has no gradient, no watercolor, no texture, no glow, and no transparency. The drawing extends beyond the color block on at least 2-3 sides and fills 60-75% of the canvas. Minimal iconic detail only. No text, no letters, no numbers, no logo, no UI, no border, no shadows, no glow, no vignette, no hatching, no third color.

If direct transparent-background generation is the only available path, keep the same style constraints and additionally require that all pixels outside the drawing and color block are fully transparent. Be strict about no glow/vignette and pure white subject interiors, because direct transparent generation tends to drift there.

Evaluation Checklist

  • The image reads as one simple iconic product metaphor.
  • The line art is bold and hand-drawn, not vector-clean.
  • The object interior is pure white-filled, not transparent, gray, dark, shaded, or backdrop-colored.
  • The color block sits behind the drawing and does not trap it inside.
  • The color block is solid flat color, not gradient/watercolor/textured.
  • The final background is transparent.
  • There is no glow, vignette, cast shadow, gray wash, or background outside the color block.
  • There is no text, letters, numbers, logo, UI chrome, border, watermark, or third color.

Frequently asked questions

What does the Vm0 Illustration AI skill do?

Generate vm0-style vm0 in-app spot illustrations: bold hand-drawn ink line art with white-filled interiors, a soft rounded color backdrop, transparent output, and simple iconic metaphors for product states.

Why use Vm0 Illustration on TypingMind?

Because you install it once and use it with any model. Vm0 Illustration 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 Vm0 Illustration in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vm0-ai/vm0-skills/tree/main/illustration-template/vm0-illustration. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Vm0 Illustration?

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 Vm0 Illustration?

As many as you like. As long as a model supports skills, you can use Vm0 Illustration with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Vm0 Illustration AI skill free?

It is published on GitHub by vm0-ai. 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 👇