Surprise Me example output generated by Doodle AI
A real run of this skill. The input is a synthetic portrait, not a customer photo.
Ready to use

Surprise Me

No photo needed — a random fictional doodle character

Use this skill
Your photo
Not needed
Output
Single square 1:1
Category
freeform
Cost
1 credit
  • freeform
  • no photo
  • random

What it does

What you get back

For when you do not have (or do not want to use) a photo. Picks a random fictional character description — hairstyle, expression, accessories — and draws it in the same naive doodle style as Doodle Avatar.

When the agent picks it

Use when the user has no photo and does not want to upload one, or explicitly says "surprise me" / "make something up" / "random character". This is the only skill that needs no photo.

The full skill file

Every skill is one SKILL.md — this is the exact file the agent reads.

src/mastra/skills/surprise-me/SKILL.md

Surprise Me

Draw a fully fictional naive doodle fashion-chibi character. No photo required — this is the only skill that works with nothing attached.

When this is the right skill

Pick this skill when:

  • the user explicitly asks to be surprised, or for something random
  • the user describes a character in words instead of attaching a photo
  • the user says they have no photo, or would rather not upload one

It is also the right thing to offer whenever a photo-based skill is blocked because nothing is attached. Suggest it rather than leaving the user stuck.

What to draw

If the user gave any description at all — hair, vibe, outfit, accessories, personality, occupation — build the character from it and follow it closely. If they gave nothing, invent something fun yourself; see references/character-ideas.md for seeds worth combining.

Style notes for this skill specifically:

  • bold graphic hair shapes
  • rough marker or dry-brush edges
  • restrained, watercolor-like color rather than fully flat fills
  • clean white or warm-white background
  • fashion-forward, deliberately naive brushwork with playful asymmetry

No photorealism, no 3D, no heavy shading. The shared rules in ../doodle-avatar/references/style-guide.md still apply.

How to run it

  1. Never ask for a photo — the point of this skill is that none is needed.
  2. Call generateDoodle with skill: "surprise". Pass the user’s own words as description when they gave any; omit it to get a random one.
  3. Never pass imageUrl for this skill. There is no subject photo, and the tool ignores it.
  4. Report the result briefly without repeating the URL.

Following up

Invite a twist on the same character — a different palette, a new outfit, a change of mood — or point out that attaching a real photo unlocks the likeness-preserving skills.

More skills

Browse all 40
Hand-drawn doodle avatar of a person with long wavy hair and round glasses
SAMPLE AVATAR
Nova hand-drawn character
Doodle AI

Make something
worth keeping.

Sign in to create, save, and revisit your doodles across devices.

Starter credits included

Drop a note

It lands on the roadmap board for the team to see.

Credits

Let's sort this out directly

Doodle AI is in its testing phase, so checkout isn't switched on yet. Message me and I'll add credits to your account by hand — usually within a few hours.

No payment details are collected anywhere in this flow.

Settings Your profile

Give your team a name

Anyone you invite will see this name.

Join a team

Paste the invite link a teammate sent you.

Invite your teammates

Choose a role, then copy the link and send it yourself.