Coloring Page example output generated by Doodle AI
The photo used as input for Coloring Page from this photo
A real run of this skill. The input is a synthetic portrait, not a customer photo.
Ready to use

Coloring Page

Your photo, redrawn as a printable colouring page

Use this skill
Your photo
Required
Output
Single square 1:1
Category
freeform
Cost
1 credit
  • coloring
  • line art
  • printable
  • kids

What it does

What you get back

Redraws the person or pet in your photo as a real colouring-book page: bold confident black outlines, every shape fully closed, generous white space inside so colour never leaks, and a plain white background. No colour, no shading, no gradients — just neat line art you print out and colour in with crayons, pencils, or markers. Still recognisably the subject in the photo.

When the agent picks it

Use when the user wants a printable colouring page of themselves, a friend, a kid, or a pet from a photo — phrases like "colouring page", "coloring book page", "line art to colour in", "black and white outline of me", "turn my photo into a page I can print and colour", or "colouring sheet". The output is uncoloured line art, not a finished coloured drawing. For a fully coloured childlike crayon portrait, use crayon-self instead. For a polished coloured doodle avatar, use doodle-avatar.

The full skill file

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

src/mastra/skills/coloring-page/SKILL.md

Coloring Page

Turn one uploaded photo into a clean, printable colouring page — bold uncoloured line art on plain white paper, made to be printed and coloured in by hand. The output is an outline drawing only: crisp black lines, every region left empty and ready to fill.

When this is the right skill

Pick this skill when the user wants line art they can print and colour in themselves — a colouring-book page of a person, a child, a friend, or a pet from their photo. The intent is an uncoloured sheet: the fun is in colouring it in later, so the model must leave every shape empty.

Choose a different skill instead when the user asks for:

  • a fully coloured childlike crayon drawing → crayon-self
  • a polished hand-drawn doodle avatar with colour → doodle-avatar
  • a multi-panel expression grid → doodle-collage
  • full-body action poses → full-body-collage
  • die-cut stickers → sticker-pack
  • mood-captioned panels → mood-captions
  • a greeting card → gift
  • artwork with no photo → surprise-me

If the user wants the drawing already coloured, this is the wrong skill — send them to crayon-self or doodle-avatar.

What to draw

The reference is a page from a children’s colouring book: bold black outlines on white, nothing filled in. It should still read clearly as the subject in the photo, just reduced to clean colourable line work.

Keep these recognisability anchors from the photo:

  • overall pose, silhouette, and proportions
  • hairstyle shape, glasses, and facial hair
  • one or two signature features (a hat, freckles as tiny outlined dots, a distinctive item of clothing)

Redraw the photo as printable line art:

  • bold, confident, fully closed outlines — every shape completely bounded so colour can’t leak between regions
  • even, consistent line weight like a printed colouring book, slightly thicker on the outer silhouette and finer for interior detail
  • generous white space inside every shape — no fill of any kind
  • busy areas simplified into a few large, clearly separated regions rather than many tiny ones
  • shadows and shading reduced to a handful of optional contour lines, never tone
  • a plain empty white background, no scene or border unless a theme calls for one simple outlined prop

The single hardest constraint: no colour and no fill anywhere. If any region ends up shaded, tinted, or filled in, the page is unusable — the whole point is that the person colours it in themselves.

How to run it

  1. Confirm a photo is attached. If none is, ask the user to attach one — do not call the tool without a photo.
  2. Call generateDoodle with skill: "coloring" and the uploaded photo as imageUrl.
  3. If the user also attached a style reference, pass it as refImageUrl.
  4. Report the result briefly. The app displays the image itself.

Following up

After a successful generation, offer to print it at page size, or suggest crayon-self if the user would rather see a colourful childlike version instead of colouring one in themselves.

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.