illo: mascot illustrations for articles
illo
A skill that draws original print-style illustrations: one idea per frame, played out by a recurring mascot
- 412 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The illo.py script runs on your machine and calls the network to generate pictures
- An OpenRouter key is billed per image, while Codex and Grok spend subscription quota
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/illoDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The illo.py script runs on your machine and calls the network to generate pictures
- An OpenRouter key is billed per image, while Codex and Grok spend subscription quota
This is third-party code. Review the repository files before installing.
What it does
illo turns an idea or an article into an illustration in the style of a print magazine. One picture says one thing: a judgment, a flow or a before and after. A recurring mascot plays the idea out as the hero of the frame. By default it is Blot, a deadpan ink drop in risograph print. There are four modes. A regular scene is the default. An explainer draws a diagram by hand: labeled stages, a fan-out, a timeline, a loop or a stack. A mini-comic fits a story into two to four panels in one image. A cutout gives the mascot in the pose you need on a transparent PNG with no text or background. A "surprise me" mode lets the skill pick the topic itself. There are seventeen looks, from grainy risograph to blueprint, woodcut and clay. The palette can come from a preset, from your own file or be derived from one brand color. A built-in character builder interviews you and prepares candidates on a model sheet, and you pick your own mascot from them.
Who it is for. For authors of blogs, newsletters and documentation who need recognizable illustrations for their texts without a separate illustrator.
Good fit when
- An article needs a cover or an illustration where one idea reads in a second
- You need a process diagram as a hand-drawn chart with stages and arrows, for example how a newsletter issue ships
- You want a series of pictures with the same character in one style
- Layout needs a mascot on a transparent background to overlay on your own design
- The palette should be built from your site's colors so the pictures fit the blog right away
Not a fit when
- You need a photo of a real place or person: the skill makes illustrations, and only one look, with toy bricks, is photorealistic
- You need an infographic with a lot of data and small text: labels on the picture are few and short
- You want a generic image generator for any request: the skill fires only on a direct call
- You are on Windows or WSL and count on the Codex engine: it is not supported there
Example request
illo: draw how we replatform with zero downtime, for a blog post.Limitations
Images are generated by a separate engine, so you need one of three options. A Codex or Grok subscription spends its own quota with no per-image charge, and an OpenRouter key is billed per image. Codex relies on OpenAI services, which are unavailable from Russia. The Codex engine does not work on Windows or WSL. Grok has no transparent cutouts, so for them the skill falls back to Codex. It moves to paid OpenRouter only with the --allow-paid-fallback flag.
Python 3 with only the standard library and network access are required. The skill is meant for macOS and Linux.
How to disable. In Claude Code disable the plugin through /plugin; in other agents remove the plugin or the illo folder with the agent's own tools. Your custom styles live separately in ~/.config/illo/styles and can be kept or deleted.
FAQ
How do I install illo in Claude Code?
Run /plugin marketplace add tmchow/illo-skill, then /plugin install illo@illo-skill. Update with claude plugin update illo or marketplace auto-update. The README has its own commands for Codex, Gemini CLI, Copilot, Hermes and OpenClaw, and a fallback for any agent: npx skills add tmchow/illo-skill --skill illo.
How do I call illo?
Write /illo and an idea, for example /illo we replatform with zero downtime, or start the phrase with the word illo. The skill deliberately ignores generic requests like "draw this" or "make an image".
Do I need a paid API for the pictures?
No, if you have a Codex or Grok subscription: the skill calls them through your command line with no key and spends subscription quota. An OpenRouter key is paid, and if Codex or Grok fails the skill does not switch to it on its own: that needs the --allow-paid-fallback flag.
Can I create my own character?
Yes. The character builder offers candidates on a model sheet, you pick one, and it is installed as a pack. The repository ships more than thirty characters, and you can add your own style file to ~/.config/illo/styles.
How do I get pictures in my site's colors?
Copy the site colors into a palette: background to paper, text to ink, link color to accent. One line in the palettes file ties a palette to a destination: blog uses the notes palette, and pictures for the blog come out in the right colors right away.
Discussion
No questions or reviews yet.
Related
SkillsA skill that generates extremely simple, cute mascot characters for logos: rounded forms, three colors, lower-corner composition
A skill that turns your photo or description into a hand-drawn character and uses it for diagrams, knowledge cards and slides
A skill that turns Chinese story copy or a set of ordered images into a vertical hand-drawn animation, a silent diary-comic picture track
A Codex skill that redraws your photo as a watercolor illustration on white paper, with wide margins and a handwritten caption
A Codex skill that turns a Chinese article into a series of hand-drawn 16:9 illustrations on white background with the Xiaohei character
A skill that assembles ready image prompts in hand-drawn styles from a set of tested recipes: kids drawing, minimal line, crayon, Ghibli look and more
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Repository stars | Main difference |
|---|---|---|---|
| illo: mascot illustrations for articles (this entry) | no | 412 | |
| Smart Illustrator | no | 569 | picks spots for illustrations in an article and draws pictures, diagrams and covers without a recurring character |
| Anidoodle | no | 1,160 | draws illustrations and animation in code, while illo makes print-style pictures through image generation |
README in short
The README shows sample results and phrases for calling the skill, then an install table for ten platforms: Claude Code, Codex, Grok CLI and Grok Bot, Gemini CLI, Copilot, Hermes, OpenClaw, Cursor and an npx fallback. Details about engines, models and cost are moved to the skill's own README, and the illo-skill.com site holds live examples and character packs.
README badge
Original SKILL.md
---
name: illo
description: >-
Creates original editorial illustrations where a recurring mascot
character performs the idea — one caught scene by default, a hand-built
explainer diagram (labeled stages, a fan-out, timeline, loop, or stack) when the
structure itself is the point, or a transparent character cutout
(pose-only compositing asset, no scene or text) — in one of seventeen bundled
looks (sixteen print, plus a photoreal toy-brick set). Also handles
"surprise me" / "random" (optionally scoped to a focus or character): rolls
provenance, builds three saying candidates, picks via interactive choice or
auto-pick-best (`--autopick`), and renders one image. Triggers only when
the skill is directly invoked or "illo" is requested; never on generic
illustrate / draw / make-an-image requests.
# x-release-please-start-version
version: 0.37.0
# x-release-please-end
argument-hint: "[idea or article URL] | build a character | install <character> | surprise me [focus] [--autopick] [using character]"
author: Trevin Chow
license: MIT
metadata:
hermes:
tags: [illustration, riso, image-generation, editorial, mascot, codex, grok, openrouter, muse]
category: creative
requires_toolsets: [terminal]
openclaw:
emoji: "🎨"
homepage: https://illo-skill.com
os: [macos, linux]
requires:
bins: [python3]
---
# Illo
Make original, distinctive editorial illustrations for written content. One
image explains one idea: a key judgment, a flow, a before/after, a trap, a
loop. A **recurring mascot** is the one performing the idea in every scene —
the subject, never decoration. When one idea advances through stages, it can
be a **mini-comic**: 2–4 panels inside a single image. And when the idea is
itself a traceable structure — a pipeline, labeled stages, a fan-out, a
timeline, a loop — it can be an **explainer**: the same mascot and look
drawing the structure as a hand-built sketch-diagram with arrows and
callouts (`references/composition.md`, "Two registers" and "Pick the
diagram type"; editorial scene is always the default). A named pipeline