By tmchow
Generate original editorial illustrations with a recurring mascot character — one scene, an explainer diagram, or a transparent cutout — in fifteen bundled looks, using a built-in character builder and color palettes derived from your site. Ships a dual-backend image engine: free generation via gpt-image-2 when available, otherwise OpenRouter.
Generate original print-style editorial illustrations for articles and blogs, starring a recurring mascot that performs each idea. Each character pack carries one of ten bundled looks (riso, blueprint, woodcut, pixel, clay, manila, chalk, phosphor, enamel, gouache) or a custom style — default Blot (a deadpan ink-drop), or design your own with the built-in character builder. One-metaphor-per-image scenes with named + custom + derived palettes and reference-image character consistency. Renders through two backends: your Codex CLI (gpt-image-2 on your Codex subscription — free for subscribers, no API key) when one is installed and logged in, or OpenRouter (model-selectable: Grok Imagine, Nano Banana 2/Pro, GPT-5.4 Image 2, …) as the universal fallback.
Hand it "we replatform with zero downtime" and you get the bridge being rebuilt under live traffic:

🌐 illo-skill.com — live examples, the character gallery, and copy-paste installs.
The skill itself lives in skills/illo/ — its
README is the full developer reference
(prerequisites, API-key setup, models & cost, everything below in detail).
Same idea, different voice — four of the ten bundled looks:
![]() | ![]() |
| riso — the house default | clay — stop-motion plasticine |
![]() | ![]() |
| phosphor — CRT trace on glass | blueprint — draftsman linework |
Quick install — any agent. One command for Claude Code, Cursor, Codex,
Copilot, Gemini CLI, and the ~70 other runtimes the
skills CLI supports (update later with
npx skills update):
npx skills add tmchow/illo-skill --skill illo
Platform-native installs. The repo also ships a plugin/extension manifest for each major runtime, so you can install through your platform's own package manager and get managed updates:
| Platform | Install | Update |
|---|---|---|
| Claude Code | /plugin marketplace add tmchow/illo-skill then /plugin install illo@illo-skill | claude plugin update illo, or enable marketplace auto-update |
| Codex | codex plugin marketplace add tmchow/illo-skill then codex plugin add illo@illo-skill | codex plugin marketplace upgrade |
| Gemini CLI | gemini extensions install https://github.com/tmchow/illo-skill | gemini extensions update illo |
| Copilot / GitHub CLI | gh skill install tmchow/illo-skill illo (cross-agent via --agent) | gh skill update illo |
| Cursor | npx skills add tmchow/illo-skill --skill illo (Cursor Marketplace listing pending review) | re-run the installer |
| Hermes | hermes skills install tmchow/illo-skill/illo | hermes skills update illo |
| OpenClaw | openclaw skills install illo | reinstall with the same command |
Every lane installs the same skill; releases are tagged v<version> and
the version in every manifest is kept in lockstep with
skills/illo/SKILL.md by CI.
The skill sits in skills/illo/, following the layout of the canonical
skill repos (anthropics/skills, openai/skills): a top-level skills/
folder, one directory per skill. It is deliberately not at the repo root —
installers copy the entire skill directory verbatim, so the skill dir holds
only what every install should ship. Docs-only images live in
_assets/illo/ (linked by raw URL), and repo meta stays at the root —
including the plugin manifests (.claude-plugin/, .codex-plugin/,
.cursor-plugin/, gemini-extension.json) that make the repo installable
as a native plugin on each platform.
MIT © Trevin Chow — see LICENSE and
skills/illo/NOTICE for attribution of the Blot character and
bundled artwork.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Skill for generating and iterating on images with consistent style and subject identity using the image-sprout CLI.
Iterative development workflows. 13 agents, 12 skills for brainstorming, research, design exploration, tech planning, multi-agent reviews, TDD execution, and PR feedback resolution.
npx claudepluginhub tmchow/illo-skill --plugin illoMulti-channel visual production skill with brand-token enforcement and 8:1 contrast minimum.
Design skills: UI/UX, brand identity, visual assets
Create branded visual content (presentations, carousels, infographics, HTML pages) with Aaker personality-driven design, style recommendation engine, visual components, 26 visual styles, design systems, and Presentation Zen principles
Use this agent when creating visual narratives, designing infographics, building presentations, or communicating complex ideas through imagery. This agent specializes in transforming data and concepts into compelling visual stories that engage users and stakeholders. Examples:\n\n<example>\nContext: Creating app onboarding illustrations
Visual creative expert — search inspiration, enhance prompts, and generate AI images with intelligent workflow orchestration
OpenAI GPT Image 2 prompt gallery, image prompt library, agentic skill + CLI. Gallery-first prompt patterns, reference-image editing workflows, and a packaged CLI for skill-capable agent runtimes.