- Home
- Skills
- Writing & Content
- Ian Xiaohei Illustrations
More screenshots
Works with the AI Agents you already use
Ian Xiaohei Illustrations
Weird, clean, hand-drawn Xiaohei illustrations for English articles, generated with Gemini.
$5
/moSubscription · cancel anytime
Secure checkout via Stripe
- Always the latest version
- Delivered live to your agent via MCP
- Cancel anytime, access ends at period end
Ian Xiaohei Illustrations
Example session with this skill installed
Here's my post on why AI handoffs fail. Generate 3 Xiaohei illustrations for it.
- Read your context and instructions
- Compiled the ian xiaohei illustrations
A 3-row spec table (placement, core idea, structure type, Xiaohei action, labels), then three 16:9 images saved as assets/why-ai-handoffs-fail-illustrations/01-...png to 03-...png, with a QA manifest marking aspect ratio, white background, Xiaohei core action, label count, no title, and no old-case reuse for each.
Subscription · always the latest version
- Secure checkout via Stripe
- Cancel anytime
- Delivered live via MCP
About this skill
Turns an article's key ideas into 16:9 hand-drawn explainer illustrations: pure white background, black wobbly line art, sparse red/orange/blue handwritten English labels, and Xiaohei, a deadpan black creature who performs the core action in every image.
The skill reads your article, picks the cognitive anchor points worth drawing, writes a compact shot list, then generates one image at a time with a Gemini image model ("Nano Banana") through a bundled stdlib-only Python script. It runs a QA checklist on every image (no PPT look, no top-left titles, Xiaohei not decorative, enough white space) and saves slugged, numbered files. No API key? It falls back to drawing the illustration as inline SVG.
Four modes: plan only (shot list), generate, edit (remove titles, fix garbled text, make Xiaohei more central), and save.
Credit. Ian Xiaohei Illustrations was created by Ian (helloianneo/ian-xiaohei-illustrations, ianneo.xyz). Xiaohei is part of Ian's visual language, and the example images are Ian's. This listing is an English adaptation, via the tojileon/ian-xiaohei-illustrations-en translation, packaged for Claude Code with a Gemini image script. MIT licensed; source at zasmail/xiaohei-illustration-skill.
Image models sometimes garble handwritten text; use edit passes, and for stubborn labels delete and re-add rather than respell. Gemini 3.x models return JPEG, so the file extension follows the actual format. Not for generic, commercial, slide, or children's illustration.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 7 days ago
Requires
Permissions
Allowed Hosts
File Scopes
The Gemini key is read by the script from GEMINI_API_KEY or Bitwarden and never enters the AI's context. The Bitwarden lookup runs `bw list items --search gemini` only when GEMINI_API_KEY is unset.