content / skill

Ian Xiaohei Illustrations

A Codex skill for making 16:9, white-background, hand-drawn illustrations with a few red, orange and blue Chinese annotations for Chinese articles.

At a glance

Purpose
A Codex skill for making 16:9, white-background, hand-drawn illustrations with a few red, orange and blue Chinese annotations for Chinese articles.
Runs in
Local agent with shell
Operating systems
Not stated
Needs
Runtime: Not stated; Needs internet: Not stated; Needs accounts or API keys beyond your agent: Not stated
Files and data
Reads files: Yes; Writes files: Yes; Sends data to other services: Not stated
Tool type
Skill
Delivery
From GitHub
Version
Latest on the main branch
Access
Code on GitHub
Compatibility
According to the README, this is a Codex skill, installed into the Codex skills folder (CODEX_HOME or $HOME/.codex) and used in Codex with a prompt that names $ian-xiaohei-illustrations. The README gives install steps for no other agent.
External costs
The repository is MIT-licensed and states no pricing. Your coding agent, and the image model it calls, may charge for usage.
Permissions
The skill acts through your coding agent with the access you give it. The README's installation route clones the repository and copies its skill subfolder into ${CODEX_HOME:-$HOME/.codex}/skills. The README says the workflow reads supplied articles, Markdown, Notion content, screenshots or topics, calls an image model for each image, and saves PNG files under assets/<article-slug>-illustrations/ in the workspace.
Usage terms
MIT License, as stated in the repository. See its LICENSE file for the exact terms.

Code on GitHub

helloianneo/ian-xiaohei-illustrations

MIT

12,540 stars1,439 forksLast pushed 24 Sept 2026 UTC

中文小黑怪诞正文配图生成 Skill | 16:9 白底手绘 | 少量红橙蓝批注 | Codex Skill

Topics: ai-agent chinese codex-skill handdrawn illustration image-generation xiaohei

Public GitHub data fetched · 0 days old

Skill folders in this repository (1)

Folders that contain a SKILL.md file, from GitHub's file list on .

View on GitHub ↗

What it does

Ian Xiaohei Illustrations is a Codex skill for Chinese article illustrations. The Chinese-language README describes instructions for illustrating articles, posts, blogs, Notion documents and methodology content. The README states a goal of turning an article's judgment, process, structure, state or metaphor into a 16:9 hand-drawn explanatory image.

The README describes a default style with a white background, thin black hand-drawn lines, white space and a few red, orange and blue handwritten Chinese annotations. The README says Xiaohei, a solid black figure with white dot eyes and thin legs, must participate in the central action. The README says the skill is not a general illustration prompt or a slide infographic template.

The README describes a default shot list of 4 to 8 images, with a topic, core meaning, structure type, Xiaohei action and suggested Chinese labels for each image, followed by PNG files saved under assets/<article-slug>-illustrations/. The README excludes PPTX, PDF, Keynote, editable images in SVG, HTML or Canvas, commercial posters or cover key visuals, and text-heavy infographics from the default output.

Who it is for

Writers and content makers who use Codex and need hand-drawn illustrations for Chinese articles, posts, blogs or Notion documents.

Example tasks

Plan about five illustrations for a Chinese article as a shot list, without generating images.
Generate four in-article illustrations for a Chinese article.
Draw one illustration for a single concept.
Remove a stray title from a generated image and keep the rest unchanged.

Getting started

The README says to clone the repository, then copy the ian-xiaohei-illustrations subfolder into the Codex skills folder with mkdir -p "${CODEX_HOME:-$HOME/.codex}/skills" and cp -R ./ian-xiaohei-illustrations "${CODEX_HOME:-$HOME/.codex}/skills/". It says only that subfolder needs to be installed. The README's Codex examples begin with Use $ian-xiaohei-illustrations followed by the request. The README has the exact commands.

Limitations

The README presents it as a Codex skill and gives install steps for Codex only. It is written for Chinese-language articles, and the README is in Chinese. The README says each image is generated by calling an image model, and it does not name one. It says the skill is not suited to commercial illustration, brand key visuals, polished flat illustration, traditional slide infographics, complex architecture diagrams or flowcharts, children's cartoon, cute-character or sticker styles, long text packed into one image, or editable vector sources. It warns that image models can produce typos, invented labels, style drift or extra titles, so each image needs checking, and that shorter Chinese text is more stable. The repository can change at any time; check its README before you install.

Data practices

The README says the workflow reads articles, Markdown, Notion content, screenshots or supplied topics, calls an image model for each image, and saves PNG files in the workspace. It does not specify model providers, what data those providers receive, or retention practices.

Community experience

Not rated yet

Sign in to share your experience.

Comments 0

No comments yet.

Sign in to comment

Report a listing concern