Ian Xiaohei Illustrations skill
A Codex skill that turns a Chinese article into a series of hand-drawn 16:9 illustrations on white background with the Xiaohei character
- 13,183 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Reads article files and saves generated PNGs into the workspace
- Calls an external image model over the network
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/ian-xiaohei-illustrationsDetects 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.
- Reads article files and saves generated PNGs into the workspace
- Calls an external image model over the network
This is third-party code. Review the repository files before installing.
What it does
The skill gives a Codex agent a method for illustrating Chinese articles in one recognizable style. It reads the text, picks the key ideas and turns, and builds a shot list of four to eight images with the placement, topic and structure of each. For every image it chooses a composition type, invents a simple physical metaphor and generates a separate PNG with the built-in image model. The style is fixed: white background, black hand-drawn lines, a few red, orange and blue handwritten notes, and the Xiaohei character taking part in the core action. It ships references for style, the character, composition, a prompt template and a QA checklist.
Who it is for. For authors and editors of Chinese content who need article illustrations in one consistent hand-drawn style.
Good fit when
- You need illustrations for a Chinese article in one recognizable style
- You need a shot list for the text: where each image goes and what it shows
- You want to turn an abstract point into a concrete visual metaphor
Not a fit when
- You need text and captions in a language other than Chinese
- You need commercial illustration, a key visual, PPT infographics or an editable vector
Example request
Use $ian-xiaohei-illustrations, build a shot list of 5 illustrations for this Chinese articleLimitations
The skill and the on-image captions are built for Chinese language and Chinese articles. Generation needs Codex with a built-in image model that runs through OpenAI and is not reachable from Russia without a VPN. The output is raster PNG, not an editable vector. The image model may produce typos, extra titles or style drift, so a checklist review is needed.
How to disable. Remove the ian-xiaohei-illustrations folder from the Codex skills directory, usually ~/.codex/skills/.
FAQ
What language are the on-image captions?
The captions are Chinese and the skill targets Chinese texts. The shorter the text in a frame, the more stable the result.
Can it plan without generating?
Yes. You can ask for only a shot list with topics and structure, without running generation.
Discussion
No questions or reviews yet.
Related
SkillsA Codex skill that draws 16:9 scenes with the Xiaohei character among real objects for Chinese articles
A Codex skill that turns articles and notes into a set of page images in a Chinese handdrawn technical explanation style
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 photograph into a vertical composition with an abstract memory panel and an English title
A skill for Codex and Claude Code that makes medical comics, illustrations and schematics backed by traceable anatomy sources.
README in short
The README describes a Codex skill that makes hand-drawn 16:9 illustrations on white background for Chinese articles, with the Xiaohei character. The skill first extracts the meaning anchors in the text, then proposes a shot list and generates one PNG per frame with the built-in image model. It installs by copying the nested folder into the Codex skills directory and is invoked with Use $ian-xiaohei-illustrations. It lists supported flows: planning only, generation, one image per concept and removing stray titles. Examples and references for style, character and composition are in the repository, MIT licensed.
README badge
Original SKILL.md
--- name: ian-xiaohei-illustrations description: 生成 Ian 风格的中文正文配图。用于用户要求为中文文章、帖子、博客、Notion 文档、工作流文档、方法论、流程、结构、状态、隐喻或观点生成怪诞、小黑、手绘、正文配图、文章插图、配图建议、shot list、去标题/改图等任务；默认使用小黑 IP、纯白手绘、少量红橙蓝批注、简洁清爽但天马行空的视觉风格。 --- # Ian 小黑怪诞正文配图 ## 核心定位 为中文文章设计和生成 16:9 横版正文配图。目标不是做商业插画、PPT 信息图或可爱卡通，而是把文章里的关键判断、流程、结构、状态或隐喻，变成一张清爽、怪诞、有创意、可读但不说明书的手绘解释图。 默认视觉 IP 是小黑：黑色实心、白点眼、细腿、空表情，认真做一件荒诞但成立的事。小黑必须参与画面的核心动作，不能只是站在旁边当装饰。 ## 先读这些参考 按任务需要读取，不要一次塞满上下文： - references/style-dna.md：风格 DNA、颜色、文字、禁忌。 - references/xiaohei-ip.md：小黑 IP 的形象、性格、动作库和禁忌。 - references/composition-patterns.md：结构类型、原创隐喻方法和反复刻规则。 - references/prompt-template.md：单张生图提示词模板。 - references/qa-checklist.md：生成后检查和迭代规则。 - assets/examples/：只作低频视觉校准，不进入默认生成路径。不要照抄这些案例的构图、物件或标注。