Ian Xiaohei Illustrations: A Codex Skill for Hand-Drawn Editorial AI Visuals

Repositoryhelloianneo/ian-xiaohei-illustrationsTool

This open-source repository provides a Codex Skill designed to guide AI agents in producing 16:9 hand-drawn editorial graphics for Chinese articles and notes. Featuring the recurring character Xiaohei, it translates cognitive insights and workflows into distinct, minimalist illustrations.

Key points

  1. Produces 16:9 graphics characterised by plain white backgrounds, wobbly black line work, generous white space, and sparse colour annotations.
  2. Integrates Xiaohei, a faceless minimalist character who actively performs the core mechanism rather than serving as a decorative mascot.
  3. Structures content workflows by creating shot lists of typically four to eight images per article before individual image generation.
  4. Targets writers producing analytical and methodology content who prefer idiosyncratic sketches over corporate presentation graphics.
  5. Boasts strong community traction with almost 11,000 GitHub stars and over 1,300 forks, showing high maturity.

Why it matters

Standard AI image generation often produces generic, over-rendered stock visuals. This skill demonstrates how structured agent workflows can maintain visual brand consistency and express conceptual metaphors through constrained artistic rules.

Analysis

The repository directly addresses the friction between abstract text and memorable editorial art. By enforcing a strict shot-list planning step and a QA checklist, it discourages repetitive stock compositions. Xiaohei functions as an explanatory tool rather than branding clutter. With extensive usage guidelines, prompt templates, and significant community engagement, the skill is mature and ready for automated content workflows in Codex environments.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • X post:David

    Codex Skill for Hand-Drawn Illustrations and David's Thesis on AI Slop

    David (@dzhng) showcases Ian Neo's open-source Codex skill »ian-xiaohei-illustrations«. Using the tool as an example, he argues that generic AI »slop« is a process issue rather than a model capability flaw, resolvable through structured workflows and strict guidance.

    1.9kbookmarks112.8kviews

    AI & LLMs· Tool

  • X post:Serena 木瓜

    handraw-style: GitHub Skill Compiles 261 Hand-Drawn Styles

    Serena highlighted a GitHub project called handraw-style Skill on X. The repository catalogues 261 hand-drawn artistic styles with a numbered gallery, allowing users to apply specific visual styles by referencing their IDs in prompts.

    1kbookmarks37.5kviews

    AI & LLMs· Resource

  • Repository:cathrynlavery/diagram-design

    Diagram Design: Editorial HTML and SVG Diagrams for AI Coding Agents

    Diagram Design is a skill and template framework for AI agents like Claude Code, Codex, and Pi. It produces 39 editorial diagram types as self-contained HTML and SVG, avoiding common Mermaid clichés and generic AI styling.

    30.2kstarsHTML

    AI & LLMs· Tool

  • Repository:MengTo/Skills

    Agent Skills: Reusable Playbooks for AI Coding Agents

    The GitHub repository MengTo/Skills provides a curated collection of Markdown-based 'agent skills'. It enables designers and builders to guide AI coding agents like Codex, Claude, and Cursor through complex web design, interaction, and 3D rendering tasks.

    6.2kstarsHTML

    AI & LLMs· Resource

  • X post:Trending GitHub Repositories

    diagram-design: Editorial SVG and HTML Diagrams for AI Coding Agents

    The diagram-design repository by Cathryn Lavery introduces a plugin for Claude Code, Codex, and compatible agents that generates 39 editorial-quality diagram types as self-contained HTML and SVG. It aims to eliminate generic Mermaid-style layouts and manual Figma redesigns.

    1.2kbookmarks86.3kviews

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.