A Codex skill that analyzes Chinese articles to extract cognitive anchors and generate 16:9 hand-drawn illustrations featuring the 'Xiaohei' IP. It requires OpenAI Codex and an external AI image model to operate.
Project overview
It focuses on extracting specific cognitive actions or metaphors from text and translating them into black line-art illustrations with concise Chinese annotations, rather than generating generic photos or infographics.
Creators and general users seeking to visualize key cognitive points from Chinese articles or notes as hand-drawn illustrations.
Key capabilities
Analyzes Chinese articles, posts, blogs, or Notion content to extract key judgments, processes, structures, states, or metaphors suitable for visualization.
Generates a shot list of 4-8 illustrations per article detailing theme, core meaning, structure type, character action, and suggested Chinese annotations.
Prompts the image model to produce 16:9 horizontal illustrations using a pure white background, black hand-drawn line art, and sparse red, orange, and blue Chinese annotations.
Edits generated illustrations to remove incorrect text or unwanted titles while keeping other content unchanged.
Limitations and risks
The skill does not output editable vector files, SVGs, HTML, or Canvas files.
It does not produce PPTX, PDF, or Keynote files.
AI image models may produce typos, hallucinated labels, style drift, or unwanted titles in the generated images.
Getting started
Setup is rated as easy and does not require coding. Users clone the repository, copy the 'ian-xiaohei-illustrations' directory into the Codex skills folder, and invoke the skill via the $ian-xiaohei-illustrations command in Codex.