A manga-ink illustration style for clear visual explanations with Codex

Manim scenes explaining how LLMs represent and transform arithmetic prompts

Manim scenes explaining vector search, BM25, and hybrid retrieval for RAG

Manim animations explaining superposition in neural networks

ManimGL animation explaining how CLIP encodes text-image pairs into embeddings

Credit-first intent-led HTML artifacts for Claude Code

Calm, consistent, self-contained HTML explainers for dense docs — a Claude Code skill family.

Create validated 3:4 Xiaohongshu knowledge cards with editorial HTML and slot-matched AI illustrations.