interactive-explainer

生成美观自包含单文件HTML工件的技能，13种模式、五维评审、DevLoop迭代 |A skill for generating beautiful, self-contained, single-file HTML artifacts. 13 patterns, 5-dimension critique, DevLoop iteration.

Interactive explainer: BDH's attention has no softmax, so it is exactly a Hebbian synaptic memory — one fixed-size matrix written once per token. Run both forms, watch them agree to 1e-16, then break it with one toggle. DataForge 2026, Pathway track.

Grok Bot 头像动画引擎的逆向解剖：可交互讲解页 + 动画编辑器（程序化 SVG / 贝塞尔 clip / 弹簧 / 球面眼睛），0 依赖 0 构建 · Reverse-engineered anatomy of the GrokBot avatar animation engine — interactive explainer + editor, zero-dependency procedural SVG

Multi-audience interactive explainers (JEPA & world models, orbital mechanics, quantum computing, elasticity, electromagnetism) + the Claude Code skill that generates them

Language as lossy compression of thought: an interactive explainer, in a single self-contained HTML file, on which kinds of thought survive being put into words.

The Atlas is a knowledge base of language models with information on how they work as well as agentic loops and loop engineering!!

Seven kinds of website, one AI agent. A WebMCP-powered interactive explainer where your agent proves what agents do to the web, room by room.

Interactive explainers on robot data: LeRobot datasets, ROS bags, MCAP, and which format to use

Following Summer: a three-part visualisation of bird migration. A phylogenetic canopy, a flyway atlas, and a WebGL globe lit by a moving day/night terminator.

The complete ASD-STE100 Simplified Technical English skill for Claude Code, Codex, and LLMs. Features Andrej Karpathy's Ladder of Understanding (STE-100, diagrams, interactive HTML, 3b1b video), linter, and prompt compiler.

Every way from a corporate network into AWS, drawn as a road map: VPN, Direct Connect, SD-WAN, Transit Gateway, Cloud WAN, PrivateLink, hybrid DNS, user access. EN/JA.

Interactive, in-browser explainer of Neural Architecture Generation (NAG): from architecture search to architecture generation.

Interactive explainer of real LLM inference: KV cache, roofline, batching, paging, FlashAttention, speculative decoding, quantisation, parallelism and serving metrics. Companion to the Transformer Decoder Explainer.

Anatomy of an AI Operator OS: an interactive explainer of a personal multi-agent AI operator OS, shown in motion on a synthetic timeline.