molearn

Use when adding a new open-source project to the documentation site for deep source code analysis, or when generating structured zh-TW documentation covering architecture, features, controllers, APIs, and integrations from a real codebase. Model-agnostic — works with any AI (Cursor, GitHub Copilot, Claude, internal LLMs, etc.).

Use when the user wants to create any technical diagram - architecture, data flow, flowchart, sequence, agent/memory, or concept map - and export as SVG+PNG. Trigger on: "画图" "帮我画" "生成图" "做个图" "架构图" "流程图" "可视化一下" "出图" "generate diagram" "draw diagram" "visualize" or any system/flow description the user wants illustrated.

Complete blueprint for scaffolding the Kubernetes learning documentation site from scratch. Contains the full design system, all component source code, directory structure, and deployment setup. Any AI reading this file should be able to produce an identical site.

Use when generating interactive team quiz questions from existing project documentation. Produces quiz.json format for the React QuizQuestion component (zh-TW, 4-choice, with explanation). Supports automatic topic decomposition based on project complexity. Model-agnostic — works with any AI tool.