// REFERENCE · GENERATIVE AI · CURATED
Your reference for
Generative AI
Concepts, patterns and tools. Bilingual, encyclopedic, developer-oriented. No fluff, no news — just what you need to build.
$/
32 concepts · 5 categories · ● updated 2026-07
$ hub ls --featured
FIG. 01fundamentals
What is an LLM
A language model trained on massive text to predict and generate coherent language — the engine behind ChatGPT, Claude, and Gemini.
read →FIG. 02tools
How to install Claude Code
Step-by-step guide to installing Claude Code on macOS, Linux, and Windows. Covers all installation methods, system requirements, and initial setup.
read →FIG. 03agents
AI Agent Skills
Skills are modular capabilities that an AI agent can invoke to interact with external systems and data.
read →FIG. 04agents
What is the Model Context Protocol (MCP)?
MCP is an open standard that connects AI models to external tools and data sources through a universal protocol.
read →$ hub ls categories/
[dir]fundamentalsThe basics: how models work and why.4 art.[dir]agentsSystems that reason, use tools and act.7 art.[dir]promptingTechniques to communicate with models effectively.5 art.[dir]patternsRecurring architectures in AI systems.6 art.[dir]toolsThe practical stack: frameworks, SDKs and platforms.10 art.