An agent tutorial website for applying to agent R&D positions at major tech companies, covering technical roadmaps and common interview questions
zero2Agent is a tutorial repository that teaches software developers how to build AI agents, covering core concepts, model APIs, tools, memory, frameworks, implementation, and complete projects. It is intended for programmers learning agent engineering and for candidates preparing for agent-related technical interviews.
Latest release v1.2.0 — zero2Agent Greenbook v1.2.0 · 26 Aug 2026
9 files for Claude Code, Codex and OpenCode: chinese-quotes-fix, classify-interview-questions, content-review, drawio-skill and 5 more — 1,535 tokens loaded in every session.
AGENTS.md A 1,535 tok .agents/skills/chinese-quotes-fix/SKILL.md A 32 tok .agents/skills/classify-interview-questions/SKILL.md A 109 tok .agents/skills/content-review/SKILL.md A 112 tok .agents/skills/drawio-skill/SKILL.md A 68 tok .agents/skills/mermaid-check/SKILL.md B 83 tok .agents/skills/new-article/SKILL.md A 124 tok .agents/skills/new-module/SKILL.md A 95 tok .agents/skills/scrape-nowcoder/SKILL.md A 92 tok These files are ranxi2001/zero2Agent's own configuration — they tell Claude Code, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.