datawhalechina/agent-skills-with-anthropic

本项目围绕吴恩达老师在DeepLearning.AI出品的agent-skills-with-anthropic系列课程，为学习者打造中文翻译与知识整理教程。项目提供课程内容翻译、知识点梳理和示例代码解读等内容，欢迎大家Star!

What it solves

This project removes language barriers for Chinese-speaking learners who want to study the DeepLearning.AI course "Agent Skills with Anthropic." It provides high-quality translations and structured study materials to help users understand how to build and use AI agent skills effectively.

How it works

The project serves as a comprehensive Chinese-language companion to the official course. It breaks down the curriculum into ten modules, offering translated content, organized knowledge summaries, and detailed explanations of the provided example code. It covers topics ranging from the fundamental concepts of agent skills to practical implementation using the Claude API, Claude Code, and the Claude Agent SDK.

Who it’s for

This resource is designed for students, researchers, and developers who are interested in AI agents and Claude technology but prefer learning in Chinese. It is ideal for those who want to master the practical application of AI skills but may face challenges with English-language technical documentation.

Highlights

  • Complete Chinese translation of the official course content
  • Systematic breakdown of core concepts for easier comprehension
  • In-depth code walkthroughs to facilitate hands-on practice
  • Open-source collaborative model that encourages community contributions
  • Regularly updated to remain synchronized with the official course material

Related

  • Project
    six2dez/burp-ai-agent

    A Burp Suite extension that integrates AI models and MCP tools to automate vulnerability scanning and HTTP traffic analysis for security researchers.

  • Project
    langwatch/better-agents

    A CLI tool and set of standards for building production-ready AI agents with standardized project structures, prompt versioning, and integrated testing.

  • Project
    bcurts/agentchattr

    agentchattr is a local chat server that lets AI coding agents (Claude, Codex, Gemini, and others) and humans coordinate in a shared chat room with channels and @mention wake-ups, so agents can respond and collaborate with each other hands-free — no copy-pasting between terminals.

  • Project
    RunanywhereAI/wally

    Wally is a command-line tool that launches coding agents (like OpenCode or Claude Code) pre-configured for any LLM, handling agent installation and letting you use either hosted models or locally downloaded open models. It also provides terminal chat, an OpenAI-compatible API, and a decision model (Eve) for label-scoring questions, all from a single cross-platform interface.