Agent Skills Dev · Independent Course Notes
Agent Skills Dev (agentskillsdev) publishes independent notes on the Agent Skills course by Andrew Ng and Anthropic on DeepLearning.AI, alongside Claude Code architecture and Harness Engineering analysis. Start with the English architecture guide or explore the Chinese course notes.
Claude Code is Anthropic's official CLI tool, built on ~512,000 lines of TypeScript across 1,884 files. We break down the architecture from a system-wide view down to eight core subsystems.
Complete breakdown of 6 subsystems: Entry Layer, Query Engine, Tool System, Command System, Permission System, and Multi-Agent Coordination. Based on 1,884 TypeScript files.
Read more →The complete course library is currently available in Chinese — including Agent Skills L0-L8 lessons, Harness Engineering methodology, and the Harness architecture book (10 chapters + 2 appendices).
Browse (Chinese) →The Agent Skills course — taught by Elie Schoppik — covers how to build reusable Skills for Claude, combine them with MCP and Subagents, and apply them across Claude.ai, Claude Code, Claude API, and the Agent SDK. English lesson-by-lesson notes are being translated from the Chinese originals. Below is what's already mapped out.
Agent Skills Dev (agentskillsdev.com) is independently maintained by 渔夫. We publish source-level analysis of Claude Code and engineering methodology research on building AI agents, grounded in source code and primary references. Most articles are in Chinese; the Claude Code architecture analysis is also available in English. This site is independent of Anthropic and DeepLearning.AI.