Claude Code Learning Hub
中文 Mingyu's Library

Hub / Course

Course overview

A linear syllabus where each lesson builds on the last — start at D1 and read in order. Every lesson is grounded in the official docs fetched the day it was written, with hands-on steps and acceptance criteria.

DayTopicStatus
D1The agentic loop and what Claude can actually read (/context)Published 2026-08-05
D2The context window & prompt cachingPublished 2026-08-05
D3Permission modes & sandboxingPublished 2026-08-05
D4CLAUDE.md & rulesPublished 2026-08-05
D5Plan mode and explore→plan→codePublished 2026-08-05
D6Checkpoints, rewind and session managementPublished 2026-08-05
D7SkillsPublished 2026-08-05
D8HooksPublished 2026-08-05
D9MCPPublished 2026-08-05
D10SubagentsPublished 2026-08-05
D11Worktrees & agent viewPublished 2026-08-05
D12Agent teams & dynamic workflowsPublished 2026-08-05
D13Headless & CIPublished 2026-08-05
D14Plugins: packaging & distributionPublished 2026-08-05
How the syllabus runs When the official docs change, published lessons are revised in step (the lesson's "Last updated" date moves). With all 14 lessons out, the course is in continuous-revision mode: each day one lesson gets deepened or re-verified against the latest docs, and new advanced topics are appended to the syllabus.