learn-claude-code
Learn to build AI agent harnesses from scratch
All Skills in This Repository (4)
Pure Emerald Level Indicatorscode-review
Analyze codebases for security, correctness, performance, and maintainability issues.
Extract text, create PDFs, and merge documents using Python tools.
mcp-builder
Create Python or TypeScript MCP servers exposing tools, resources, and prompts.
agent-builder
Design and implement autonomous AI agent architectures using modular capabilities and context management.
Frequently Asked Questions
FAQPage SchemaHow to install learn-claude-code?โผ
Run `npx skills add shareAI-lab/learn-claude-code --all -g -y` in your terminal to install all skills in this suite globally.
What is an agent harness?โผ
A harness is the code that gives a model tools, knowledge, context, and permissions so it can act in a real environment. This course teaches you to build that layer step by step.
Do I need to be an expert to follow this course?โผ
No. Each lesson starts from a simple runnable Python file and builds up gradually, so basic Python knowledge is enough to get started.
What topics does this course cover?โผ
It covers the agent loop, todo tracking, cron scheduling, agent teams, MCP plugins, goal loops, and a fully integrated harness, plus skills for PDF processing, code review, and agent building.
Is the course available in other languages?โผ
Yes. Every lesson includes full documentation in English, Chinese, and Japanese.
Related Repositories in Education & Research
View All in Education & Researchโai-agents-for-beginners
Learn to build, deploy, and secure AI agents step by step
33-js-concepts
Master 33 essential JavaScript concepts with tested, verified guides
academic-research-skills
Full academic pipeline from research question to peer-reviewed paper