#on-demand loading
17 related articles
MCP Protocol Deep Dive: The Core Mecha…
·2 min
MCP Protocol Deep Dive: The Core Mechanism Behind Claude Code's External Tool Connections
Deep dive into the MCP protocol's architecture, server types, scope modes, and context window optimization strategies for configuring Claude Code's external tool connections.
Read more →
Claude Code Skills Encapsulation: Maki…
·1 min
Claude Code Skills Encapsulation: Making AI Testing Tools Truly Efficient and Reusable
Learn how to encapsulate Claude Code Agent Skills for test case design. Solve prompt repetition pain points with on-demand loading and skill reuse techniques.
Read more →
·2 min
Andrew Ng's Agent Skills Course Explained: Building Reusable Professional Skills for AI Agents
Deep dive into Andrew Ng's Agent Skills course with Anthropic, covering Skills architecture, progressive loading, MCP integration, and hands-on examples for building reusable AI agent skills.
Read more →
Tutorials·2 min
How AI Coding Skills Work: From Function Call to Sub-Agent Implementation
Deep dive into how AI coding Skills work: from Function Call to MCP to Skills as sub-agents with on-demand loading, implemented via Spring AI Alibaba.
Read more →
Tutorials·2 min
How AI Coding Skills Work: From Function Call to Sub-Agent Implementation
Deep dive into how AI coding Skills work technically, from Function Call to MCP to Skills as sub-agents with on-demand loading, implemented via Spring AI Alibaba.
Read more →
Deep Dives·3 min
Deep Dive into How OpenClaw (Open-Source Crayfish) AI Agent Works
Deep analysis of OpenClaw AI Agent internals: System Prompt, tool calling, SubAgents, Skill system, memory, and Context Engineering explained.
Read more →
Tutorials·2 min
Getting Started with Claude Code MCP: Connecting External Tools and Context Management Practices
A detailed guide to MCP (Model Context Protocol) in Claude Code, covering server setup, three scope configurations, context window optimization, CLI alternatives, and Skills best practices.
Read more →
Tutorials·2 min
Claude Code + Typst: An AI Typesetting Workflow Where Speaking Creates Slides
Use Claude Code to drive Typst with natural language, paired with Skim for real-time preview, to generate academic slides just by speaking. A five-step workflow from idea to professional presentation.
Read more →
Tutorials·3 min
Claude Code Hooks Explained: A Safety Net for When Rules Fail
Deep dive into Claude Code Hooks: why CLAUDE.md rules fail, and how PreCommand blocking, PostCommand reminders, and Stop Hooks form a reliable AI behavior constraint system.
Read more →
Tutorials·3 min
Claude Code Hooks Explained: A Safety Net for When Rules Fail
Deep dive into Claude Code Hooks: why CLAUDE.md rules fail and how PreCommand, PostCommand, and Stop Hooks provide a reliable safety net through on-demand context injection.
Read more →
Tutorials·3 min
Claude Code Source Code Analysis: A Complete Breakdown of the Startup and Bootstrap Flow
Deep dive into Claude Code's source code startup and bootstrap flow, from CLI entry's on-demand loading design and REPL startup to sentiment analysis and the Agent Loop prelude.
Read more →
Tutorials
Enterprise Claude Code Workflows: Five…
·3 min
Enterprise Claude Code Workflows: Five Core Components for Taming Million-Line Codebases
Deep dive into Anthropic's enterprise Claude Code deployment: CLAUDE.md layering, Hooks, Skills, Plugins, and MCP servers for million-line codebases.
Read more →
Deep Dives
Deep Dive into Cursor Skills: From Fun…
·4 min
Deep Dive into Cursor Skills: From Function Call to Practice
Deep dive into Cursor Skills' underlying principles, from Function Call and MCP protocol to Workflow Agent, with Spring AI Alibaba practical demo for any LLM.
Read more →
Industry Insights
MCP Isn't Dead! Anthropic's Two Power …
·3 min
MCP Isn't Dead! Anthropic's Two Power Moves Cut Costs by 85% + 12 Agentic Patterns Fully Explained
Deep dive into MCP's cloud repositioning strategy, how Anthropic cuts token costs by 85% with Tool Search and code sandboxes, and 12 Agentic patterns for production-grade AI Agents.
Read more →
Tutorials·2 min
Career Progression in AI/LLM Application Development: Four Stages from Beginner to 40K Monthly Salary
A systematic four-stage career path for AI/LLM application development: from RAG and Agent fundamentals to architecture design, helping developers transition to AI roles targeting 40K+ monthly salary.
Read more →
Deep Dives·3 min
Deep Dive into MCP Code Execution & Agent Skills: Compressing 150K Tokens Down to 2,000
Deep analysis of two MCP ecosystem breakthroughs: code execution compresses tool definitions from 150K to 2K tokens, and Agent Skills enable capability packaging and reuse.
Read more →
Product Reviews
UE5.7 AI Assistant Plugin Hands-On: Wh…
·1 min
UE5.7 AI Assistant Plugin Hands-On: What Can It Do? What Can't It Do?
Hands-on test of UE5.7's built-in AI Assistant plugin: how to enable it, knowledge Q&A and C++ code generation results, plus key limitations like no project file access and no Blueprint support.
Read more →