10 related articles
Codex Beginner's Guide: Lessons Learne…
Deep dive into OpenAI Codex Agent's core features, Skill ecosystem, context compression, and project-level Harness management tips from 660M tokens of real-world usage.

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.
Product ReviewsDeep dive into how Claude Code helps product managers independently investigate bugs, understand codebases, and generate professional technical reports — transforming PM-engineer collaboration.
Product ReviewsDeep dive into how Claude Code helps product managers independently investigate bugs, understand codebases, and generate professional technical reports—boosting PM-engineer collaboration efficiency.
TutorialsAnthropic engineers share how to properly use Claude Code at AI Code Summit: build composable Skills systems instead of one-off prompts. Master four core rules for skills that get smarter over time.
TutorialsDeep analysis of ByteDance's Codex Chinese manual covering environment setup, MCP workflows, Skills encapsulation, and multi-Agent collaboration across ten chapters for developers.
Product ReviewsDeep dive into Multica, an open-source Agent management platform for coordinating Claude Code, Codex, and other AI coding assistants as unified team members with self-hosted deployment.
Product ReviewsDeep dive into Hermes Agent desktop app: closed-loop learning, persistent cross-session memory, multi-agent management, and tool integration. Discover how this open-source AI agent self-evolves to become a true productivity powerhouse.
TutorialsDeep dive into Andrew Ng's viral AI Agent course covering five core modules: Reflection, Planning, Tool Use, Multi-Agent Collaboration, and Memory, with practical learning paths for LLM agent development.
Claude Code + Skills: A Practical Guid…
Learn how Claude Code combined with Skills encapsulation enables AI-driven test case generation with 10x efficiency gains, from 33 to 400+ cases through encoded expert knowledge.