Cẩm nang thực chiến Mastering Claude Code (tiếng Việt): 16 chương biên soạn từ tài liệu chính thức của Anthropic — CLI, workflows, MCP, subagents, skills, hooks, plugins, CI/CD & tối ưu context.
Cuốn sách thực chiến giúp bạn dùng Claude Code một cách hiệu quả — biên soạn từ bộ tài liệu chính thức của Anthropic.
- Đối tượng: Developer đã biết cơ bản, muốn nâng cao và tối ưu cách làm việc. - Phong cách: Súc tích, dạng tra cứu nhanh — nhiều bảng, bullet, ví dụ config/lệnh thật. - Phạm vi: Claude Code CLI là trọng tâm (kèm IDE/CI-CD ở mức cần thiết).
Phần I — Nền tảng & Tư duy Chương File ----------------- 1 Foundations & Mindset — agentic loop, context window, triết lý dùng hiệu quả 01-foundations-and-mindset.md 2 Installation & Configuration — setup, authentication, model config, fast mode, env vars 02-installation-and-configuration.md
Phần II — Làm việc hằng ngày Chương File ----------------- 3 Essential Workflows — common workflows, best practices, interactive mode, keybindings 03-essential-workflows.md 4 Slash Commands & CLI — built-in + custom commands, CLI reference, headless mode 04-slash-commands-and-cli.md 5 Context & Memory — CLAUDE.md, memory, context window, sessions, checkpointing 05-context-and-memory.md 6 Permissions & Sandboxing — permission rules/modes, sandboxing, security 06-permissions-and-sandboxing.md
Phần III — Mở rộng năng lực Chương File ----------------- 7 MCP (Model Context Protocol) — thêm/quản lý MCP server, scope, managed MCP 07-mcp.md 8 Subagents & Agent Teams — sub-agents, agent teams, agent view, delegate 08-subagents-and-agent-teams.md 9 Skills — SKILL.md, frontmatter, auto-invoke, tổ chức skill 09-skills.md 10 Hooks — hook events, matcher, JSON I/O, tự động hóa hành vi 10-hooks.md 11 Plugins — đóng gói, plugin.json, marketplaces,
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/cuongnbms--mastering-claude-code.html)
runs anywhere. uses anything
KernelLord/pickysteveSkill router and context picker for Claude Code, Cursor, and Aider. Auto-picks the right skill for every prompt, with prompt-injection filtering for MCP.
Smitner-Studio/facetRender agent-written Markdown as a live local page, and send the human's click back to the agent as typed data. Human-in-the-loop approval gates for coding agents.
hung12ct/culiSelf-improving context & memory for Claude Code and OpenAI Codex. One canonical knowledge store injected only when relevant — hooks push budgeted context, an MCP server serves depth on demand, and it
12122J/mcpvetMCP security scanner — vet a Model Context Protocol server before you add it to Claude Code, Cursor, or Windsurf. Grades it A–F, catching credential theft, tool-poisoning, and install-script payloads
luckeyfaraday/frontier-orchestratorMulti-agent orchestration for Claude Code: MCP server + skill that keeps Claude as lead engineer while delegating backend work to OpenAI Codex and frontend/design work to Kimi
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.