Back to Details

claude-code-learning

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Claude Code Learning Skill

Claude Code学习技能

Master Claude Code configuration and optimization
精通Claude Code配置与优化

Actions

操作指令

ActionDescriptionExample
learn
Start learning guide
/claude-code-learning learn 1
setup
Auto-generate settings
/claude-code-learning setup
upgrade
Latest features guide
/claude-code-learning upgrade
操作描述示例
learn
启动学习指南
/claude-code-learning learn 1
setup
自动生成设置
/claude-code-learning setup
upgrade
最新功能指南
/claude-code-learning upgrade

learn [level]

learn [等级]

Learning content by level:
  • Level 1: Basics - Writing CLAUDE.md, Using Plan Mode
  • Level 2: Automation - Commands, Hooks, Permission management
  • Level 3: Specialization - Agents, Skills, MCP integration
  • Level 4: Team Optimization - GitHub Action, Team rule standardization
  • Level 5: PDCA Methodology - bkit methodology learning
按等级划分的学习内容：
  • Level 1：基础 - 编写CLAUDE.md、使用计划模式
  • Level 2：自动化 - 命令、钩子、权限管理
  • Level 3：专业化 - Agents、Skills、MCP集成
  • Level 4：团队优化 - GitHub Action、团队规则标准化
  • Level 5：PDCA方法论 - bkit方法论学习

setup

setup

Auto-generate appropriate settings after analyzing current project:
  1. Analyze/generate CLAUDE.md
  2. Check .claude/ folder structure
  3. Suggest required configuration files
分析当前项目后自动生成合适的设置：
  1. 分析/生成CLAUDE.md
  2. 检查.claude/文件夹结构
  3. 建议所需的配置文件

upgrade

upgrade

Guide to latest Claude Code features and best practices.
指导了解Claude Code的最新功能与最佳实践。

Learning Levels

学习等级

Level 1: Basics (15 min)

Level 1：基础（15分钟）

markdown
undefined
markdown
undefined

What is CLAUDE.md?

什么是CLAUDE.md？

A shared knowledge repository for the team. When Claude makes mistakes, add rules to prevent the same mistakes from recurring.
团队共享的知识库。当Claude出现错误时，添加规则以防止重复犯错。

Example

示例

Development Workflow

开发工作流

Package Management

包管理

  • Always use 
    pnpm
     (
    npm
    , 
    yarn
    prohibited)
  • 始终使用
    pnpm
    （禁止使用
    npm
    、
    yarn
    ）

Coding Conventions

编码规范

  • Prefer 
    type
    , avoid 
    interface
  • Never use 
    enum
     → Use string literal unions
  • 优先使用
    type
    ，避免
    interface
  • 绝不使用
    enum
     → 使用字符串字面量联合类型

Prohibited

禁止事项

  • ❌ No console.log (use logger)
  • ❌ No any type
undefined
  • ❌ 禁止console.log（使用logger）
  • ❌ 禁止any类型
undefined

Level 2: Automation (30 min)

Level 2：自动化（30分钟）

markdown
undefined
markdown
undefined

What are Slash Commands?

什么是斜杠命令？

Execute repetitive daily tasks with 
/command-name
.
使用
/command-name
执行日常重复任务。

Command Location

命令位置

.claude/commands/{command-name}.md
.claude/commands/{command-name}.md

PostToolUse Hook

PostToolUse钩子

Auto-formatting after code modification:
// .claude/settings.local.json { "hooks": { "PostToolUse": [{ "matcher": "Write|Edit", "hooks": [{ "type": "command", "command": "pnpm format || true" }] }] } }
undefined
代码修改后自动格式化：
// .claude/settings.local.json { "hooks": { "PostToolUse": [{ "matcher": "Write|Edit", "hooks": [{ "type": "command", "command": "pnpm format || true" }] }] } }
undefined

Level 3: Specialization (45 min)

Level 3：专业化（45分钟）

markdown
undefined
markdown
undefined

What are Sub-agents?

什么是子Agent？

AI agents specialized for specific tasks.
专门用于特定任务的AI Agent。

What are Skills?

什么是Skills？

Domain-specific expert context. Claude auto-references when working on related tasks.
特定领域的专家上下文。Claude处理相关任务时会自动引用。

MCP Integration

MCP集成

Connect external tools (Slack, GitHub, Jira, etc.) via .mcp.json.
undefined
通过.mcp.json连接外部工具（Slack、GitHub、Jira等）。
undefined

Level 4: Team Optimization (1 hour)

Level 4：团队优化（1小时）

markdown
undefined
markdown
undefined

PR Automation with GitHub Action

借助GitHub Action实现PR自动化

Mention @claude in PR comments to auto-update documentation.
在PR评论中提及@claude以自动更新文档。

Team Rule Standardization

团队规则标准化

  1. Manage CLAUDE.md with Git
  2. Add rules during PR review
  3. Gradually accumulate team knowledge
  1. 使用Git管理CLAUDE.md
  2. 在PR评审时添加规则
  3. 逐步积累团队知识

Agent Teams (v1.5.1)

Agent Teams（v1.5.1）

Parallel PDCA execution with multiple AI agents working simultaneously.
Requirements: CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1
Usage: /pdca team {feature} Start team mode /pdca team status Check teammate progress /pdca team cleanup End team session
Team composition by level: Dynamic: 2 teammates (developer, qa) Enterprise: 4 teammates (architect, developer, qa, reviewer)
undefined
多个AI Agent同时工作，并行执行PDCA。
要求： CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1
用法： /pdca team {feature} 启动团队模式 /pdca team status 查看团队成员进度 /pdca team cleanup 结束团队会话
按等级划分的团队组成： Dynamic: 2名成员（开发人员、QA） Enterprise: 4名成员（架构师、开发人员、QA、评审人员）
undefined

Level 5: PDCA Methodology

Level 5：PDCA方法论

markdown
undefined
markdown
undefined

What is PDCA?

什么是PDCA？

Document-driven development methodology.
Plan → Design → Do → Check → Act
文档驱动的开发方法论。
计划 → 设计 → 执行 → 检查 → 改进

Folder Structure

文件夹结构

docs/ ├── 01-plan/ # Planning ├── 02-design/ # Design ├── 03-analysis/ # Analysis └── 04-report/ # Reports
docs/ ├── 01-plan/ # 规划 ├── 02-design/ # 设计 ├── 03-analysis/ # 分析 └── 04-report/ # 报告

Learn More

了解更多

Use /pdca skill to learn PDCA methodology.
undefined
使用/pdca skill学习PDCA方法论。
undefined

Level 6: Advanced Features (v1.5.1)

Level 6：高级功能（v1.5.1）

markdown
undefined
markdown
undefined

Output Styles

输出样式

Customize how Claude responds based on your project level.
Available styles: bkit-learning Best for beginners (learning points, TODO markers) bkit-pdca-guide Best for PDCA workflows (status badges, checklists) bkit-enterprise Best for architects (tradeoff analysis, cost impact)
Usage: /output-style Select interactively /output-style bkit-learning Apply directly
Auto-recommendation: Starter → bkit-learning Dynamic → bkit-pdca-guide Enterprise → bkit-enterprise
根据项目等级自定义Claude的响应方式。
可用样式： bkit-learning 适合初学者（学习要点、TODO标记） bkit-pdca-guide 适合PDCA工作流（状态徽章、检查清单） bkit-enterprise 适合架构师（权衡分析、成本影响）
用法： /output-style 交互式选择 /output-style bkit-learning 直接应用
自动推荐： Starter → bkit-learning Dynamic → bkit-pdca-guide Enterprise → bkit-enterprise

Agent Memory

Agent记忆

All bkit agents automatically remember context across sessions. No configuration needed.
Memory scopes: project 9 agents remember per-project context (.claude/agent-memory/) user 2 agents remember cross-project learning (~/.claude/agent-memory/)
Agents with user-scope memory: starter-guide Remembers your learning progress across projects pipeline-guide Remembers your pipeline preferences globally
所有bkit Agent会自动跨会话记住上下文。无需配置。
记忆范围： project 每个项目有9个Agent记住上下文（.claude/agent-memory/） user 2个Agent记住跨项目学习内容（~/.claude/agent-memory/）
拥有用户范围记忆的Agent： starter-guide 记住你跨项目的学习进度 pipeline-guide 记住你全局的流水线偏好

Agent Teams

Agent Teams

Parallel PDCA execution for Dynamic and Enterprise projects. See Level 4 for details.
undefined
为Dynamic和Enterprise项目提供并行PDCA执行。详情见Level 4。
undefined

Output Format

输出格式

📚 Claude Code Learning Complete!

**Current Level**: {level}
**Learned**: {summary}

🎯 Next Steps:
- Continue learning with /claude-code-learning learn {next_level}
- Auto-generate settings with /claude-code-learning setup
- Check latest trends with /claude-code-learning upgrade
📚 Claude Code学习完成！

**当前等级**：{level}
**已学习内容**：{summary}

🎯 下一步：
- 使用/claude-code-learning learn {next_level}继续学习
- 使用/claude-code-learning setup自动生成设置
- 使用/claude-code-learning upgrade了解最新趋势

Current Settings Analysis

当前设置分析

Files to analyze:
  • CLAUDE.md (root)
  • .claude/settings.local.json
  • .claude/commands/
  • .claude/agents/
  • .claude/skills/
  • .mcp.json
需要分析的文件：
  • CLAUDE.md（根目录）
  • .claude/settings.local.json
  • .claude/commands/
  • .claude/agents/
  • .claude/skills/
  • .mcp.json