Skip to main content

Claude Code

Setup​

~/.bashrc:

export ANTHROPIC_AUTH_TOKEN="<YOUR_API_KEY>"
export ANTHROPIC_BASE_URL="https://open.bigmodel.cn/api/anthropic"
export ANTHROPIC_MODEL="glm-4.7"
export ANTHROPIC_SMALL_FAST_MODEL="glm-4.7"
export ANTHROPIC_DEFAULT_OPUS_MODEL="glm-4.7"
export ANTHROPIC_DEFAULT_SONNET_MODEL="glm-4.7"
export ANTHROPIC_DEFAULT_HAIKU_MODEL="glm-4.7"
export API_TIMEOUT_MS="3000000"
export CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1

~/.claude/settings.json:

{
  "env": {
    "ANTHROPIC_AUTH_TOKEN": "<YOUR_API_KEY>",
    "ANTHROPIC_BASE_URL": "https://open.bigmodel.cn/api/anthropic",
    "ANTHROPIC_MODEL": "glm-4.7",
    "ANTHROPIC_SMALL_FAST_MODEL": "glm-4.7",
    "ANTHROPIC_DEFAULT_OPUS_MODEL": "glm-4.7",
    "ANTHROPIC_DEFAULT_SONNET_MODEL": "glm-4.7",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "glm-4.7",
    "API_TIMEOUT_MS": "3000000",
    "CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC": 1
  }
}

Switch​

Quick configuration with All-in-One assistant tool Claude Code Switch.

Bootstrap​

Opinionated project initialization for Claude Code.

Tools​

Claude code has built-in tools, follow certain paradigm to use them.

Commands​

.claude/commands/api/api-new.md:

Create a new POST $ARGUMENTS endpoint with:

- Auth middleware.
- Rate limiting middleware.
- Error handling wrapper.
- TypeScript interfaces for request and response.
/api-new /api/users

Memory​

Captures everything Claude does during your coding sessions, compresses it with Claude agent-sdk, and injects relevant context back into future sessions.

Session​

Resume from session:

# Most recent session
claude -c

# Specific session
claude -r
claude -r [session_id]

Skills​

渐进式披露:

  • 核心功能简洁: 500 行以内.
  • 高级功能分离.
  • 按需加载: metadata -> instructions -> resources and code.
工具选择
  • 临时任务 -> prompts
  • 标准作业程序 -> skills
  • 连接外部系统 -> MCP
  • 复杂独立任务 -> sub-agents

Skills Description​

核心原则: 既要说明做什么，也要说明什么时候用:

description: Extract text and tables from PDF files, fill forms, merge documents.
  Use when working with PDF files or when the user mentions PDFs,
  forms, or document extraction.

Skills Effective Checklist​

  1. Core quality:
    • Description is specific and includes key terms
    • Description includes both what the Skill does and when to use it
    • SKILL.md body is under 500 lines
    • Additional details are in separate files (if needed)
    • No time-sensitive information (or in "old patterns" section)
    • Consistent terminology throughout
    • Examples are concrete, not abstract
    • File references are one level deep
    • Progressive disclosure used appropriately
    • Workflows have clear steps
  2. Code and scripts:
    • Scripts solve problems rather than punt to Claude
    • Error handling is explicit and helpful
    • No "voodoo constants" (all values justified)
    • Required packages listed in instructions and verified as available
    • Scripts have clear documentation
    • No Windows-style paths (all forward slashes)
    • Validation/verification steps for critical operations
    • Feedback loops included for quality-critical tasks
  3. Testing:
    • At least three evaluations created
    • Tested with Haiku, Sonnet, and Opus
    • Tested with real usage scenarios
    • Team feedback incorporated (if applicable)

Skills Security Checklist​

  1. Code Review:
    • 所有脚本已审查
    • 无硬编码密钥或密码
    • 无危险的系统命令（rm -rf, eval, exec）
    • 文件路径经过验证（防止路径遍历）
  2. Network Access:
    • 检查所有外部 URL
    • 验证 API 端点可信
    • 处理网络失败情况
  3. Data Handling:
    • 无敏感数据泄露
    • 日志不包含 PII
    • 临时文件正确清理
  4. Permissions:
    • 最小权限原则
    • 不请求不必要的文件访问
    • 明确说明需要的权限
  5. Documentation:
    • 安全注意事项已文档化
    • 数据处理流程透明
    • 用户知情同意
grep -r "requests\." .
grep -r "os.system" .
grep -r "subprocess" .
grep -r "eval" .
  • Superpowers: Complete software development workflow.
  • DevBrowser: Browser automation.
  • NotebookLM: Communicate directly with Google NotebookLM notebooks.
  • Scientific: Comprehensive collection of ready-to-use scientific skills.

Skills List​

  • Anthropic: Anthropic repository for agent skills.
  • Awesome: Curated list of Claude Code skills.
  • Marketplace: Agent skills marketplace.
  • Seekers: Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection.

Skills Guide​

Plugins​

Install plugins from marketplace, it will extend Claude Code through the plugin system with:

  • Custom commands.
  • Agents.
  • Hooks.
  • Skills.
  • MCP servers.
  • Agents: Comprehensive production-ready system combining agents, multi-agent workflow orchestrators, skills, and slash commands.
  • Continuous: Context management.
  • Figma: Figma official skills and MCP server.
  • Notion: Notion official skills, commands and MCP server.
  • SafetyNet: Catching destructive git and filesystem commands before they execute.
  • Edmuds: Personal configuration for productive web development.
  • LifeAssistant: Personal coach that remembers, notices patterns, and holds accountable.
/plugin marketplace add anthropics/claude-plugins-official
/plugin marketplace add obra/superpowers-marketplace
/plugin marketplace add sabertazimi/claude-code
/plugin install frontend-design
/plugin install superpowers@superpowers-marketplace
/plugin install sabertaz-claude-code

Plugins List​

  • Anthropic: Anthropic-managed directory of high quality Claude Code plugins.
  • Plugins: Lightweight registry to discover and manage Claude plugins and agent skills.

Best Practices​

Claude code best practices:

  • Extended thinking mode: "think" -> "think hard" -> "think harder" -> "ultrathink".
  • Plan mode: 对于复杂的任务, 使用 plan mode 先进行规划, 会比直接执行更高效.
  • Avoid /compact: dump plan and progress + /clear the state + restart from dump file.
  • Use Claude Code GitHub Actions.