datadog

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Datadog Skill

Datadog Skill

Overview

概述

Enables Claude to access Datadog to view infrastructure metrics, APM traces, logs, dashboards, and monitor alerts across your entire observability stack.
让Claude能够访问Datadog,查看基础设施指标、APM追踪、日志、仪表板,并监控整个可观测性堆栈中的告警。

Quick Install

快速安装

bash
curl -sSL https://canifi.com/skills/datadog/install.sh | bash
Or manually:
bash
cp -r skills/datadog ~/.canifi/skills/
bash
curl -sSL https://canifi.com/skills/datadog/install.sh | bash
或者手动安装:
bash
cp -r skills/datadog ~/.canifi/skills/

Setup

设置

Configure via canifi-env:
bash
undefined
通过canifi-env进行配置:
bash
undefined

First, ensure canifi-env is installed:

首先,确保已安装canifi-env:

canifi-env set DATADOG_EMAIL "your-email@example.com"
undefined
canifi-env set DATADOG_EMAIL "your-email@example.com"
undefined

Privacy & Authentication

隐私与认证

Your credentials, your choice. Canifi LifeOS respects your privacy.
您的凭证,由您掌控。 Canifi LifeOS尊重您的隐私。

Option 1: Manual Browser Login (Recommended)

选项1:手动浏览器登录(推荐)

If you prefer not to share credentials with Claude Code:
  1. Complete the Browser Automation Setup using CDP mode
  2. Login to the service manually in the Playwright-controlled Chrome window
  3. Claude will use your authenticated session without ever seeing your password
如果您不想与Claude Code共享凭证:
  1. 使用CDP模式完成浏览器自动化设置
  2. 在Playwright控制的Chrome窗口中手动登录服务
  3. Claude将使用您的已认证会话,全程不会获取您的密码

Option 2: Environment Variables

选项2:环境变量

If you're comfortable sharing credentials, you can store them locally:
bash
canifi-env set SERVICE_EMAIL "your-email"
canifi-env set SERVICE_PASSWORD "your-password"
Note: Credentials stored in canifi-env are only accessible locally on your machine and are never transmitted.
如果您愿意共享凭证,可以将其存储在本地:
bash
canifi-env set SERVICE_EMAIL "your-email"
canifi-env set SERVICE_PASSWORD "your-password"
注意:存储在canifi-env中的凭证仅能在您的本地机器上访问,绝不会被传输。

Capabilities

功能

  • View infrastructure metrics
  • Check APM traces and services
  • Monitor log streams
  • View custom dashboards
  • Check alert status
  • Analyze host health
  • 查看基础设施指标
  • 检查APM追踪和服务
  • 监控日志流
  • 查看自定义仪表板
  • 检查告警状态
  • 分析主机健康状况

Usage Examples

使用示例

Example 1: Check Infrastructure

示例1:检查基础设施

User: "How's my infrastructure looking?"
Claude: I'll check your Datadog dashboard.
- Opens app.datadoghq.com via Playwright MCP
- Logs into account
- Infrastructure:
  - Hosts: 12 active
  - Containers: 45 running
  - CPU avg: 34%
  - Memory avg: 67%
- Alerts: 1 warning (disk space)
- All critical services healthy
用户:“我的基础设施状态如何?”
Claude:我将查看您的Datadog仪表板。
- 通过Playwright MCP打开app.datadoghq.com
- 登录账户
- 基础设施情况:
  - 主机:12台活跃
  - 容器:45台运行中
  - 平均CPU使用率:34%
  - 平均内存使用率:67%
- 告警:1条警告(磁盘空间不足)
- 所有关键服务运行正常

Example 2: Check APM

示例2:检查APM

User: "How are my services performing?"
Claude: I'll check APM.
- Views APM section
- Services:
  - api-gateway: 45ms p50, 120ms p99
  - user-service: 23ms p50, 89ms p99
  - order-service: 67ms p50, 234ms p99
- Throughput: 2.3k req/s
- Error rate: 0.12%
- Slowest endpoint: /api/reports (890ms)
用户:“我的服务性能如何?”
Claude:我将检查APM。
- 查看APM板块
- 服务情况:
  - api-gateway:p50延迟45ms,p99延迟120ms
  - user-service:p50延迟23ms,p99延迟89ms
  - order-service:p50延迟67ms,p99延迟234ms
- 吞吐量:2.3k请求/秒
- 错误率:0.12%
- 最慢端点:/api/reports(890ms)

Example 3: Check Logs

示例3:检查日志

User: "Any errors in the logs?"
Claude: I'll check Log Management.
- Views Logs section
- Last hour:
  - ERROR: 23 events
  - WARN: 156 events
  - INFO: 45,678 events
- Top errors:
  - ConnectionTimeout: 12 occurrences
  - ValidationError: 8 occurrences
- Pattern detected: DB connection spikes
用户:“日志中有错误吗?”
Claude:我将检查日志管理模块。
- 查看日志板块
- 过去一小时:
  - 错误:23条事件
  - 警告:156条事件
  - 信息:45,678条事件
- 主要错误类型:
  - ConnectionTimeout:12次出现
  - ValidationError:8次出现
- 检测到模式:数据库连接峰值

Authentication Flow

认证流程

  1. Navigate to app.datadoghq.com via Playwright MCP
  2. Enter email address
  3. Enter password
  4. Handle 2FA/SAML if enabled
  5. Select organization if multiple
  6. Maintain session for dashboard access
  1. 通过Playwright MCP导航至app.datadoghq.com
  2. 输入邮箱地址
  3. 输入密码
  4. 若启用则处理2FA/SAML验证
  5. 若有多个组织则选择对应组织
  6. 维持会话以访问仪表板

Error Handling

错误处理

  • Login Failed: Retry credentials
  • 2FA Required: Complete verification
  • SAML/SSO: Follow redirect
  • Session Expired: Re-authenticate
  • Rate Limited: Wait and retry
  • Access Denied: Check org permissions
  • 登录失败:重试凭证
  • 需要2FA:完成验证
  • SAML/SSO:跟随重定向
  • 会话过期:重新认证
  • 速率限制:等待后重试
  • 访问被拒绝:检查组织权限

Self-Improvement Instructions

自我改进说明

After each interaction:
  • Track metric patterns
  • Note alert frequency
  • Log performance trends
  • Document UI changes
Suggest updates when:
  • Datadog updates dashboard
  • New features added
  • Integrations expand
  • Metrics added
每次交互后:
  • 追踪指标模式
  • 记录告警频率
  • 记录性能趋势
  • 记录UI变更
在以下情况时建议更新:
  • Datadog更新仪表板
  • 添加新功能
  • 扩展集成
  • 添加新指标

Notes

注意事项

  • Comprehensive observability
  • APM and tracing
  • Log management
  • Custom dashboards
  • Alert management
  • 600+ integrations
  • Enterprise-grade
  • 全面的可观测性
  • APM与追踪
  • 日志管理
  • 自定义仪表板
  • 告警管理
  • 600+集成
  • 企业级服务