Token导航 LogoToken导航

Agent Skill · 云服务

azure-devops(Azure DevOps 开发平台)

用于辅助云资源、部署、容器、基础设施和运维自动化任务。它适合让 Agent 检查配置、整理部署步骤、分析资源状态、生成排障思路或辅助云服务接入。使用时需要明确目标环境、账号权限、区域和资源组,区分本地测试与生产操作;涉及删除资源、重启服务、修改网络或权限配置时,应先确认影响范围。

azure-devops 是云服务类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为调用外部服务;许可证为 MIT,暂无第三方扫描结果,按安装量在云服务类的 479 个 Skill 里排第 442。

总安装 423周安装 18GitHub Stars 公开资料未说明下载 148核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:azure-devops(Azure DevOps 开发平台)
来源仓库:https://github.com/thomasholknielsen/claude-code-config
仓库路径:skills/azure-devops
安装命令:
npx skills add thomasholknielsen/claude-code-config --skill "azure-devops"
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

AgentSkills.tonpx skills
npx skills add thomasholknielsen/claude-code-config --skill "azure-devops"

这个 Skill 是做什么的

云服务类 Skill 对接各家云平台的接口,用来查询资源、估算成本和执行变更。

用于 Azure DevOps 平台的资源管理与部署自动化支持。适合在云服务运维、CI/CD 流程优化或基础设施监控中使用。可协助分析资源配置、生成部署脚本或排查服务异常。azure-devops 属于云服务类 Skill,可作为该场景下的辅助能力补充。执行操作前需明确目标环境与权限级别,避免误删关键资产。

建议在测试环境验证后再应用于生产系统,降低风险。

来源仓库内路径:skills/azure-devops

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add thomasholknielsen/claude-code-config --skill "azure-devops";命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要调用外部服务,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

azure-devops 怎么安装?

在终端执行 npx skills add thomasholknielsen/claude-code-config --skill "azure-devops"。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

azure-devops 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

azure-devops 需要什么权限?

权限级别是调用外部服务。该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

azure-devops 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

azure-devops 用的人多吗?

公开数据是累计安装 423 次,近一周安装 18 次,下载 148 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

azure-devops 安全吗?

没有查到第三方扫描结果,安全性无法从公开资料判断,安装前请自行审查源码、依赖和命令行为。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 许可证明确为 MIT,商用和分发边界好判断。

先想清楚的地方

  • 没有第三方扫描结果,安全性只能靠自己读源码判断。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理云服务类任务、又不想每次都手写提示词的人。

不太适合

  • 要求有安全扫描结论才肯安装的团队。
  • 需要厂商级技术支持和 SLA 的生产系统。

云服务类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
azure-deploy

Azure 部署 · Codex、Claude

6,641,856764调用外部服务未明确通过
azure-diagnostics

Azure diagnostics 问题管理 · Codex、Claude

6,575,520764调用外部服务未明确通过
azure-aigateway

Azure aigateway 部署 · Codex、Claude

6,553,272764调用外部服务未明确有提醒
azure-ai

Azure AI 搜索 · Codex、Claude

6,514,128764调用外部服务未明确通过
azure-cloud-migrate

Azure Cloud migrate 部署 · Codex、Claude

6,506,784764调用外部服务未明确有提醒
azure-devops

Azure DevOps 开发平台 · 本页

423—调用外部服务MIT未收录

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
azure-devops
description
Provides expert guidance on Azure DevOps tasks including work item management, pipelines, repositories, pull requests, and CI/CD workflows. Use when working with Azure DevOps projects, configuring pipelines, managing work items, or integrating Azure DevOps with development workflows.

Azure DevOps Skill

Instructions

When working with Azure DevOps, follow these workflows based on task type:

Work Items & Tracking

  1. Identify the work item type (Epic, Feature, User Story, Task, Bug)
  2. Set appropriate fields: Title, Description, Acceptance Criteria, State
  3. Link related items (depends on, related to, blocked by)
  4. Assign to team member and set sprint/iteration
  5. Apply area path and tags for organization

Repositories & Branches

  1. Identify repository type (Git or TFVC)
  2. For Git: Create feature branches following naming convention
  3. Configure branch policies (require reviewers, build validation)
  4. Set branch protection rules for main/develop branches
  5. Configure merge strategies (squash, rebase, or three-way)

Pull Requests

  1. Create PR with clear title and description
  2. Link to related work items (#1234 syntax)
  3. Request appropriate reviewers
  4. Ensure build passes and policy requirements met
  5. Address review comments and iterate
  6. Complete PR with appropriate merge strategy

Pipelines & CI/CD

  1. Determine pipeline type (Build, Release, Multi-stage YAML)
  2. Configure triggers (commit, PR, scheduled, manual)
  3. Set up agent pool and demands
  4. Define stages and jobs
  5. Add tasks for build, test, and deployment
  6. Configure approvals and gates
  7. Set up notifications and retention policies

Test Management

  1. Create test plans and test suites
  2. Define test cases with steps and expected results
  3. Run manual tests or automated tests
  4. Link tests to work items
  5. Generate test reports and track metrics

Examples

Example 1: Creating a Feature Work Item

Scenario: Need to add user authentication to a project

Process:

  1. Create Feature work item with title "Implement User Authentication"
  2. Add acceptance criteria:

- Users can register with email/password - Users can login securely - Sessions persist across page reloads - Password reset functionality works

  1. Create child User Stories:

- "Registration form UI and validation" - "Authentication API endpoints" - "Session management" - "Password reset flow"

  1. Link to Epic "Security & Auth"
  2. Assign to team and add to sprint
  3. Add tags: #authentication, #backend, #frontend

Example 2: Setting Up YAML Pipeline

Scenario: Configure CI/CD for .NET project

Pipeline Structure:

trigger:
  - main
  - develop

pr:
  - main
  - develop

pool:
  vmImage: 'windows-latest'

variables:
  buildConfiguration: 'Release'
  dotnetVersion: '6.0.x'

stages:
  - stage: Build
    jobs:
      - job: BuildJob
        steps:
          - task: UseDotNet@2
            inputs:
              version: $(dotnetVersion)
          - task: DotNetCoreCLI@2
            inputs:
              command: 'build'
              arguments: '--configuration $(buildConfiguration)'
          - task: DotNetCoreCLI@2
            inputs:
              command: 'test'
              arguments: '--configuration $(buildConfiguration) --no-build'

  - stage: Deploy
    condition: and(succeeded(), eq(variables['Build.SourceBranch'], 'refs/heads/main'))
    jobs:
      - deployment: DeployJob
        environment: 'production'
        strategy:
          runOnce:
            deploy:
              steps:
                - task: PublishBuildArtifacts@1
                - task: AzureWebApp@1
                  inputs:
                    azureSubscription: 'Azure Connection'
                    appName: 'your-app-name'

Example 3: Branch Policy Configuration

Scenario: Protect main branch with quality gates

Settings:

  1. Require pull request reviews:

- Minimum reviewers: 2 - Require at least one approval from codeowners

  1. Build validation:

- Build policy: require build to pass - Build expiration: 720 minutes

  1. Automatic code review:

- Require approval from code owners

  1. Merge restrictions:

- Prevent completion with active comments - Default merge strategy: Squash commit

  1. Status checks:

- No optional status checks required

Example 4: Pull Request Workflow

PR Description Template:

## Description
Brief description of changes

## Linked Work Items
Fixes #1234
Related to #5678

## Type of Change
- [ ] Bug fix
- [ ] New feature
- [ ] Breaking change
- [ ] Documentation update

## Testing Done
Describe testing performed

## Checklist
- [ ] Code follows style guidelines
- [ ] Self-review completed
- [ ] Comments added for complex logic
- [ ] Tests pass locally
- [ ] No new warnings generated

Review Workflow:

  1. Create PR from feature branch to main/develop
  2. Wait for build validation and status checks
  3. Request reviewers (typically 2-3 team members)
  4. Address feedback in follow-up commits
  5. Once approved and checks pass, complete PR
  6. Delete branch after merge (keep repository clean)

Example 5: Multi-stage Pipeline with Approvals

Scenario: Production deployment requires approval

Pipeline Configuration:

  1. Build stage: Automated on every commit
  2. Integration stage: Run integration tests (requires build pass)
  3. Staging stage: Deploy to staging (requires manual approval)
  4. Production stage: Deploy to production (requires business approval + sign-off)

Approval Gates:

  • Technical lead approves staging deployment
  • Product manager approves production deployment
  • Maximum wait time: 24 hours, then auto-reject
  • Notifications sent to stakeholders

Best Practices

Work Item Management

  • Keep descriptions concise but detailed enough to understand scope
  • Break down large features into smaller user stories
  • Use acceptance criteria to define "done"
  • Link related items to show dependencies
  • Update state and progress regularly
  • Estimate using consistent units (story points or hours)
  • Review and prioritize backlog regularly

Repository & Code Management

  • Use meaningful commit messages (Conventional Commits)
  • Keep commits focused on single logical change
  • Push frequently to avoid long-lived branches
  • Delete merged branches to keep repo clean
  • Protect critical branches with policies
  • Use .gitignore and .gitattributes appropriately
  • Tag releases for easy identification

Pull Request Best Practices

  • Create PRs early, even if still in progress (draft PR)
  • Link to related work items
  • Keep PRs focused and reasonably sized
  • Write clear PR descriptions
  • Respond to feedback promptly
  • Approve PRs only when confident in changes
  • Keep review comments constructive and actionable

Pipeline Best Practices

  • Start simple, add complexity as needed
  • Use variables for configuration
  • Implement caching for faster builds
  • Run tests in parallel when possible
  • Keep build times under 10 minutes if feasible
  • Use templates for reusable pipeline logic
  • Monitor pipeline health and success rates
  • Archive and clean up old artifacts

Team Collaboration

  • Define clear code review standards
  • Establish naming conventions for branches/items
  • Create templates for work items and PRs
  • Document deployment procedures
  • Use notifications effectively (avoid alert fatigue)
  • Have regular backlog refinement sessions
  • Celebrate completed features and wins

Common Commands & Workflows

Azure CLI (az devops)

# View work items
az boards work-item show --id 1234

# Create work item
az boards work-item create --title "New Feature" --type Feature

# Update work item state
az boards work-item update --id 1234 --state "Active"

# Clone repository
az repos show --repo-id [repo-id]

Common Azure DevOps Tasks in Pipelines

# Run tests with coverage
- task: DotNetCoreCLI@2
  inputs:
    command: 'test'
    arguments: '--configuration Release /p:CollectCoverage=true'

# Deploy to Azure Web App
- task: AzureWebApp@1
  inputs:
    azureSubscription: 'subscription'
    appName: 'app-name'
    package: '$(Pipeline.Workspace)/**/*.zip'

# Create release annotation
- task: CreateWorkItem@1
  inputs:
    workItemType: 'Issue'
    title: 'Production Release: v1.0.0'

# Send notification
- task: SendEmail@1
  inputs:
    to: ' [email protected] '
    subject: 'Deployment Complete'

Troubleshooting

Build Fails Without Clear Error:

  • Check agent logs in pipeline run details
  • Verify agent pool has required software installed
  • Test build locally before pushing to Azure DevOps
  • Check environment variables and secrets configuration

Pull Request Won't Complete:

  • Verify all required reviewers have approved
  • Check that build validation passes
  • Ensure no active comments blocking completion
  • Confirm you have permission to complete PR

Pipeline Doesn't Trigger:

  • Check trigger configuration in YAML or UI
  • Verify branch matches trigger conditions
  • Check if pipeline is enabled/paused
  • Review commit filters and path filters

Tests Pass Locally but Fail in Pipeline:

  • Agent may have different environment/dependencies
  • Check test output logs for actual error
  • Verify test data and fixtures are available
  • Consider environment-specific configuration

Integration Tips

  • Link Azure DevOps work items to GitHub when using GitHub repos
  • Integrate with Slack for notifications
  • Use Azure Artifacts for package management
  • Configure security scanning in pipelines
  • Set up continuous deployment with environment approvals
  • Monitor pipeline metrics and trends over time

适合场景

01

Azure 资源规划

02

云服务升级

03

基础设施检查

04

企业云环境自动化

能力概览

能力 1

整理 Azure 服务操作流程

能力 2

提示 CLI/MCP 前置条件

能力 3

辅助云资源检查和规划

能力 4

保留官方服务来源线索

平台分布

Claude Code

26.79%
按下载量换算40

windsurf

23.71%
按下载量换算35

OpenCode

16.67%
按下载量换算25

Codex

12.04%
按下载量换算18

Antigravity

7.23%
按下载量换算11

Gemini CLI

3.66%
按下载量换算5

安全审计

暂无安全审计结果可展示。

权限和风险

调用外部服务

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills