MCP HubMCP Hub
返回技能列表

orchestrating-test-workflows

jeremylongshore
更新于 Today
51 次查看
409
51
409
在 GitHub 上查看
aitestingautomation

关于

This skill enables Claude to orchestrate complex test workflows using a dedicated plugin. It allows defining test execution graphs with dependencies, running tests in parallel, and intelligently selecting tests based on code changes. Use it for managing test orchestration, dependency management, parallel execution, and smart test selection in CI/CD pipelines.

技能文档

Overview

This skill empowers Claude to manage and execute complex test suites efficiently. It leverages the test-orchestrator plugin to handle test dependencies, parallel execution, and intelligent test selection, resulting in faster and more reliable testing processes.

How It Works

  1. Workflow Definition: Claude uses the plugin to define the test workflow, specifying dependencies between tests.
  2. Parallelization: The plugin identifies independent tests and executes them in parallel to reduce overall execution time.
  3. Smart Selection: Based on code changes, the plugin selects only the affected tests to run, minimizing unnecessary execution.

When to Use This Skill

This skill activates when you need to:

  • Optimize test execution time.
  • Manage dependencies between tests.
  • Run only relevant tests after code changes.

Examples

Example 1: Optimizing Regression Testing

User request: "Orchestrate the regression tests for the user authentication module after the recent code changes."

The skill will:

  1. Use the test-orchestrator plugin to identify the tests affected by the changes in the user authentication module.
  2. Execute those tests in parallel, respecting any dependencies.

Example 2: Setting up a CI/CD Pipeline

User request: "Set up a test workflow for the CI/CD pipeline that runs unit tests, integration tests, and end-to-end tests with appropriate dependencies."

The skill will:

  1. Define a test workflow using the test-orchestrator plugin, specifying the order and dependencies between the different test suites (unit, integration, end-to-end).
  2. Configure the pipeline to trigger the orchestrated test execution upon code commits.

Best Practices

  • Dependency Mapping: Clearly define dependencies between tests to ensure correct execution order.
  • Granularity: Break down large test suites into smaller, more manageable units for better parallelization.
  • Change Tracking: Integrate the test-orchestrator with version control to accurately identify affected tests.

Integration

This skill integrates with the test-orchestrator plugin and can be incorporated into CI/CD pipelines. It can also be used in conjunction with other code analysis tools to further refine test selection.

快速安装

/plugin add https://github.com/jeremylongshore/claude-code-plugins-plus/tree/main/test-orchestrator

在 Claude Code 中复制并粘贴此命令以安装该技能

GitHub 仓库

jeremylongshore/claude-code-plugins-plus
路径: backups/skills-migration-20251108-070147/plugins/testing/test-orchestrator/skills/test-orchestrator
aiautomationclaude-codedevopsmarketplacemcp

相关推荐技能

llamaguard

其他

LlamaGuard是Meta推出的7-8B参数内容审核模型,专门用于过滤LLM的输入和输出内容。它能检测六大安全风险类别(暴力/仇恨、性内容、武器、违禁品、自残、犯罪计划),准确率达94-95%。开发者可通过HuggingFace、vLLM或Sagemaker快速部署,并能与NeMo Guardrails集成实现自动化安全防护。

查看技能

sglang

SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。

查看技能

evaluating-llms-harness

测试

该Skill通过60+个学术基准测试(如MMLU、GSM8K等)评估大语言模型质量,适用于模型对比、学术研究及训练进度追踪。它支持HuggingFace、vLLM和API接口,被EleutherAI等行业领先机构广泛采用。开发者可通过简单命令行快速对模型进行多任务批量评估。

查看技能

langchain

LangChain是一个用于构建LLM应用程序的框架,支持智能体、链和RAG应用开发。它提供多模型提供商支持、500+工具集成、记忆管理和向量检索等核心功能。开发者可用它快速构建聊天机器人、问答系统和自主代理,适用于从原型验证到生产部署的全流程。

查看技能